# US 11,908,131 B2 · Mapping brain perivascular spaces

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

- Number: US 11,908,131 B2
- Document ID: US11908131B2
- Status: Granted
- Kind: B2
- Application number: 17/176,725
- Filed: 2021-02-16
- Published: 2021-08-19
- Granted: 2024-02-20
- Earliest claimed: 2020-02-14
- Assignees: University of Southern California
- Applicants: University of Southern California
- Inventors: Farshid Sepehrband; Jeiran Choupan
- Web page: https://patentgrep.com/patent/US11908131B2

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G01R 33/50: based on the determination of relaxation times {, e.g. T1 measurement by IR sequences; T2 measurement by multiple-echo sequences}
- G01R 33/5608: {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)}
- G01R 33/56341: {Diffusion imaging}
- G06T 7/11: Region-based segmentation
- G06T 7/136: involving thresholding
- G01R 33/5602: {by filtering or weighting based on different relaxation times within the sample, e.g. T1 weighting using an inversion pulse}
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10092: Diffusion tensor magnetic resonance imaging [DTI]
- G06T 2207/20024: Filtering details
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30016: Brain
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)

## Abstract

Systems and methods for mapping brain perivascular spaces. A system may include a memory to store one or more images of a brain of a patient. The system may further include a processor coupled to the memory. The processor may be configured to obtain a first and a second image of the brain. The processor may be further configured to combine the first image and the second image to preserve and magnify structures including the brain perivascular spaces within the image of the brain. The processor may be further configured to determine the brain perivascular spaces within the combined image of the brain of the patient. The processor may be further configured to generate a three-dimensional (3-D) map of the perivascular spaces. The system may further include a display configured to display the perivascular spaces to an operator.

## Claims

### Claim 1

A system for mapping brain perivascular spaces, comprising:
a memory to store one or more images of a brain of a patient;
a processor coupled to the memory and configured to:
obtain a first image of the brain of the patient, the first image including a first contrast,
obtain a second image of the brain of the patient, the second image including a second contrast,
combine the first image and the second image to form a combined image, the combined image preserving and magnifying structures including the brain perivascular spaces within the combined image of the brain of the patient, the combined image including a third contrast, the third contrast being higher than the first contrast and the second contrast,
determine the brain perivascular spaces within the combined image of the brain of the patient, and
generate a three-dimensional (3-D) map of the brain perivascular spaces within the brain of the patient; and
a display configured to display the perivascular spaces of the brain of the patient to an operator.

### Claim 2 (depends on 1)

The system of claim 1, wherein the 3-D map of the brain perivascular spaces indicates a caliber, a distribution, an amount, a number, a volume or a volume fraction or a density of the brain perivascular spaces within the brain and within each region of the brain.

### Claim 3 (depends on 2)

The system of claim 2, wherein the processor is configured to:
generate statistics of the brain perivascular spaces, wherein the statistics include the caliber, the distribution, the amount, the number, the volume or the volume fraction or the density of the brain perivascular spaces within the brain and within each region of the brain; and
provide the statistics of the brain perivascular spaces to the operator, wherein the statistics indicate, correlate with or relate to a neurological disease condition.

### Claim 4 (depends on 1)

The system of claim 1, wherein the first image and the second image are high-resolution scans having different modalities with different contrasts from a magnetic resonance imaging device, wherein the different modalities include a T1-weighted modality and a T2-weighted modality that contrasts white matter and fluid patterns inversely in comparison to the T1-weighted modality wherein the high-resolution scans have a resolution of approximately 0.7 mm or less.

### Claim 5 (depends on 1)

The system of claim 1, wherein the first image and the second image are low-resolution scans obtained from clinical data, wherein the low-resolution scans have a resolution of approximately 1 mm or greater.

### Claim 6 (depends on 1)

The system of claim 1, wherein the processor is configured to:
perform pre-processing of the first image and the second image including at least one of non-uniform intensity normalization, motion correction, alignment correction, Talairach transform computation, skull stripping and intensity normalization; and
filter high-frequency noise from the first image and the second image to reduce high-frequency noise within the first image and the second image.

### Claim 7 (depends on 1)

The system of claim 1, wherein to determine the brain perivascular spaces the processor is configured to:
applying a Frangi filter that provides a likelihood or a probability of each voxel being a brain perivascular space in the combined image; and
for each voxel, determining that the voxel is the brain perivascular space when the likelihood or the probability of the voxel is greater than or equal to a threshold value, wherein the threshold value is a modeled based on neurological data.

### Claim 8

A system for mapping brain perivascular spaces using clinical data, comprising:
a memory to store one or more images of a brain of a patient;
a processor coupled to the memory and configured to:
obtain a combined image of the brain of the patient, the combined image generated by combining a first image and a second image of the brain of the patient, the first image including a first contrast, the second image including a second contrast, the combined image including a third contrast, the third contrast being higher than the first contrast and the second contrast,
determine the brain perivascular spaces within the combined image of the brain of the patient, and
generate a three-dimensional (3-D) map of the brain perivascular spaces; and
a display configured to display or render an image of the brain perivascular spaces of the brain of the patient to an operator.

### Claim 9 (depends on 8)

The system of claim 8, wherein the first image has a T1-weighted modality and the second image has
a FLAIR modality that suppresses fluids in the first image while providing a high contrast for lesions including segmenting or excluding lesions or microbleeds from the first image based on the first image and the other image having the FLAIR modality; and
optimizing lesion detection techniques using machine learning.

### Claim 10 (depends on 8)

The system of claim 8, wherein to determine the brain perivascular spaces the processor is configured to:
applying a Frangi filter that provides a likelihood or a probability of each voxel being a brain perivascular space; and
for each voxel, determining that the voxel is the brain perivascular space when the likelihood or the probability of the voxel is greater than or equal to a threshold value, wherein the threshold value is a modeled based on neurological data.

### Claim 11

A method for analyzing brain perivascular spaces, comprising:
obtaining a first image of a brain of a patient, the first image including a first contrast;
obtaining a second image of the brain of the patient, the second image including a second contrast;
combining the first image and the second image to form a combined image, the combined image preserving and magnify structures including the brain perivascular spaces within the brain of the patient, the combined image including a third contrast, the third contrast being higher than the first contrast and the second contrast;
determining the brain perivascular spaces within the combined image of the brain of the patient;
determining fluid characteristics within the brain;
generating a map of the brain perivascular spaces along with fluid characteristics within the brain of the patient; and
displaying the map of the brain perivascular spaces along with the fluid characteristics within the brain of the patient.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
obtaining diffusion magnetic resonance imaging scans over a period of time;
wherein determining the fluid characteristics within the brain includes measuring or determining diffusion or motion hydrogen molecules at the microscopic or molecular level using diffusion magnetic resonance imaging scans over the period of time.

### Claim 13 (depends on 12)

The method of claim 12, wherein determining the diffusion or the motion of the hydrogen molecules includes decomposing or separating the diffusion or the motion of the hydrogen molecules inside white matter diffusion or fluid diffusion based on a speed of a motion or the motion of the hydrogen molecules, wherein the fluid diffusion is a faster diffusion than the white matter diffusion.