WO2017090044A1

WO2017090044A1 - Systems and methods for mri based imaging of peripheral nerves

Info

Publication number: WO2017090044A1
Application number: PCT/IL2016/051267
Authority: WO
Inventors: Ilan KRYMKA; Assaf Dekel; Dan Rappaport; Anat GRINFELD
Original assignee: Tpm Medical Systems Ltd.
Priority date: 2015-11-26
Filing date: 2016-11-24
Publication date: 2017-06-01

Abstract

An imaging method, comprising: selecting a first and a second set of parameters for instructing a first and a second set of magnetic resonance imaging (MRI) sequences for creating first and second raw MRI images of at least a first and a second anatomical region, the first and second set of parameters selected as a combination for processing first and second raw MRI images to define contrast that delineates peripheral nerve(s) of a patient according to the tissue architecture of the first and second anatomical regions; processing the first and second MRI images based on the selected combination of the first and second set of parameters, along different 2D and/or 3D viewing planes to delineate peripheral nerve(s) within the first and second anatomical regions; tracing the peripheral nerve(s) along the first and second anatomical regions; and rendering for presentation a 3D image delineating the location of the peripheral nerve(s).

Description

SYSTEMS AND METHODS FOR MRI BASED IMAGING OF PERIPHERAL

NERVES

RELATED APPLICATION This application claims the benefit of priority under 35 USC § 119(e) of U.S.

Provisional Patent Application No. 62/260,274 filed November 26, 2015, the contents of which are incorporated herein by reference in their entirety.

BACKGROUND

The present invention, in some embodiments thereof, relates to magnetic resonance imaging (MRI) and, more specifically, but not exclusively, to systems and methods for imaging peripheral nerves using MRI.

Over the past two decades technical advances in MRI have made dramatic differences in the diagnosis, understanding, and treatment of central nervous system (CNS) anatomy, physiology, and patho-physiology. Traditionally, the focus was placed on the identification of central nerves. In contrast, parallel advances in peripheral nerve imaging have not occurred.

SUMMARY

According to a first aspect, a method for imaging at least one peripheral nerve of a patient comprises: receiving a designation of a first anatomical region of a body of the patient and a second anatomical region each including the at least one peripheral nerve; selecting a first set of parameters for instructing a first set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of first raw MRI images of at least the first anatomical region, the first set of parameters selected as a combination for processing the plurality of first raw MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the first anatomical region; selecting a second set of parameters for instructing a second set of a plurality of MRI sequences for creating a plurality of second MRI images of at least the second anatomical region, the second set of parameters selected as a combination for processing the plurality of second MRI images to for define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the second anatomical region; processing the plurality of first MRI images based on the selected combination of the first set of parameters, along different 2D and/or 3D viewing planes to delineate the at least one peripheral nerve within the first anatomical region; processing the plurality of second MRI images based on the selected combination of the second set of parameters, to delineate the at least one peripheral nerve within the second anatomical region; tracing the at least one peripheral nerve along the first anatomical region and the second anatomical region of the body; and rendering for presentation a 3D image delineating the location of the at least one peripheral nerve within the first anatomical region and the second anatomical region.

The systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein improve the performance of existing MRI machines, by delineating the location of peripheral nerves (optionally including small branches of the peripheral nerve(s)) within MRI images acquired using the existing MRI machine. The peripheral nerve(s) is detected, localized, traced, and/or visualized. The peripheral nerve is visualized, and explicitly visible in the acquired MRI images. In contrast, using existing MRI images acquired using standard methods, the peripheral nerves cannot be directly visualized. Instead, abnormalities of the peripheral nerves are indirectly inferred based on other anatomical features. For example, MRI images are acquired to rule out (or detect) compression of neural bundles by surrounding structures, for example, by depiction of soft tissue tumors, hematomas, cysts, anatomical variants such as hypertrophic muscles, ligamentous restriction or impingement due to scarring. The compression of the bundle may be inferred without precisely depicting the nerve in the MRI image.

According to a second aspect, a system for imaging at least one peripheral nerve of a patient, comprising: a non-transitory memory having stored thereon a code for execution by at least one processor adapted to execute the code fonreceiving a designation of a first anatomical region of a body of the patient and a second anatomical region each including the at least one peripheral nerve; selecting a first set of parameters for instructing a first set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of first MRI images of at least the first anatomical region, the first set of parameters selected as a combination for processing the plurality of first MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the first anatomical region; selecting a second set of parameters for instructing a second set of a plurality of MRI sequences for creating a plurality of second MRI images of at least the second anatomical region, the second set of parameters selected as a combination for processing the plurality of second MRI images to for define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the second anatomical region; processing the plurality of first MRI images based on the selected combination of the first set of parameters, along different 2D and/or 3D viewing planes to delineate the at least one peripheral nerve within the first anatomical region; processing the plurality of second MRI images based on the selected combination of the second set of parameters, to delineate the at least one peripheral nerve within the second anatomical region; tracing the at least one peripheral nerve along the first anatomical region and the second anatomical region of the body; and rendering for presentation a 3D image delineating the location of the at least one peripheral nerve within the first anatomical region and the second anatomical region.

According to a third aspect, a computer program product comprising a non- transitory computer readable storage medium storing program code thereon for implementation by at least one processor of a system for imaging at least one peripheral nerve of a patient, comprising: instructions for receiving a designation of a first anatomical region of a body of the patient and a second anatomical region each including the at least one peripheral nerve; instructions for selecting a first set of parameters for instructing a first set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of first MRI images of at least the first anatomical region, the first set of parameters selected as a combination for processing the plurality of first MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the first anatomical image; instructions for selecting a second set of parameters for instructing a second set of a plurality of MRI sequences for creating a plurality of second MRI images of at least the second anatomical region, the second set of parameters selected as a combination for processing the plurality of second MRI images to for define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the second anatomical image; instructions for processing the plurality of first MRI images based on the selected combination of the first set of parameters, along different 2D and/or 3D viewing planes to delineate the at least one peripheral nerve within the first anatomical region; instructions for processing the plurality of second MRI images based on the selected combination of the second set of parameters, to delineate the at least one peripheral nerve within the second anatomical region; instructions for tracing the at least one peripheral nerve along the first anatomical region and the second anatomical region of the body; and instructions for rendering for presentation a 3D image delineating the location of the at least one peripheral nerve within the first anatomical region and the second anatomical region.

In a first possible implementation form according to the first, second, or third aspects, each of the first and second set of parameters include a first sub-set of parameters for imaging a large field of view (FOV), and a second sub-set of parameters for imaging a small (FOV) with higher resolution than the large FOV, wherein the first sub-set of parameters and the second sub-set of parameters are selected as the combination, wherein each of the first and second set of MRI sequences each acquire a first sub-set of MRI images having a large FOV and a second sub-set of MRI images having a small FOV.

In a second possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, each of the first and second set of parameters include a first sub-set of parameters defining a first MRI sub-sequence for imaging using a set of coils, and a second sub-set of parameters defining a second MRI sub-sequence for imaging using the set of coils, wherein the first sub-set of parameters and the second sub-set of parameters are selected as the combination, wherein each of the plurality of first MRI images and the plurality of second MRI image includes a first sub- set of MRI images captured the set of coils according to the first sub- sequence based on the first sub- set of parameters and a second sub-set of MRI images captured using the set of coils according to the second sub-sequence based on the second sub-set of parameters.

In a third possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, each of the first and second set of parameters include a first sub-set of parameters defining a first MRI sub-sequence for imaging using volumetric coils, and a second sub-set of parameters defining a second MRI sub-sequence for imaging using surface coils, wherein the first sub-set of parameters and the second subset of parameters are selected as the combination, wherein each of the plurality of first MRI images and the plurality of second MRI image includes a first sub-set of MRI images captured using the volumetric coils according to the first sub-sequence based on the first sub-set of parameters and a second sub-set of MRI images captured using the surface coils according to the second sub-sequence based on the second sub-set of parameters.

In a fourth possible implementation form according to the third possible implementation form, the first sub-set of parameters define a spoiled 3D gradient echo (GRE) first MRI sub-sequence, and the second set of parameters define a spoiled transverse-coherence second MRI sub- sequence, wherein the first sub- set of parameters are selected to create Tl weighted 3D images using interpolation and/or partial Fourier techniques combined with water excitation, to create a high signal-to-noise ratio (SNR) contrast, wherein the first set of parameters include echo time (TE) < 10 milliseconds (ms), repetition time (TR) < 15 ms, flip angle (FA) < 30, and slice width < 0.8mm, wherein the second sub- set of parameters are selected to create a Contrast-Enhanced Fast Field Echo sequence with a low-flip angle and a rapid repetition of the basic sequence using repetition time shorter than typical Tl relaxation time of protons in biologic tissue to create a spoiled transverse coherence having T1/T2 contrast, wherein the second set of parameters include TE< 10ms, TR < 15ms, FA < 30, slice width < 0.8mm, and further comprising subtracting the acquired first sub-set of MRI images and second sub-set of MRI images, thereby distinguishing between small nerve fibers and small vessels that appear as tissues with similar contrast.

