Automatic identification of subjects at risk of multiple sclerosis

Patent metadata

Field	Value
Publication number	US-11272843-B2
Application number	US-201916254710-A
Country	US
Kind code	B2
Filing date	Jan 23, 2019
Priority date	Jan 23, 2019
Publication date	Mar 15, 2022
Grant date	Mar 15, 2022

Abstract

A computer-implemented method for automatically identifying subjects at risk of Multiple Sclerosis (MS) includes acquiring a plurality of images of a subject's brain using a Magnetic Resonance Imaging (MRI) scanner. A contrast enhancement process is applied to each image to generate a plurality of contrast-enhanced images. An automated lesion detection algorithm is applied to detect one or more lesions present in the contrast-enhanced images. An automated central vein detection algorithm is applied to detect one or more central veins present in the contrast-enhanced images. An automated paramagnetic rim detection algorithm is applied to detect one or more paramagnetic rims present in the contrast-enhanced images. The patient's risk for MS may then be determined based on the one or more of the lesions, central veins, and paramagnetic rims present in the contrast-enhanced images.

First claim

What is claimed is:

1. A computer-implemented method for automatically identifying subjects at risk of Multiple Sclerosis (MS), the method comprising:
acquiring a plurality of images of a subject's brain using a Magnetic Resonance Imaging (MRI) scanner;
applying a contrast enhancement process to each image to generate a plurality of contrast-enhanced images, wherein the plurality of contrast-enhanced images comprise at least one contrast-enhanced image generated using a phase unwrapping/filtering contrast enhancement process and at least one contrast-enhanced image generated using gadolinium contrast media;
applying an automated lesion detection algorithm to detect one or more lesions present in the contrast-enhanced images;
applying an automated central vein detection algorithm to detect one or more central veins present in the contrast-enhanced images;
applying an automated paramagnetic rim detection algorithm to detect one or more paramagnetic rims present in the contrast-enhanced images;
determining the patient's risk for MS based on the one or more of the lesions, central veins, and paramagnetic rims present in the contrast-enhanced images.

2. The method of claim 1 , further comprising:
generating a report describing the patient's risk for MS listing:
a lesion load value determined based on a count of the lesions,
a central vein percentage indicating a percentage of the lesions having central veins,
a paramagnetic rim percentage indicating a percentage of the lesions having paramagnetic rims.

3. The method of claim 1 , wherein at least one of the images is acquired using a T2*-weighted 3D segmented Echo-Planar Imaging (3D EPI) pulse sequence.

4. The method of claim 1 , wherein at least one of the images is acquired using a flow-compensated 3D spoiled Gradient-Echo (3D GRE) pulse sequence.

5. The method of claim 1 , wherein at least one of the images is acquired using a T2-weighted 3D Fluid suppression Inversion Recovery pulse sequence (3D FLAIR).

6. The method of claim 1 , wherein at least one of the images is acquired using a T1-weighted 3D Magnetization Prepared Rapid Acquisition of Gradient Echo (3D MPRAGE) or Magnetization-Prepared Two Rapid Acquisition Gradient Echoes (MP2RAGE) pulse sequence.

7. The method of claim 1 , wherein each contrast-enhanced image is generated using a distinct contrast enhancement process.

8. The method of claim 7 , wherein the contrast-enhanced images comprise at least one contrast-enhanced image generated using a Susceptibility-Weighted-Imaging (SWI) contrast enhancement process.

9. The method of claim 7 , wherein the contrast-enhanced images comprise at least one contrast-enhanced image generated using a FLAIR* or a FLAIR-SWI contrast enhancement process.

10. The method of claim 7 , wherein the contrast-enhanced images comprise a quantitative susceptibility mapping contrast enhancement process.

11. A computer-implemented method for automatically identifying subjects at risk of Multiple Sclerosis (MS), the method comprising:
receiving a plurality of images of a subject's brain acquired using a Magnetic Resonance Imaging (MRI) scanner, wherein one or more contrast-enhancement processes is applied to each image to enhance biomarkers related to MS, wherein the one or more contrast-enhancement processes include a phase unwrapping/filtering contrast enhancement process and a process using gadolinium contrast media;
applying a plurality of image analysis algorithms to identify a plurality of biomarkers present in the images; and
using a trained machined learning model to determine the patient's risk for MS based on a combined assessment of the plurality of biomarkers.

12. The method of claim 11 , wherein the biomarkers comprise lesions, paramagnetic rims, and central veins.

13. The method of claim 12 , further comprising:
generating a report describing the patient's risk for MS listing:
a lesion load value determined based on a count of the lesions,
a central vein percentage indicating a percentage of the lesions having central veins,
a paramagnetic rims percentage indicating a percentage of the lesions having paramagnetic rims.

14. The method of claim 11 , wherein at least one of the images is acquired using a T2*-weighted 3D segmented Echo-Planar Imaging (3D EPI) pulse sequence.

15. The method of claim 11 , wherein at least one of the images is acquired using a flow-compensated 3D spoiled Gradient-Echo (3D GRE) pulse sequence.

16. The method of claim 11 , wherein at least one of the images is acquired using a T2-weighted 3D Fluid suppression Inversion Recovery pulse sequence (3D FLAIR).

17. The method of claim 11 , wherein at least one of the images is acquired using a T1-weighted 3D Magnetization Prepared Rapid Acquisition of Gradient Echo (3D MPRAGE) or Magnetization-Prepared Two Rapid Acquisition Gradient Echoes (MP2RAGE) pulse sequence.

18. The method of claim 11 , wherein the one or more contrast-enhancement processes comprise one or more of:
a Susceptibility-Weighted-Imaging (SWI) contrast enhancement process,
a FLAIR* contrast enhancement process,
a FLAIR-SWI contrast enhancement process, and
a quantitative susceptibility mapping contrast enhancement process.

19. A system for automatically identifying subjects at risk of Multiple Sclerosis (MS), the system comprising:
a display;
a Magnetic Resonance Imaging (MRI) scanner configured to acquire a plurality of images of a subject's brain;
a central control computer configured to:
apply a contrast enhancement process to each image to generate a plurality of contrast-enhanced images, wherein the plurality of contrast-enhanced images comprise at least one contrast-enhanced image generated using a phase unwrapping/filtering contrast enhancement process and at least one contrast-enhanced image generated using gadolinium contrast media;
apply an automated lesion detection algorithm to detect one or more lesions present in the contrast-enhanced images;
apply an automated central vein detection algorithm to detect one or more central veins present in the contrast-enhanced images;
apply an automated paramagnetic rim detection algorithm to detect one or more paramagnetic rims present in the contrast-enhanced images;
determine the patient's risk for MS based on the one or more of the lesions, central veins, and paramagnetic rims present in the contrast-enhanced images; and
present the patient's risk for MS on the display.

Assignees

• Siemens Healthcare Gmbh
• Us Health

Inventors

• Sati Pascal
• Patil Sunil Goraksha
• Reich Daniel

Classifications

• A61B5/055

  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging · CPC title

• A61B5/0042 Primary

  for the brain · CPC title

• G01R33/5608 Primary

  Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T) · CPC title

• G01R33/5602

  by filtering or weighting based on different relaxation times within the sample, e.g. T1 weighting using an inversion pulse · CPC title

• G06T2207/30016

  Brain · CPC title