# US 2021/0279877 A1 · A novel, quantitative framework for the diagnostic, prognostic, and therapeutic evaluation of spinal cord diseases

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279877 A1
- Document ID: US20210279877A1
- Status: Published application
- Kind: A1
- Application number: 17/251,513
- Filed: 2019-06-14
- Published: 2021-09-09
- Earliest claimed: 2018-06-14
- Assignees: Thomas Jefferson University
- Applicants: Thomas Jefferson University
- Inventors: Christopher J. CONKLIN; Feroze B. MOHAMED; Devon M. MIDDLETON; Mahdi ALIZADEH
- Web page: https://patentgrep.com/patent/US20210279877A1

## CPC

- G06T 7/0014: {using an image reference approach}
- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/4566: {Evaluating the spine (A61B5/4561 takes precedence)}
- A61B 5/7203: {for noise prevention, reduction or removal}
- A61B 5/7214: {using signal cancellation, e.g. based on input of two identical physiological sensors spaced apart, or based on two signals derived from the same sensor, for different optical wavelengths}
- A61B 5/7267: {involving training the classification device}
- A61B 34/10: Computer-aided planning, simulation or modelling of surgical operations
- G06N 3/00: Computing arrangements based on biological models
- G06N 3/02: Neural networks
- G06N 3/043: based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/06: Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/136: involving thresholding
- G06T 7/155: involving morphological operators
- G06T 7/187: involving region growing; involving region merging; involving connected component labelling
- G06T 12/10: Image preprocessing, e.g. calibration, positioning of sources or scatter correction
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- A61B 5/7425: {Displaying combinations of multiple images regardless of image source, e.g. displaying a reference anatomical image with a live image}
- A61B 2034/105: {Modelling of the patient, e.g. for ligaments or bones}
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10092: Diffusion tensor magnetic resonance imaging [DTI]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30012: Spine; Backbone
- G06T 2211/424: Iterative
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A method of generating a quantitative characterization of injury presence and status of spinal cord tissue using an adaptive CNN system for use in diagnostic assessment, surgical planning, and therapeutic strategy comprises preprocessing for artifact correction of diffusion based, spinal cord MRI data, training an adaptive CNN system with healthy and abnormal (injured/pathologic) spinal cord images obtained by imaging a population of healthy, typically developed spinal cord subjects and subjects with spinal cord injury, evaluating a novel, diffusion-based MRI image for injury biomarkers using the adaptive CNN system, generating a three-dimensional predictive axonal damage map for quantitative characterization and visualization of the novel, diffusion-based MRI image, and transmitting the sets of healthy and injured spinal cord images back to a central database for continued improvement of the adaptive CNN system training. A system for defining a predictive spinal axonal damage map is also described.

## Claims

### Claim 1

A method of generating a quantitative characterization of injury presence and status of spinal cord tissue using an adaptive CNN system for use in diagnostic assessment, surgical planning, and therapeutic strategy comprising:
preprocessing for artifact correction of diffusion based, spinal cord MRI data;
training an adaptive CNN system with healthy and abnormal (injured/pathologic) spinal cord images obtained by imaging a population of healthy, typically developed spinal cord subjects and subjects with spinal cord injury;
evaluating a novel, diffusion-based MRI image for injury biomarkers using the adaptive CNN system;
generating a three-dimensional predictive axonal damage map for quantitative characterization and visualization of the novel, diffusion-based Mill image; and
transmitting the sets of healthy and injured spinal cord images back to a central database for continued improvement of the adaptive CNN system training.

### Claim 2 (depends on 1)

The method of claim 1 further comprising:
capturing and storing diffusion-sensitized MRI data, such data including at least one of: Diffusion Tensor Imaging (DTI) data, Diffusion Kurtosis Imaging (DKI) data, Neurite Orientation Dispersion and Density Imaging (NODDI) data, Other higher-order diffusion sampling schema;
correcting artifacts of the diffusion-based MRI data which can but does not explicitly mandate the inclusion of noise reduction, eddy current correction, segmentation of the spinal cord, ghost artifact removal, coregistration and motion correction (realignment), and automated image quality control;
estimating and calculating the diffusion tensor, kurtosis tensor, and multi-compartment models (e.g. NODDI) using an iteratively-reweighted outlier rejection scheme;
analyzing a texture to extract relevant 1st order, 2nd order, higher order, as well as geometric image features for texture training of the adaptive CNN system; and
including healthy volunteer and injured spinal cord datasets, processed as detailed above, for continued diagnostic training of the adaptive CNN system.