In a fifth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: receiving a designation of another anatomical region of a body of the patient including the at least one peripheral nerve; selecting another set of parameters for instructing another set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of another MRI images of the another anatomical region, the another set of parameters selected as a combination for processing the plurality of another MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the another anatomical image; processing the plurality of another MRI images based on the selected combination of the another set of parameters, to delineate the at least one peripheral nerve within the another anatomical region; further tracing the at least one peripheral nerve along the another anatomical region; and updating the rendering for presentation of the 3D image that further delineates the location of the at least one peripheral nerve within the another anatomical region.

In a sixth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: processing the plurality of MRI images, with different acquisition planes of the first anatomical region to identify a branch of the at least one peripheral nerve, and wherein tracing comprises tracing at least one designated branch of the at least one peripheral nerve.

In a seventh possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, tracing of the at least one peripheral nerve is performed at least one of: in an upstream direction towards a synapse with the central nervous system, and in a downstream direction towards innervations of a target end organ.

In an eighth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, each of the first and second set of parameters are independently selected according to the respective tissue architectures of the first and second anatomical regions.

In a ninth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the first and second anatomical regions are contiguous with each other.

In a tenth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the first and second anatomical regions have a gap between each other.

In an eleventh possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the first and second anatomical regions overlap each, wherein the overlap region is less than 50% of the surface area of the regions.

In a twelfth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the first and second anatomical regions demonstrate an anatomical bifurcation of the at least one peripheral nerve, wherein a downstream or a lateral split is demonstrated in less than 50% of the surface area of the respective first and second anatomical regions, wherein the tracing is performed to delineate the portions of the anatomical bifurcations are belonging to a common at least one peripheral nerve.

In a thirteenth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: identifying at least one anatomical structure located in proximity to the expected location of the at least one peripheral nerve in each of the first and second anatomical regions, and selecting the respective first and second set of parameters according to the identified at least one anatomical structure to define contrast between the at least one anatomical structure and the at least one peripheral nerve that delineates the at least one peripheral nerve.

In a fourteenth possible implementation form according to the thirteenth possible implementation form, the at least one anatomical structure is identified by correlating each of the first and second anatomical regions to a predefined anatomical model.

In a fifteenth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the first and second set of parameters are selected for defining contrast that delineates the at least one peripheral nerve that includes one or more members selected from the group consisting of: cross sectional dimension less than about 1 millimeter (mm), high anatomical variability in location between patients, predominantly non-myelinated, external from a vein-artery-nerve (VAN) structure.

In a sixteenth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the designation of the first and second anatomical regions is performed by at least one of: manual user input entered using a graphical user interface, and code instructions executed by at least one processor that automatically identifies the first and second anatomical regions based on processing of at least one image of the patient.

In a seventeenth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: anatomically aligning the at least one peripheral nerve traced in the first anatomical region with the at least one peripheral nerve traced in the second anatomical region.

In an eighteenth possible implementation form according to the seventeenth possible implementation form, the anatomically aligning is performed by image processing code executed by at least one processor that automatically registers anatomical features of at least one of the plurality of first MRI images and at least one of the plurality of second MRI images.

In a nineteenth possible implementation form according to the eighteenth possible implementation form, the method, system, and/or computer program product further comprise processing the at least one of the plurality of first MRI images and the at least one of the plurality of second MRI images to account for differences that define contrast for different tissue types, for improving the process of the automatic registration of the at least one of the plurality of first MRI images and the at least one of the plurality of second MRI images.

In a twentieth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: registering at least one of the plurality of first MRI images with at least one of the plurality of second MRI images, and wherein the tracing is performed using the registered MRI images.

In a twenty first possible implementation form according to the twentieth possible implementation form, the method, system, and/or computer program product further comprise simulating the location of the at least one nerve within the registered

MRI images, and wherein tracing comprises searching for the at least one nerve within the registered MRI images according to the simulated location.

In a twenty second possible implementation form according to the twentieth possible implementation form, the method, system, and/or computer program product further comprise segmenting at least one branch of the at least one peripheral nerve within the registered MRI images by performing at least one of horizontal edge detection and longitudinal edge detection of the traced at least one peripheral nerve that delineates a curved path of the at least one peripheral nerve.

In a twenty third possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: the first and second set of parameters are selected using a statistical classifier that is trained using a training set of MRI images from a population of patients that include defined contrast that delineates the at least one peripheral nerve of each respective patient for the respective first and second anatomical regions, and associated set of parameters used to define MRI sequences for acquiring the respective training

MRI images.

In a twenty fourth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: the processing of one or both of the plurality of first MRI images and the processing of the plurality of second MRI image is performed by one or more members selected from the group consisting of: linear weighted combination of a plurality of MRI images, non-linear combination of a plurality of weighted MRI images using multiple derivates of a certain image and at least one operator, subtraction of a certain MRI image from another certain MRI image, application of an operator to a certain MRI image determined locally by at least one derivative of another certain MRI image.

In a twenty fifth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: the processing of one or both of the plurality of first MRI images and the processing of the plurality of second MRI image is performed based on diffusion tensor imaging (DTI) with tractography.

In a twenty sixth possible implementation form according to the first, second, or third aspects as such or according to any of the preceding implementation forms of the first, second, or third aspects, the method, system, and/or computer program product further comprise: the first set and the second set of the plurality of magnetic resonance imaging (MRI) sequences are applied during a common scan session to acquire the first MRI images of the first anatomical region and the second MRI images of the second anatomical regions during the common scan session.

Unless otherwise defined, all technical and/or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention pertains. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of embodiments of the invention, exemplary methods and/or materials are described below. In case of conflict, the patent specification, including definitions, will control. In addition, the materials, methods, and examples are illustrative only and are not intended to be necessarily limiting.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

Some embodiments of the invention are herein described, by way of example only, with reference to the accompanying drawings. With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of embodiments of the invention. In this regard, the description taken with the drawings makes apparent to those skilled in the art how embodiments of the invention may be practiced. In the drawings:

FIG. 1 is a flowchart of a method for imaging one or more peripheral nerves of a patient using an MRI machine, in accordance with some embodiments of the present invention;

FIG. 2 is a block diagram of components of a system that selects parameters for

MRI sequences for acquiring MRI images for two or more anatomical regions through which one or more peripheral nerves pass, and for rendering an image that delineates the one or more peripheral nerves based on processing of the acquired MRI images at each of the anatomical regions, in accordance with some embodiments of the present invention;

FIG. 3 is a flowchart of another method for delineating peripheral nerve(s) in images created using an MRI, in accordance with some embodiments of the present invention; and

FIG. 4 includes an MRI image of a knee region captured using a standard imaging protocol, and another MRI image of the knee region captured by applying the selected parameters that delineate the peripheral nerves, in accordance with some embodiments of the present invention.

DETAILED DESCRIPTION

The present invention, in some embodiments thereof, relates to MRI imaging and, more specifically, but not exclusively, to systems and methods for imaging peripheral nerves using MRI.

An aspect of some embodiments of the present invention relates to systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) that compute 3D image(s) that delineate one or more peripheral nerves based on processing of MRI images acquired using sets of different MRI sequences applied to multiple different anatomical regions through which the peripheral nerve(s) passes. The nerve passes through at least two anatomical regions that may be covered in a common scan session (e.g., during a common MRI scan) and/or may be independently imaged (e.g., using two or more separate scans, performed during different scan sessions, and/or performed during the common MRI scan session as independent scans). At each anatomical region, a different set of parameters may be selected to instruct a respective set of MRI sequences for acquiring a set of MRI images for the respective anatomical region. The parameters are selected as a combination, to acquire the set of MRI images that are processed using image processing methods based on the selected combination, to delineate the peripheral nerve of the patient. The parameters for the respective anatomical region are selected according to the architecture and/or features of the tissue(s) in the anatomical region that is in near proximity to the peripheral nerve. In each anatomical region, the peripheral nerve is located next to different tissue, for example, bone, lung, muscle, fat, blood vessels, intestine, heart, and kidney. The parameters are independently selected for each anatomical region, to achieve image contrast between the peripheral nerve and the nearby tissue of the anatomical region. The processing of the MRI images obtained at each anatomical region is performed according to the selected combination of parameters, for example, at one anatomical region MRI images are subtracted, while at another anatomical region MRI images are combined using a weighed linear combination. The nerve(s) is traced though the multiple anatomical regions, optionally to identify one or more branch nerves. An image, optionally a 3D image, of the peripheral nerve(s) located within the multiple anatomical regions is rendered based on the tracing of the nerve(s) through the anatomical regions. Effectively, the 3D image of the peripheral nerve(s) is rendered by piecing together the data delineating the location of the nerve(s) at each anatomical region, where the delineation of the nerve(s) at each anatomical region is determined using different MRI images having different contrast based on MRI sequences processed using different image methods. The image may be based on the MRI imaging data of the anatomical regions, optionally based on registration of the MRI imaging data from neighboring and/or overlapping anatomical regions.

