Technologies for diagnosing neurological or psychiatric illnesses

Patent metadata

Field	Value
Publication number	US-10846858-B2
Application number	US-201916267067-A
Country	US
Kind code	B2
Filing date	Feb 4, 2019
Priority date	Apr 17, 2014
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

Abstract

A technology which enables identifying, via a computer, a vessel in a third image. The third image is obtained from a subtraction of a second image from a first image. The second image and the first image are aligned within an imaging space. The first image is post-contrast. The second image is pre-contrast. The technology enables determining, via the computer, a voxel intensity mean value of a segment of the vessel in the third image. The technology enables obtaining, via the computer, a fourth image from a division of the third image by the voxel intensity mean value. The technology enables applying, via the computer, a filter onto the fourth image. The technology enables generating, via the computer, a filter mask based on the fourth image.

First claim

The invention claimed is:

1. A method comprising:
identifying, via a processor, a brain vessel segment in a subtracted image;
determining, via the processor, a voxel intensity mean value of the brain vessel segment based on a highest voxel intensity in the brain vessel segment such that the voxel intensity mean value indicates at least one of a content of a blood in the brain vessel segment or a flow of the blood in the brain vessel segment;
dividing, via the processor, the subtracted image by the voxel intensity mean value such that a resulting image is obtained and such that a percentage of a volume of the blood in the brain vessel segment of the resulting image is determinable;
applying, via the processor, a filter onto the resulting image; and
generating, via the computer, a mask based on the filter being applied to the resulting image.

2. The method of claim 1 , wherein the voxel intensity mean value indicates the content of the blood in the brain vessel segment.

3. The method of claim 1 , wherein the voxel intensity mean values indicates the flow of the blood in the brain vessel segment.

4. The method of claim 1 , wherein the filter is a first filter, wherein the brain vessel segment is identified based on a second filter and a pre-defined region of interest.

5. The method of claim 4 , wherein the brain vessel segment is of a superior sagittal sinus.

6. The method of claim 1 , wherein the voxel intensity mean value is obtained on a voxel-by-voxel basis for the brain vessel segment based on the highest voxel intensity in the brain vessel segment.

7. The method of claim 1 , wherein the mask is a first mask, wherein the voxel intensity mean value is based on a second mask being applied to the subtracted image and a measure of an absolute blood is determined as a mean of the subtracted image.

8. The method of claim 1 , wherein the subtracted image is divided by the voxel intensity value based on a matrix.

9. The method of claim 1 , wherein the resulting image is a cerebral blood volume map.

10. The method of claim 1 , wherein the filter filters out a first set of vasculature and filters in a second set of vasculature, wherein the first set of vasculature has a first vasculature, wherein the second set of vasculature has a second vasculature, wherein the first vasculature is larger than the second vasculature.

11. The method of claim 1 , wherein the filter filters based on fitting a bimodal Gaussian curve to a histogram of data.

12. The method of claim 1 , wherein the filter filters based on performing an expectation-maximization segmentation.

13. The method of claim 1 , wherein the mask is based on an intensity value of the filter.

14. The method of claim 1 , wherein the mask is a binary mask.

15. The method of claim 1 , wherein the brain vessel segment is identified based on a vesselness filter and a pre-defined region of interest, wherein the vesselness filter filters based on a set of eigenvalues of a Hessian matrix of the subtracted image, wherein the subtracted image is modified such that the region of interest is positioned in a predefined area.

16. The method of claim 1 , wherein the voxel intensity mean value is based on a highest voxel intensity range in the brain vessel segment, wherein the highest voxel intensity range comprises a top 40% of voxel intensities.

17. The method of claim 16 , wherein the highest voxel intensity range comprises a top 33% of voxel intensities.

18. The method of claim 16 , wherein the highest voxel intensity range comprises a top 25% of voxel intensities.

19. The method of claim 1 , further comprising:
causing, via the processor, a formation of a set of diagnosis data for a neurological illness based on the resulting image, wherein the neurological illness is of a patient associated with the brain vessel segment.

20. The method of claim 1 , further comprising:
causing, via the processor, a formation of a set of diagnosis data for a psychiatric illness based on the resulting image, wherein the psychiatric illness is of a patient associated with the brain vessel segment.

Assignees

• Univ Columbia

Inventors

• Small Scott A
• Provenzano Frank A
• Khan Usman A

Classifications

• G06T7/0016 Primary

  involving temporal comparison · CPC title

• G06T2207/30101

  Blood vessel; Artery; Vein; Vascular · CPC title

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title

• G06T7/136

  involving thresholding · CPC title

• G06T5/20

  using local operators · CPC title