### Claim 3 (depends on 2)

The method of claim 2, further comprising: wherein the diffusion sensitized data (e.g. DTI, DKI, NODDI) is captured and stored.

### Claim 4 (depends on 1)

The method of claim 1, wherein the pre-processing comprises a step selected from the group consisting of: noise reduction based on a principal component analysis (PCA) method for signal decomposition and elimination of noise, eddy current correction based on estimation of the eddy current (EC) distortion field, segmentation of the cord using histogram thresholding for tissue classification, morphological processing, and region growing techniques, ghost artifact removal based on texture analysis and automated classification using neuro-adaptive fuzzy logic, co-registration and realignment based on maximized mutual information and a variable degree of freedom transformation and combinations thereof.

### Claim at position 5

5-8. (canceled)

### Claim 9 (depends on 1)

The method of claim 1, wherein the pre-processing module comprises an automated image quality control step based on local SNR characteristics, Euclidean metrics, and tissue contrast.

### Claim 10 (depends on 1)

The method of claim 1, wherein the pre-processing module comprises a tensor estimation step unique to the sampling scheme used (e.g. DTI, DKI, NODDI).

### Claim 11 (depends on 1)

The method of claim 1, wherein the pre-processing module comprises an outlier rejection step based on iteratively reweighting individual diffusion sensitized images based on residuals during the tensor estimation process.

### Claim 12 (depends on 1)

The method of claim 1, wherein after completion of a pre-processing module, a pattern recognition module is performed.

### Claim 13 (depends on 1)

The method of claim 1, wherein a pattern recognition module comprises histogram textures e.g. image intensity, variance, entropy, skewness, and kurtosis.

### Claim 14 (depends on 1)

The method of claim 1, wherein a pattern recognition module comprises 2nd order textures e.g. co-occurrence matrix contrast, homogeneity, correlation, and energy at 45° intervals.

### Claim 15 (depends on 1)

The method of claim 1, wherein a pattern recognition module comprises higher order textures e.g. mean, variance, entropy, and energy of vertical, horizontal, and diagonal wavelet components.

### Claim 16 (depends on 1)

The method of claim 1, wherein a pattern recognition module comprises geometric textures e.g. edge, corner, roundness, elasticity, and solidness.

### Claim 17 (depends on 1)

The method of claim 1, wherein a pattern recognition module comprises histogram textures, 2nd order textures, higher order textures, and geometric textures, and statistical testing of the same to determine feature relevance for the adaptive CNN system.

### Claim 18 (depends on 1)

The method of claim 1, where training an adaptive CNN system using the captured and processed diffusion sensitized MRI data (e.g. DTI, DKI, NODDI) for normal and abnormal subjects.

### Claim 19 (depends on 1)

The method of claim 1, wherein the trained adaptive CNN system classifies imaged tissue from patients as likely to be injured or not likely to be injured based on the aforementioned training using normative diffusion sensitized MRI data.

### Claim 20

(canceled)

### Claim 21 (depends on 1)

The method of claim 1, further comprising generating a quantitative, three-dimensional predictive axonal damage map for the spinal cord, wherein output from the trained, adaptive CNN system will provide the quantitative information needed to characterize the presence, location, and extent of spinal cord injury on a per subject basis.

### Claim 22 (depends on 1)

The method of claim 1, further comprising identifying injury to a spinal cord, wherein the predictive axonal damage map will be used by clinicians, surgeons, physical therapist, PM&R staff for reporting, surgical planning, and therapeutic strategy, for example: the map is used to precisely localize candidate sites for gene therapy with greater specificity than is possible through conventional MRI imaging as well as the tracking of therapeutic outcomes by examining changes in microstructural diffusion properties over the course of treatment.

### Claim 23 (depends on 1)

The method of claim 1, wherein the predictive axonal damage map is imported to a neuronavigational system, such as a Stryker or Medtronic system;
wherein the map is imported as a 3-D image to the neuronavigational system; and
wherein the map is overlaid onto conventional, structural MRI imaging to provide the clinician with a real time view, location, and extent of tissue damage during surgical procedures.

### Claim 24 (depends on 1)

The method of claim 1, wherein the diffusion sensitized image features (e.g. diffusion metrics, histogram, 1st, 2nd, and higher-order texture values) are transmitted and stored on a centralized database for continued improvement of the adaptive CNN system training.

### Claim at position 22

25-52. (canceled)

### Claim 53 (depends on 24)

A method of treating a patient exhibiting spinal cord damage comprising: use of the method of claim 24 to generate a predictive axonal damage map, wherein said predictive axonal damage map is imported into a neuronavigational system for performing a surgical procedure.