Optionally, each anatomical region is imaged using a large field of view (FOV) and a small FOV with higher resolution than the large FOV. Alternatively or additionally, each anatomical region is imaged with volumetric coils and with surface coils. The surface coils may correspond to the anatomical regions, for example, the surface coils may be moved to each anatomical region, or a different set of surface coils may be placed at each anatomical region to image the respective anatomical region. Alternatively or additionally, MRI images are acquired for two or more of the anatomical regions using a common set of coils (e.g., the surface coils, the volumetric coils). The MRI images for the two or more anatomical regions may be acquired during a common scan session. For example, a large MRI image that includes both (or more) anatomical regions is acquired using the common set of coils. The large MRI image may be processed to extract the first anatomical region and the second anatomical region from the large MRI image. Each anatomical region may be independently processed to delineate the peripheral nerve(s).

The systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein present a technical solution to the technical problem of delineating peripheral nerves using MRI images. The technical problem relates to detecting, localizing, tracing, and/or visualizing the peripheral nerve(s) and optionally the small branch(es) of the peripheral nerve(s). In general, normal nerves appear isointense to the surrounding tissues on Tl and T2 weighted MRI scans, making their detection on MRI images difficult. Peripheral nerves are especially difficult to delineate on MRI images in a manner such that the peripheral nerves are visible on the MRI image.

Peripheral nerves are structurally different than central nerves (e.g., in terms of size, distribution, anatomical structure, and/or biological composition), and therefore methods used to capture MRI images of central nerves cannot be applied to capture MRI images of peripheral nerves. In one example, central nerves are large, having a diameter of 2 or 3 millimeters (mm) or greater, and include surrounding fat that cause high signals in Tl weighted images, allowing easy identification of the central nerves. In contrast, many peripheral nerve fibers are small in diameter, less than about 1 mm, and/or lack surrounding fat (e.g., nerve fibers that about muscle or have an intramuscular course) making their detection difficult, even when such nerves have larger diameters. In another example, the nerves of the CNS have distinct anatomical locations and/or connect to main organs through a relatively small number of nerves. In contrast, the PNS nerves are spread out from the CNS, having a large variability in location, and innervate end organs with a relatively large number of nerves. In yet another example, CNS nerves are myelinated and include Ranvier nodes, which in contract the PNS nerves are predominantly non-myelinated. In yet another example, CNS nerves are located together with an artery and vein by being included in an anatomical configuration referred to as VAN (vein, artery, nerve). In contrast, peripheral nerves are independent of veins and arteries, and not included in the VAN structure.

Delineating the actual location of the peripheral nerve(s) on MRI images may be used, for example, to improve diagnosis of medical conditions, plan treatment, and guide treatment such as catheter ablation. The detection and delineation of the peripheral nerves may be used, for example, for the planning and guidance of treatment procedures such as genicular neurotomy using radiofrequency (RF) ablation catheters. The image that includes the peripheral nerve localization may be used for planning the optimal path of the ablation catheter in aspects of procedure efficacy and safety. For example, better efficacy is determined by improvement of selection of the angle between the ablation catheter and the targeted peripheral nerve. The angle determines the length of the nerve injury achieved by applying the ablation energy. The angle selected based on the image delineating the peripheral nerve plays a role in selection of a parameter that determines regeneration of the nerve. Regeneration of the nerve may cause neuroma formation and reoccurrence of pain. Another example of improving safety of the procedure based on the image that delineates the location of the peripheral nerve is based on planning a penetration path that does not injure important anatomical structures at the penetration phase and that position the tip of the catheter such that the region of ablation does not include any important anatomical structures beside the targeted peripheral nerve.

The systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein generate new data in the form of rendered 3D images that delineate the location of one or more peripheral nerves.

The systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein tie mathematical operations (e.g., selection of the parameters that define the MRI sequences, alignment of MRI images of different anatomical regions, processing of the aligned images to trace the peripheral nerve(s)) to the ability of processor(s) to execute code instructions. The systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein are tied to physical real-life components, including an MRI machine.

The systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein provide a unique, particular, and advanced technique of acquiring MRI images, and processing the MRI images to delineate the location of peripheral nerve(s).

Accordingly, the systems and/or methods (e.g., implemented as code instructions stored in a data storage device executed by one or more processors) described herein are necessarily rooted in computer technology to overcome an actual technical problem arising in the technical field of MRI imaging.

Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and the arrangement of the components and/or methods set forth in the following description and/or illustrated in the drawings and/or the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways.

The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.

The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non- exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.

Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction- set- architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

As referred to herein, the term CNS means the component of the nervous system located within the brain (i.e., neurons) and spinal cord (i.e., nerves).

As referred to herein, the term PNS or peripheral nerve(s) means the component of the nervous system (e.g., nerves and/or ganglia) located externally to the brain and spinal cord. It is noted that some peripheral nerves may include a relatively small region within the spinal cord and/or CNS. The term PNS or peripheral nerve(s) refers to the nerves located distally from the CNS (e.g., the nerves that innervate the end organ or tissue) which excludes main tracts of the PNS that are more similar to the CNS nerves in terms of appearance on MRI images than the distally located peripheral nerves that are difficult to delineate on MRI images.

As referred to herein, the term peripheral nerve means a nerve of the PNS, including, for example, a nerve of the autonomic nervous system (ANS), a nerve of the enteric nervous system (ENS), a motor nerve, a sensor nerve, a sympathetic nerve, a parasympathetic nerve, an afferent nerve, an efferent nerve, a nerve innervating an end organ, an intermediary nerve connecting to the nerve innervating the end organ, cranial nerves, and dermatome nerves.

As used herein, the term peripheral nerve(s) may sometimes relate to one or more parts of the nerve that have different anatomical names, but that are physically part of a single continuous structure. For example, the sciatic nerve divides into the tibial nerve and the common peroneal nerve, and further branching into the superior and inferior genicular branches of the knee. Tracing and/or delineating the sciatic nerve may include tracing and/or delineating the tibial nerve and/or common peroneal nerve, and/or superior genicular branch and/or inferior genicular branch.

It is noted that the term peripheral nerve as used herein excludes large PNS neural structures that are delineated using conventional MRI imaging methods, for example, the carotid body, large ganglions, a plexus, and the sympathetic trunk. However, the axons of the nerves that synapse, or axons of nerves that have cell bodies within the large neural structures are included within the meaning of the term peripheral nerve, since such axons cannot be properly delineated using conventional MRI imaging methods.

As used herein, sometimes the term peripheral nerve and peripheral nerves are interchanged, and do not necessarily imply either only a single nerve or multiple nerves.

Reference is now made to FIG. 1, which is a flowchart of a method for imaging one or more peripheral nerves of a patient using an MRI machine, in accordance with some embodiments of the present invention. Reference is also made to FIG. 2, which is a block diagram of components of a system 200 that selects parameters for MRI sequences for acquiring MRI images for two or more anatomical regions through which one or more peripheral nerves pass, and for rendering an image that delineates the one or more peripheral nerves based on processing of the acquired MRI images at each of the anatomical regions, in accordance with some embodiments of the present invention. System 200 may implement the acts of the method described with reference to FIG. 1, optionally by one or more processors 202 of a computing device 204 executing code instructions stored in a program store 206. System 200 may be used to train the classifier (or other machine learning code) to perform the selection of the parameters for the MRI sequences for each anatomical region.

Computing device 204 may be implemented as a data analysis system (DAS), for example, a client terminal, a server, a radiology workstation, a computing cloud, a mobile device, a desktop computer, a thin client, a Smartphone, a Tablet computer, a laptop computer, a wearable computer, glasses computer, and a watch computer. Computing unit 204 may be implemented as, for example, software installed on an existing computing system, a hardware card installed within an existing computing system, an external component connected to an existing system, and/or an independent computing unit. For example, computing device 204 may be implemented as the computing system that controls the gradient coils and/or RF pulses within existing MRI systems (e.g., located in the machine room next to the magnetic room), and/or collects thee acquired signals. Computing device 204 may include locally stored software that performs one or more of the acts described with reference to FIG. 1, and/or may act as one or more servers (e.g., network server, web server, radiology server, a computing cloud) that provides services (e.g., one or more of the acts described with reference to FIG. 1) to one or more client terminal 209 (e.g., remotely located radiology workstations, remotely located MRI machines) over a network 210, for example, providing software as a service (SaaS) to the client terminal(s) 209, providing an application for local download to the client terminal(s) 209, and/or providing functions using a remote access session to the client terminal 209, such as through a web browser. As depicted herein, client terminal 209 may be interchanged with MRI 212, for example, computing device 204 computes the set of parameters and transmits the computed set of parameters to MRI 212 over network 210.

Computing device 204 selects the sets of parameters for the MRI sequences (as described herein) using parameter selection code 206A stored in program store 206). The selected parameters may be stored in a parameter repository 214, which is a storage device associated, for example, with the MRI (e.g., memory of the MRI), with the computing device 204 (e.g., stored in a data repository 208), and/or an external storage device (e.g., storage server, computing cloud, a hard drive). MRI 212 executes MRI sequences based on the sets of parameters (as described herein).

MRI 212 may be an existing standard MRI machine located, for example, in a hospital, and/or radiology clinic. MRI 212 may include two or more sets of coils 216A- B for generating the sets of MRI images using the combination of MRI sequences according to the selected parameters for each anatomical region of the patient. For example, coils 216A include volume coils, and coils 216B include surface coils. The sets of MRI images obtained for each anatomical region may be stored in an MRI image repository 218, which is a data storage device, for example, associated with the MRI 212, associated with computing device 204 (e.g., data repository 208), and/or an external data storage device (e.g., storage server, computing cloud, hard drive). A set of MRI training images 220 (e.g., acquired by MRI 212, by other MRI machines, and/or obtained from a library of MRI images) used to train the classifier that selects the parameters (as described herein) may be stored in MRI image repository 218 and/or at another data storage device, for example, a server 222 accessibly by computing device 204 over network 210.

As used herein, the term MRI image(s) refers to the MRI images that are outputted by the MRI machine, and/or MRI images that are reconstructed based on the imaging data acquired by the MRI machine. The term MRI image(s) may be interchanged with the term raw MRI image(s), or reconstructed raw MRI image(s). The MRI image(s) are reconstructed from raw data (collected by the MRI machine) which represents the imaged anatomy in £-space.

It is noted that as described herein, MRI 212 represents the computing device and/or stored code instructions executed by one or more processors that reconstruct the MRI image(s) from the acquired MR signal (acquired as a collection of frequencies). The reconstructed MRI image(s) may represent raw MRI images, for example, in DICOM (Digital Imaging and Communications in Medicine) format that includes the header with the acquisition parameters, and a 2D and/or 3D viewable image. The raw MRI images may be stored in MRI image repository 218. The reconstructed raw MRI images may be processed to delineate the peripheral nerve, for example, as described with reference to block 108. Computing device 204 may receive the MRI images using one or more MRI interfaces 224, for example, a wire connection (e.g., physical port), a wireless connection (e.g., antenna), a network interface card, other physical interface implementations, and/or virtual interfaces (e.g., software interface, application programming interface (API), software development kit (SDK)).

Processor(s) 202 may be implemented, for example, as a hardware processor, as a central processing unit(s) (CPU), a graphics processing unit(s) (GPU), field programmable gate array(s) (FPGA), digital signal processor(s) (DSP), and application specific integrated circuit(s) (ASIC). Processor(s) 202 may include multiple processors (homogenous or heterogeneous), which may be arranged for parallel processing, as clusters and/or as one or more multi core processing units, and/or as a computing cloud.

Program store 206 stores code instructions implementable by processor(s) 202, for example, a random access memory (RAM), read-only memory (ROM), and/or a storage device, for example, non-volatile memory, magnetic media, semiconductor memory devices, hard drive, removable storage, and optical media (e.g., DVD, CD- ROM). For example, program store 206 stores parameter selection code 206 A that performs the selection of the parameters (as described herein), and image processing code 206B that performs the processing of the MRI images, traces the nerve(s), and renders the 3D image (as described herein).

Computing device 204 may include a data repository 208 for storing data, for example, procedure planning code 208A for planning the procedure using the image with delineated peripheral nerve, the rendered image with delineated peripheral nerve, and/or other data as described herein. Data repository 208 may be implemented as, for example, a memory, a local hard-drive, a removable storage unit, an optical disk, a storage device, and/or as a remote server 222 and/or computing cloud (e.g., accessed over network 210). It is noted that parameter selection code 206A and/or image processing code 206B may be stored in data repository 208, with executing portions loaded into program store 206 for execution by processor(s) 202.

Program store 206 and/or data repository 208 (and/or other storage devices) may store additional data and/or code instructions for execution by processor(s) 202 to enable execution of the acts of the method described with reference to FIG. 1, for example, acquisition properties, pulse specification, reconstruction protocol. Computing device 204 may include data interface 228, optionally a network interface, for connecting to network 210 and/or other data storing components, for example, one or more of, a network interface card, a wireless interface to connect to a wireless network, a physical interface for connecting to a cable for network connectivity, a virtual interface implemented in software, network communication software providing higher layers of network connectivity, and/or other implementations.

Computing device 204 includes or is in communication with a user interface 230 allowing a user to define anatomical regions, mark anatomical features used in the process of selecting the parameters and/or tracing the peripheral nerve, and/or to view the rendered 3D image that includes the delineated peripheral nerve. Exemplary user interfaces 230 include, for example, one or more of, a touchscreen, a display, a keyboard, a mouse, and voice activated software using speakers and microphone.

At 102, a designation of multiple anatomical regions of the body of the patient is made. The anatomical regions are designated to include the course of the peripheral nerve(s). For example, to image the ulnar nerve, the anatomical regions may include the upper arm, the elbow region, the forearm, and the hand. For example, to image the sciatic nerve, the anatomical regions may include the lower back, hip, thigh, and knee.

The size of the anatomical region may be based on the size of the volume that may be imaged by dedicated coils of the MRI machine (e.g., set of coils 216B). For example, about 10 centimeters (cm) X 8 cm, or about 15 cm X 15 cm, or about 42 cm X 25 cm, or other sizes.

The anatomical region may be defined within a larger image region acquired by the MRI machine. For example, multiple anatomical regions may be defined within a large region, for example, using the volume coils. For example, the MRI may acquire images of the entire arm or the entire body of the patient. The anatomical regions may be defined within the image of the entire arm or the body of the patient, to include the upper arm, the elbow region, the forearm and the hand.

The anatomical regions may be contiguous with each other. Alternatively or additionally, one or more of the anatomical regions are located with a gap between one another. Alternatively or additionally, one or more of the anatomical regions overlap one another. The overlap region may be, for example, less than 50% of the surface area of the one of the regions, of less than about 25%, or other values. The designation of the anatomical regions may be performed using one or more methods, for example, by manually moving the surface coils to correspond to each anatomical region, by placing each of multiple surface coils to correspond to each anatomical region (e.g., single-station or multi-station acquisition), manually entering data using user interface 230 (e.g., using a graphical user interface (GUI)) by selecting a region on an image that includes the anatomical region(s), and/or code instructions executed by the processor(s) that automatically identify the anatomical regions based on processing of one or more images of the patient (e.g., based on identification of anatomical features).

The anatomical regions may be designated based on the type of tissue that is next to the peripheral nerve(s), for example, bone, muscle, tendon, lung, heart, blood vessel, fat, intestine.

Optionally, the user designates the target peripheral nerve(s) for delineating. For example, the user manually enters the name of the peripheral nerve(s), and/or selects the peripheral nerve(s) based on location, and/or function, and/or part of the PNS, and/or target innervations, for example, using the GUI. Alternatively, the user does not explicitly designate the target peripheral nerve(s). In such as case, existing peripheral nerves within the anatomical region are delineated without necessarily focusing on certain target peripheral nerve(s). Alternatively, the target nerve(s) are predefined (e.g., by an anatomical model) based on the most clinically significant nerves. In such a case, the delineation is performed for the clinically significant nerves.

At 104, a set of parameters is selected for each of the anatomical regions (e.g., by parameter selection code 206A stored in program store 206, executed by processor(s) 202 of computational device 204). The parameters may be selected and/or computed in real-time (i.e., dynamically). The selection may be performed from a set of pre-defined parameters, for example, previously used parameters, that may be stored in parameter repository 214. The selected parameters may be stored in parameter repository 214. The set of parameters define instructions for a set of MRI sequences that create a set of MRI images of the respective anatomical region. MRI images are obtained in at least two planes. Each MRI sequence includes one or more radiofrequency (RF) pulses, and one or more magnetic gradient fields. Exemplary parameters include: echo time (TE), repetition time (TR), and flip angle (FA). MRI acquisition may be contiguous, or with a gap of about 50%- 100%, to provide a reasonable scan time.

The set of parameters are selected as a combination for processing the MRI images acquired using the set of MRI sequences, to define contrast within the processed images that delineates the peripheral nerve(s) according to the tissue architecture of each anatomical region.

Optionally, each set of parameter is associated with instructions for processing the MRI images acquired using the MRI sequences instructions by the set of parameters. The instructions instruct processing of the MRI images to obtain the desired contrast for delineating the peripheral nerve from the neighboring tissue.

Each set of parameters is independently selected for the respective anatomical region according to the tissue architecture and/or features of the respective anatomical region. Optionally, one or more anatomical structures and/or anatomical features located in proximity to the expected location of the peripheral nerve are identified. The peripheral nerve(s) may be preselected by the user, predefined clinically significant nerves (e.g., by an anatomical model), and/or may not be explicitly specified. The parameters are selected according to the identified anatomical structure and/or feature, to define contrast that differentiates between the anatomical structure and/or feature and the peripheral nerve(s) to delineate the peripheral nerve(s). The anatomical structure and/or feature may be automatically identified using code instructions that correlate the designated anatomical region to a predefined anatomical model labeled with anatomical structures and/or features and expected locations of peripheral nerve(s). The model may take into account anatomical variations of the peripheral nerve(s) between patients. For example, one set of parameters is selected for an anatomical region in which the peripheral nerve(s) passes next to bone, to define contrast that delineates the peripheral nerve from bone. Another set of parameters is selected for another anatomical region in which the peripheral nerve(s) passes next to muscle, to define contrast that delineates the peripheral nerve from muscle. Yet another set of parameters is selected for yet another anatomical region in which the peripheral nerve(s) passes next to a blood vessel, to define contrast that delineates the peripheral nerve from the blood vessel.

The set of parameters are may be selected to define contrast that delineates the peripheral nerve having one or more of the following exemplary properties: cross sectional dimension less than about 1 millimeter (mm), high anatomical variability in location between patients, predominantly non-myelinated, and located external from a vein-artery-nerve (VAN) structure.

Optionally, each set of parameters for each anatomical region is selected using a statistical classifier, or other machine learning method. As used herein, the term statistical classifier may be interchanged with one or more other machine learning methods, for example, a cascade classifier, a neural network, a support vector machine, a set of rules, a regression model, a set of rules, k-nearest neighbor, a decision tree, and a table. The statistical classifier may receive an indication of the anatomical region (e.g., coordinates of the anatomical region, significant anatomical features, a quickly scanned image of the anatomical region) and optionally the desired peripheral nerve, and output the set of parameters.

The statistical classifier may output the instructions for processing the MRI images acquired using the MRI sequences instructions by the selected set of parameters. The instructions may be outputted in association with the selected parameters.

The statistical classifier may be trained using training MRI images 220 acquired from a population of patients. Each MRI image may be tagged with an indication of the contrast between one or more tissues types and the peripheral nerve(s) and/or tagged with an indication of whether the peripheral nerve(s) is sufficiently delineated in the image. MRI images may be classified according to anatomical regions. Each MRI image is associated with the set of parameters used to generate the MRI sequence that captured the respective image. The instructions used to process images to arrive that the MRI training image may be associated with the MRI image. The statistical classifier is trained to output a set of parameters suitable for generating contrast for delineating the peripheral nerve and optionally output the instructions for processing the acquired images, when a given anatomical region (or other indication such as tissue architecture that is in proximity to the peripheral nerve) is provided as input.

The trained classifier may be represented as a weighted model of three components, one component including the combination of parameters to generate the MRI sequences, another component including instructions for processing the MRI images (e.g., the integration of operators on the MRI images acquired using the combination of parameters), and yet another component including the corresponding anatomical structures (e.g., located in proximity to the peripheral nerve(s)) that is best delineated by the combination of MRI sequences.

The training of the classifier may be performed by computing device 204, or another computing device. The trained classifier may be stored in data repository 208 and/or program store 206, optionally accessed by parameter selection code 206A when performing the parameter selection. The training of the classifier may be performed by training code stored in data repository 208 and/or program store 206 executed by processor(s) 202 of computing device 204.

Optionally, the set of parameters for each anatomical region includes one sub-set of parameters for imaging a large field of view (FOV), and another sub-set of parameters for imaging a small (FOV) with higher resolution than the large FOV. The two sub-sets of parameters are selected as a combination, to instruct two sets of MRI sequences, one that acquires a sub-set of MRI images having a large FOV, and another that acquires a sub-set of MRI images having a small FOV. For example, to image the knee, a set of flex coils (e.g., knee coils) and another set of volume coils may be used.

Alternatively or additionally, the set of parameters for each anatomical region includes a sub-set of parameters defining an MRI sub-sequence for imaging using volumetric coils, and another sub-set of parameters defining another MRI sub-sequence for imaging using surface coils. The sub-sets are selected as a combination, to acquire a sub-set of MRI images using the volumetric coils, and another sub-set of MRI images captured using the surface coils.

Alternatively or additionally, a common set of coils (e.g., 216A or 216B) is used to image two or more anatomical regions, for example, all of the anatomical regions. In such a case, each set of parameters defines MRI images acquired using MRI sequences applied to the common set of coils. Optionally, each set of parameters defined for each respective anatomical region includes multiple sub-sets of parameters defining MRI sub-sequences for imaging using the common set of coils. The sub-sets of parameters may be selected as the combination. Optionally, the MRI images acquired for each respective anatomical region are acquired by applying the one or more sub- sets of parameters to the common set of coils.

In one example, a first sub-set of parameters define a spoiled 3D gradient echo (GRE) MRI sub-sequence, and a second sub-set of parameters define a spoiled transverse-coherence second MRI sub-sequence. The first sub-set of parameters are selected to create Tl weighted 3D images using interpolation and/or partial Fourier techniques (e.g., VIBE) combined with water excitation, to create a high signal-to-noise ratio (SNR) contrast, that may allow using the advantage of and excellent slice selective spatial resolution. The first set of parameters include TE < 10 milliseconds (ms), TR < 15 ms, FA < 30, and slice width < 0.8 mm. The first set of parameters provide a high resolution trace of the anatomical region, including the peripheral nerve(s), despite the small diameter of the nerve(s). The second sub-set of parameters are selected to create a Contrast-Enhanced Fast Field Echo sequence with a low-flip angle and a rapid repetition of the basic sequence using repetition time shorter than typical Tl relaxation time of protons in biologic tissue to create a spoiled transverse coherence having T1/T2 contrast. The second sub-set of parameters may provide real time MRI with high temporal resolution for dynamic imaging. The second sub- set of parameters include TE< 10ms, TR < 15ms, FA < 30, slice width < 0.8mm. The second sub-set of parameters provide results in real time with high temporal resolution for dynamic imaging (e.g., PSIF). The selected parameters are associated with processing instructions to subtract the acquired first sub-set of MRI images (obtained using the first MRI sub-sequence) and second sub-set of MRI images (obtained using the second MRI sub-sequence). The processing delineates small nerve fibers from small vessels that appear as tissues with similar contrast.

Optionally, the combination of parameters are selected to account for differences between the MRI images acquired by applying the different MRI sequences that are sensitive to different properties of the tissues, for example, moderate fat level, number of fascicles in the neural bundle, and flow rate of blood at the blood vessel neighboring the peripheral nerve(s).

At 106, MRI 212 executes MRI sequences using set of coils 216A and/or set of coils 216B according to the selected set of parameters (which may be stored in parameter repository 214) to create sets of MRI images. For each anatomical region, MRI images are captured using set of coils 216A, and another set of MRI images may be captured using set of coils 216B. Respective MRI sequences are executed for each of the defined anatomical regions using set of coils 216A and/or set of coils 216B according to the respective set of parameters selected for the respective anatomical region to create sets of MRI images for each respective anatomical region. The MRI images acquired for each anatomical region may be stored in MRI image repository 218. For example, two sets of different coils may be used for each anatomical region, or the same set of coils (i.e., common coils) may be used for two or more (e.g., all) anatomical regions. For example, the FOV that is covered by one set of coils may be sufficiently detailed to provide full coverage of other anatomical regions.

It is noted that three or more sets of coils may be used to capture three or more sets of MRI images for each anatomical location according to selected parameters. Alternatively, a single set of coils may be used to capture one, two or more sets of MRI images using different sequences for each anatomical location according to selected parameters.

At 108, the MRI images acquired for each anatomical region are processed (e.g., using image processing code 206B stored in program store 206 executed by processor(s) 202 of computing device 204) to delineate one or more peripheral nerves within each respective anatomical region. The MRI images may be processed along different (optionally multiple) 2D and/or 3D viewing planes. The processing may be performed to delineate peripheral nerves in located within the anatomical region (i.e., without explicitly defining which peripheral nerve is the target nerve for delineation), and/or the processing may be performed to delineate one or more predefined peripheral nerves that are preselected by the user using user interface 230 (e.g., that the user is targeting for imaging).

The processing of the MRI images is defined according to the selected combination of parameters for the respective anatomical location, for example, outputted by the classifier in association with the outputted selected parameters, as described herein.

The processing of the MRI images is performed using mathematical operations that are based on multiple MRI images acquired for each respective anatomical region. Optionally, the mathematical operation is performed on one or more MRI images captured using set of coils 216A and one or more MRI images captured using set of coils 216B. Exemplary image processing methods include:

* Computing a linear weighted combination of the MRI images. * Computing a non-linear combination of weighted MRI images using multiple derivates of a certain image and one or more operators (e.g., divergence).

* Using compressed sensing algorithms for various interpolations from certain MRI image type, to another.

* Subtraction of a certain MRI image from another MRI image.

* Application of an operator to a certain MRI image (e.g., maximum intensity projection (MIP), or diffusion) determined locally by one or more derivatives of another MRI image.

* Diffusion tensor imaging (DTI) with tractography.

An example of mathematical operations to process the MRI images includes: subtraction of 3D Tl fast field echo (FFE) along with spectral fat suppression to detect the fatty components of the myelin sheath of the nerves. In another example, subtraction of a water excitation sequence image is used to suppress blood vessels and create a distinction with respect to the distal peripheral nerve(s).

Optionally, MRI images are processed to delineate anatomical features, by applying for example, noise reduction, window leveling optimization, and registration between images to account for patient motion.

Optionally, one or more MRI images of each anatomical region are processed to account for differences that define contrast for different tissue types for each respective anatomical region. For example, at a certain anatomical region the MRI images are processed to define contrast between bone and a nearby peripheral nerve, and the neighboring anatomical region is processed to define contrast between muscle and the nearby peripheral nerve, resulting in different MRI images. The MRI images may be processed to produce common features that improve the process of automatic registration of MRI images from the different anatomical regions. For example, anatomical features that are not located next to peripheral nerve(s) may be processed to appear similar (e.g., in terms of contrast) so that the processed anatomical features may be used for registration, for example, bone marrow of a long bone appearing in two or more anatomical features may be processed and used for image registration.

At 110, the peripheral nerve(s) is traced along the multiple defined anatomical regions. The tracing may be performed using image processing code that segments the peripheral nerve, optionally using manual input from the user. For example, the user may select a region where the peripheral nerve is expected to be located, or click on a section of the peripheral nerve on the processed image, and/or code may automatically identify a section of the peripheral nerve on the processed image. Optionally, the location of at least a section of the peripheral nerve within the MRI image is simulated. The located section of the peripheral nerve may be used as a seed by code that traces the section of the peripheral nerve to delineate the reset of the peripheral nerve.

Optionally, the tracing of the peripheral nerve(s) is performed independently for each anatomical region.

The traced peripheral nerve(s) at each anatomical region may be anatomically aligned to each other to delineate the peripheral nerve(s) location across multiple anatomical regions. The anatomical alignment may be performed using image registration methods performed by image processing code 206B (stored in program store 206 executed by processor(s) 202) that automatically registers anatomical features of the MRI images (optionally the processed images) of each anatomical region. Alternatively or additionally, the MRI images (e.g., the processed images) of the anatomical regions are first registered (e.g., using image processing code 206B), and tracing of the peripheral nerve is performed using the set of registered images.

Optionally, the tracing is performed to identify one or more branches of the peripheral nerve(s). The MRI images of each anatomical region may be processed using different acquisition planes, optionally multiple acquisition planes. Each branch may be traced to delineate the nerve tree associated with the peripheral nerve(s). Optionally, tracing is performed for designated branch(es), for example, the most clinically significant branches. For example, the ulnar nerve is traced to identify the muscular branch, the palmar branch, and the dorsal branch.

Tracing of the peripheral nerve may be performed in an upstream direction, towards a synapse with the central nervous system, for example, until the spinal cord. Tracing of the peripheral nerve may be performed in a downstream direction, towards innervations of a target end organ, for example, until the skin, muscle, heart, kidney, or other organ is reached.

The traced peripheral nerve(s) may be further delineated by additional processing of the MRI images to further increase contrast between the peripheral nerve(s) and the nearby tissue, by marking the traced peripheral nerve(s) (e.g., coloring the nerve), and/or the location of the traced peripheral nerve(s) may be stored (e.g., as a set of coordinates in an image space).

Optionally, two or more anatomical regions demonstrate an anatomical bifurcation of the peripheral nerve(s). For example, different branches of a common peripheral nerve are seen in different MRI images of the anatomical regions. The downstream or the lateral split may be demonstrated in less than 50% (or less than 30%, or less than 70%, or other values) of the surface area of the respective anatomical regions. The tracing is performed to delineate the different branches of the anatomical bifurcation as belonging to the common peripheral nerve.

Optionally, one or more branches of the peripheral nerve(s) (and/or the peripheral nerve(s) itself) are segmented within the registered MRI images. The segmentation may be performed by processing the MRI images for horizontal edge detection and/or longitudinal edge detection of the traced peripheral nerve(s) that delineates a curved path.

At 112, a three dimensional (3D) image (or a 2D image) delineating the location of the peripheral nerve(s) within the anatomical regions is rendered for presentation on a display (e.g., user interface 230), for storage, and/or for transmission to client terminal 209 (and/or another remote computing device).

The 3D image may be based on the processed MRI images that delineate the location of the traced peripheral nerve(s). The processed MRI images may be registered to create the 3D image. The 3D image may be created using one or more MRI images (optionally registered images) by mapping the location of the peripheral nerve(s) according to coordinates of the peripheral nerve(s) in the image space.

At 114, one or more blocks 102-112 are iterated. For example, tracing of the peripheral nerve(s) may reveal that a portion of the peripheral nerve does not appear within the imaged anatomical regions. A new anatomical region within the missing portion of the peripheral nerve may be defined and imaged. The peripheral nerve(s) within the new anatomical region may be joined with the earlier delineated peripheral nerve(s) to create a more complete tree.

Optionally, parameter selection (as described with reference to block 104) may be performed in real time, for example, as images from previous scan are being reconstructed, and/or selection of the parameters may be performed based on previous training of the classifier using earlier scans and/or from an external database(s). Parameters selection may be adjusted based on the processing of the images. For example, parameters may be reselected from an anatomical region that was previously scanned when the image processing fails to adequately delineate the peripheral nerve from the earlier acquired MRI image(s) using the previously selected parameters. The adjusted parameters may be used to rescan the anatomical image to obtain an updated MRI image, which may better delineate the peripheral nerve.

At 116, the rendered image may be used for planning a procedure associated with the delineated peripheral nerve(s), for example, ablation of a portion of the peripheral nerve(s), and/or ablation of tissue located in close proximity to the peripheral nerve(s). The procedure may be planned automatically or semi-automatically using procedure planning code 208A (e.g., stored in data repository 208, executed by processor(s) 202 of computing device 204 and/or executed by another computing device).

The procedure may be planned by computing a simulation of penetration paths using the image that delineates the peripheral nerve. The image that delineates the peripheral nerve may be used to analyze the safety and/or efficacy effects of the procedure using the procedure planning code. The user may use user interface 230 to provide input to guide the simulation (e.g., selecting the target region of the nerve for ablation) and/or to analyze the results of the simulation. The procedure planning code may compute suggested penetration path(s) based on the location of the target organs, target peripheral nerve(s), adjacent clinically significant anatomical structure locations (e.g., blood vessels, other nerves, lung, heart, intestines), optimal treatment angles, and/or initial set of catheter insertion points.

The procedure planning code may include instructions that analyze each penetration path for safety and/or efficacy, optimizes each penetration path by adjusting the penetration site and target tip position, and suggest the path(s) that were found most optimal to the user. The procedure planning code may be based on a model that includes the target organs (which may be manually selected by the user using the user interface), the adjacent anatomy (which may be automatically identified according to an anatomical model and/or by analysis of the images, and/or manually defined by the user), the insertion points (which may be manually defined by the user using the user interface), the definition of optimal treatment angles (which may be computed by the code), and the like.

The procedure planning code uses the rendered MRI 3D image and the delineation of the target peripheral nerve in a computational simulation environment in which the effect of different treatment parameters (e.g., selected by the user using the user interface, and/or automatically selected by the code) may be analyzed and/or visualized to the user (e.g., presented on the display) to select the optimal set of parameters.

The procedure planning code may include code instructions that optimize the RF ablation parameters (e.g., heat, temperature, time, and/or frequency) to achieve desired and/or improved efficacy and/or safety. The planning of the procedure using the procedure planning code may be used for guidance of the procedure by visualizing the patient anatomy including the delineated peripheral nerve(s) during the procedure. For example, markers that are visible both on the body of the patient and presented on the display.

The procedure data computed by the procedure planning code based on the image delineating the peripheral nerve(s) may be integrated with and used by other advanced navigation systems. For example, the computed insertion path is registered with a real-time imaging modality (e.g. x-ray imaging) and/or with a tracking system of the operational tools, which depicts real-time guidance of the operational tool according to the computed procedure data. For example, the navigation system guides the surgeon to position the ablation catheter in the insertion point, to insert the catheter in the right angle and depth confirming that the procedure is executed according to the computed procedure data.

Reference is now made to FIG. 3, which is a flowchart of another method for delineating peripheral nerve(s) in images created using an MRI, in accordance with some embodiments of the present invention. The method described with reference to FIG. 3 represents an implementation based on the method described with reference to FIG. 1 and/or using system 200 described with reference to FIG. 2.

At 302, the patient is placed inside MRI 212.

At 304, multiple MRI sequences are acquired from the target organ that includes the peripheral nerve(s) using dedicated volume coils (e.g., coils 216A). At 306, multiple MRI sequences are acquired from proximal, more rostral field of view (FOV) using relevant surface coils (e.g., coils 216B).

At 308, the acquired MRI image data is analyzed to detect the upstream nerve root.

At 310, the nerve root is traced to the periphery using combined surface and volume coils sequences and a pre-determined anatomical model, as described herein.

At 312, the nervous tree is delineated from the root to the relevant branches, as described herein.

At 314, the 3D image is reconstructed and visualized, as described herein.

Various embodiments and aspects of the systems and/or methods (e.g., code instructions stored in a data storage executed by one or more processor(s)) as delineated hereinabove and as claimed in the claims section below find experimental support in the following example. EXAMPLE

Reference is now made to the following example, which together with the above descriptions illustrates some embodiments of the systems and/or methods (e.g., code instructions stored in a data storage executed by one or more processor(s)) described herein in a non limiting fashion.

Reference is now made to FIG. 4, which include an MRI image 402 of a right knee of a patient acquired using a standard clinical sequence protocol, and another MRI image 404 of the right knee acquired using the set of parameters selected for delineation of the peripheral nerve(s) (as described herein), in accordance with some embodiments of the present invention. Peripheral nerves 406 (superior lateral geniculate) and 408 (superior medial geniculate) are delineated in MRI image 404, but are not delineated in MRI image 402. MRI images 402 and 404 are acquired using the same hardware, but different parameters defining different sequences.

MRI images 402 and 404 are acquired using the same MRI machine using the same coils, on the same day for the same anatomical region (i.e., right knee) of the same patient (61 year old male).

MRI images 402 and 404 are acquired using the 3T system available from Siemens, the Biograph - mMR, and Knee coil. FOV was 15 X 15. MRI image 402 is acquired using a routine clinical sequence: 3D TRUFI, WE, COR, with slice width = 1.5 mm, TR = 9.0 ms, TE = 3.8 ms, and Flip Angle = 28.

MRI image 404 is acquired using the set of parameters selected to define a sequence for delineating the genicular nerve(s): 3D VIBE, WE, COR, with slice width = 0.5 mm, TR = 12.4 ms, TE = 5.6 ms, and Flip Angle = 10.

Other systems, methods, features, and advantages of the present disclosure will be or become apparent to one with skill in the art upon examination of the following drawings and detailed description. It is intended that all such additional systems, methods, features, and advantages be included within this description, be within the scope of the present disclosure, and be protected by the accompanying claims.

The descriptions of the various embodiments of the present invention have been presented for purposes of illustration, but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

It is expected that during the life of a patent maturing from this application many relevant MRI machines and MRI imaging sequences will be developed and the scope of the terms MRI machine and MRI image sequence are intended to include all such new technologies a priori.

As used herein the term "about" refers to ± 10 %.

The terms "comprises", "comprising", "includes", "including", "having" and their conjugates mean "including but not limited to". This term encompasses the terms "consisting of" and "consisting essentially of".

The phrase "consisting essentially of" means that the composition or method may include additional ingredients and/or steps, but only if the additional ingredients and/or steps do not materially alter the basic and novel characteristics of the claimed composition or method. As used herein, the singular form "a", "an" and "the" include plural references unless the context clearly dictates otherwise. For example, the term "a compound" or "at least one compound" may include a plurality of compounds, including mixtures thereof.

The word "exemplary" is used herein to mean "serving as an example, instance or illustration". Any embodiment described as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments and/or to exclude the incorporation of features from other embodiments.

The word "optionally" is used herein to mean "is provided in some embodiments and not provided in other embodiments". Any particular embodiment of the invention may include a plurality of "optional" features unless such features conflict.

Throughout this application, various embodiments of this invention may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as from 1 to 6 should be considered to have specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

Whenever a numerical range is indicated herein, it is meant to include any cited numeral (fractional or integral) within the indicated range. The phrases "ranging/ranges between" a first indicate number and a second indicate number and "ranging/ranges from" a first indicate number "to" a second indicate number are used herein interchangeably and are meant to include the first and second indicated numbers and all the fractional and integral numerals therebetween.

It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination or as suitable in any other described embodiment of the invention. Certain features described in the context of various embodiments are not to be considered essential features of those embodiments, unless the embodiment is inoperative without those elements.

Although the invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope of the appended claims.

All publications, patents and patent applications mentioned in this specification are herein incorporated in their entirety by reference into the specification, to the same extent as if each individual publication, patent or patent application was specifically and individually indicated to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the present invention. To the extent that section headings are used, they should not be construed as necessarily limiting.

Claims

WHAT IS CLAIMED IS:

1. A method for imaging at least one peripheral nerve of a patient, comprising: receiving a designation of a first anatomical region of a body of the patient and a second anatomical region each including the at least one peripheral nerve;

selecting a first set of parameters for instructing a first set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of first raw MRI images of at least the first anatomical region, the first set of parameters selected as a combination for processing the plurality of first raw MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the first anatomical region;

selecting a second set of parameters for instructing a second set of a plurality of MRI sequences for creating a plurality of second MRI images of at least the second anatomical region, the second set of parameters selected as a combination for processing the plurality of second MRI images to for define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the second anatomical region;

processing the plurality of first MRI images based on the selected combination of the first set of parameters, along different 2D and/or 3D viewing planes to delineate the at least one peripheral nerve within the first anatomical region;

processing the plurality of second MRI images based on the selected combination of the second set of parameters, to delineate the at least one peripheral nerve within the second anatomical region;

tracing the at least one peripheral nerve along the first anatomical region and the second anatomical region of the body; and

rendering for presentation a 3D image delineating the location of the at least one peripheral nerve within the first anatomical region and the second anatomical region.

2. The method of claim 1, wherein each of the first and second set of parameters include a first sub-set of parameters for imaging a large field of view (FOV), and a second sub- set of parameters for imaging a small (FOV) with higher resolution than the large FOV, wherein the first sub-set of parameters and the second sub-set of parameters are selected as the combination, wherein each of the first and second set of MRI sequences each acquire a first sub-set of MRI images having a large FOV and a second sub-set of MRI images having a small FOV.

3. The method of claim 1, wherein each of the first and second set of parameters include a first sub-set of parameters defining a first MRI sub-sequence for imaging using a set of coils, and a second sub-set of parameters defining a second MRI subsequence for imaging using the set of coils, wherein the first sub-set of parameters and the second sub- set of parameters are selected as the combination, wherein each of the plurality of first MRI images and the plurality of second MRI image includes a first subset of MRI images captured the set of coils according to the first sub- sequence based on the first sub-set of parameters and a second sub-set of MRI images captured using the set of coils according to the second sub-sequence based on the second sub-set of parameters.

4. The method of claim 1, wherein each of the first and second set of parameters include a first sub-set of parameters defining a first MRI sub-sequence for imaging using volumetric coils, and a second sub-set of parameters defining a second MRI subsequence for imaging using surface coils, wherein the first sub-set of parameters and the second sub- set of parameters are selected as the combination, wherein each of the plurality of first MRI images and the plurality of second MRI image includes a first subset of MRI images captured using the volumetric coils according to the first subsequence based on the first sub-set of parameters and a second sub-set of MRI images captured using the surface coils according to the second sub-sequence based on the second sub-set of parameters.

5. The method of claim 4, wherein the first sub-set of parameters define a spoiled 3D gradient echo (GRE) first MRI sub-sequence, and the second set of parameters define a spoiled transverse-coherence second MRI sub-sequence, wherein the first subset of parameters are selected to create Tl weighted 3D images using interpolation and/or partial Fourier techniques combined with water excitation, to create a high signal-to-noise ratio (SNR) contrast, wherein the first set of parameters include echo time (TE) < 10 milliseconds (ms), repetition time (TR) < 15 ms, flip angle (FA) < 30, and slice width < 0.8mm, wherein the second sub-set of parameters are selected to create a Contrast-Enhanced Fast Field Echo sequence with a low-flip angle and a rapid repetition of the basic sequence using repetition time shorter than typical Tl relaxation time of protons in biologic tissue to create a spoiled transverse coherence having T1/T2 contrast, wherein the second set of parameters include TE< 10ms, TR < 15ms, FA < 30, slice width < 0.8mm, and further comprising subtracting the acquired first sub-set of MRI images and second sub- set of MRI images, thereby distinguishing between small nerve fibers and small vessels that appear as tissues with similar contrast.

6. The method of claim 1, further comprising iterating:

receiving a designation of another anatomical region of a body of the patient including the at least one peripheral nerve;

selecting another set of parameters for instructing another set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of another MRI images of the another anatomical region, the another set of parameters selected as a combination for processing the plurality of another MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the another anatomical image;

processing the plurality of another MRI images based on the selected combination of the another set of parameters, to delineate the at least one peripheral nerve within the another anatomical region;

further tracing the at least one peripheral nerve along the another anatomical region; and

updating the rendering for presentation of the 3D image that further delineates the location of the at least one peripheral nerve within the another anatomical region.

7. The method of claim 1, further comprising processing the plurality of MRI images, with different acquisition planes of the first anatomical region to identify a branch of the at least one peripheral nerve, and wherein tracing comprises tracing at least one designated branch of the at least one peripheral nerve.

8. The method of claim 1, wherein tracing of the at least one peripheral nerve is performed at least one of: in an upstream direction towards a synapse with the central nervous system, and in a downstream direction towards innervations of a target end organ.

9. The method of claim 1, wherein each of the first and second set of parameters are independently selected according to the respective tissue architectures of the first and second anatomical regions.

10. The method of claim 1, wherein the first and second anatomical regions are contiguous with each other.

11. The method of claim 1, wherein the first and second anatomical regions have a gap between each other.

12. The method of claim 1, wherein the first and second anatomical regions overlap each, wherein the overlap region is less than 50% of the surface area of the regions.

13. The method of claim 1, wherein the first and second anatomical regions demonstrate an anatomical bifurcation of the at least one peripheral nerve, wherein a downstream or a lateral split is demonstrated in less than 50% of the surface area of the respective first and second anatomical regions, wherein the tracing is performed to delineate the portions of the anatomical bifurcations are belonging to a common at least one peripheral nerve.

14. The method of claim 1, further comprising identifying at least one anatomical structure located in proximity to the expected location of the at least one peripheral nerve in each of the first and second anatomical regions, and selecting the respective first and second set of parameters according to the identified at least one anatomical structure to define contrast between the at least one anatomical structure and the at least one peripheral nerve that delineates the at least one peripheral nerve.

15. The method of claim 14, wherein the at least one anatomical structure is identified by correlating each of the first and second anatomical regions to a predefined anatomical model.

16. The method of claim 1, wherein the first and second set of parameters are selected for defining contrast that delineates the at least one peripheral nerve that includes one or more members selected from the group consisting of: cross sectional dimension less than about 1 millimeter (mm), high anatomical variability in location between patients, predominantly non-myelinated, external from a vein-artery-nerve (VAN) structure.

17. The method of claim 1, wherein the designation of the first and second anatomical regions is performed by at least one of: manual user input entered using a graphical user interface, and code instructions executed by at least one processor that automatically identifies the first and second anatomical regions based on processing of at least one image of the patient.

18. The method of claim 1, further comprising anatomically aligning the at least one peripheral nerve traced in the first anatomical region with the at least one peripheral nerve traced in the second anatomical region.

19. The method of claim 18, wherein the anatomically aligning is performed by image processing code executed by at least one processor that automatically registers anatomical features of at least one of the plurality of first MRI images and at least one of the plurality of second MRI images.

20. The method of claim 19, further comprising processing the at least one of the plurality of first MRI images and the at least one of the plurality of second MRI images to account for differences that define contrast for different tissue types, for improving the process of the automatic registration of the at least one of the plurality of first MRI images and the at least one of the plurality of second MRI images.

21. The method of claim 1, further comprising registering at least one of the plurality of first MRI images with at least one of the plurality of second MRI images, and wherein the tracing is performed using the registered MRI images.

22. The method of claim 21, further comprising simulating the location of the at least one nerve within the registered MRI images, and wherein tracing comprises searching for the at least one nerve within the registered MRI images according to the simulated location.

23. The method of claim 21, further comprising segmenting at least one branch of the at least one peripheral nerve within the registered MRI images by performing at least one of horizontal edge detection and longitudinal edge detection of the traced at least one peripheral nerve that delineates a curved path of the at least one peripheral nerve.

24. The method of claim 1, wherein the first and second set of parameters are selected using a statistical classifier that is trained using a training set of MRI images from a population of patients that include defined contrast that delineates the at least one peripheral nerve of each respective patient for the respective first and second anatomical regions, and associated set of parameters used to define MRI sequences for acquiring the respective training MRI images.

25. The method of claim 1, wherein the processing of one or both of the plurality of first MRI images and the processing of the plurality of second MRI image is performed by one or more members selected from the group consisting of: linear weighted combination of a plurality of MRI images, non-linear combination of a plurality of weighted MRI images using multiple derivates of a certain image and at least one operator, subtraction of a certain MRI image from another certain MRI image, application of an operator to a certain MRI image determined locally by at least one derivative of another certain MRI image.

26. The method of claim 1, wherein the processing of one or both of the plurality of first MRI images and the processing of the plurality of second MRI image is performed based on diffusion tensor imaging (DTI) with tractography.

27. The method of claim 1, wherein the first set and the second set of the plurality of magnetic resonance imaging (MRI) sequences are applied during a common scan session to acquire the first MRI images of the first anatomical region and the second MRI images of the second anatomical regions during the common scan session.

28. A system for imaging at least one peripheral nerve of a patient, comprising: a non-transitory memory having stored thereon a code for execution by at least one processor adapted to execute the code for:

receiving a designation of a first anatomical region of a body of the patient and a second anatomical region each including the at least one peripheral nerve;

selecting a first set of parameters for instructing a first set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of first MRI images of at least the first anatomical region, the first set of parameters selected as a combination for processing the plurality of first MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the first anatomical region;

processing the plurality of second MRI images based on the selected combination of the second set of parameters, to delineate the at least one peripheral nerve within the second anatomical region; tracing the at least one peripheral nerve along the first anatomical region and the second anatomical region of the body; and

29. A computer program product comprising a non-transitory computer readable storage medium storing program code thereon for implementation by at least one processor of a system for imaging at least one peripheral nerve of a patient, comprising: instructions for receiving a designation of a first anatomical region of a body of the patient and a second anatomical region each including the at least one peripheral nerve;

instructions for selecting a first set of parameters for instructing a first set of a plurality of magnetic resonance imaging (MRI) sequences for creating a plurality of first MRI images of at least the first anatomical region, the first set of parameters selected as a combination for processing the plurality of first MRI images to define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the first anatomical image;

instructions for selecting a second set of parameters for instructing a second set of a plurality of MRI sequences for creating a plurality of second MRI images of at least the second anatomical region, the second set of parameters selected as a combination for processing the plurality of second MRI images to for define contrast that delineates the at least one peripheral nerve of the patient according to the tissue architecture of the second anatomical image;

instructions for processing the plurality of first MRI images based on the selected combination of the first set of parameters, along different 2D and/or 3D viewing planes to delineate the at least one peripheral nerve within the first anatomical region;

instructions for processing the plurality of second MRI images based on the selected combination of the second set of parameters, to delineate the at least one peripheral nerve within the second anatomical region;

instructions for tracing the at least one peripheral nerve along the first anatomical region and the second anatomical region of the body; and instructions for rendering for presentation a 3D image delineating the location of the at least one peripheral nerve within the first anatomical region and the second anatomical region.