# US 2022/0284581 A1 · Systems and methods for evaluating the brain after onset of a stroke using computed tomography angiography

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

- Number: US 2022/0284581 A1
- Document ID: US20220284581A1
- Status: Published application
- Kind: A1
- Application number: 17/752,718
- Filed: 2022-05-24
- Published: 2022-09-08
- Earliest claimed: 2018-09-14
- Assignees: Board of Regents, The University of Texas System
- Applicants: The Board of Regents, The University of Texas System
- Inventors: Sunil A. Sheth; Luca Giancardo; Sean I. Savitz
- Web page: https://patentgrep.com/patent/US20220284581A1

## CPC

- G06T 7/0016: {involving temporal comparison}
- A61B 5/02042: {Determining blood loss or bleeding, e.g. during a surgical procedure}
- A61B 5/4842: {Monitoring progression or stage of a disease}
- A61B 5/7267: {involving training the classification device}
- A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor}
- A61B 6/032: {Transmission computed tomography [CT]}
- A61B 6/501: {for diagnosis of the head, e.g. neuroimaging or craniography}
- A61B 6/504: {for diagnosis of blood vessels, e.g. by angiography}
- A61B 6/507: {for determination of haemodynamic parameters, e.g. perfusion CT}
- A61B 6/5217: {extracting a diagnostic or physiological parameter from medical diagnostic data}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06T 12/00: Tomographic reconstruction from projections
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30016: Brain
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- 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

In one embodiment, a patient's brain is evaluated after onset of a stroke by capturing computed tomography angiography (CTA) images of the brain, analyzing the CTA images with a CTA image analysis program to evaluate the patient's brain, and generating results based upon the analysis that provide an assessment of the brain. In some cases, the CTA image analysis program comprises a machine-learning algorithm that has been trained on the results of perfusion imaging analysis.

## Claims

### Claim 1

A method for evaluating the brain after onset of a stroke, the method comprising:
capturing computed tomography angiography (CTA) images of a patient's brain;
analyzing the CTA images with a CTA image analysis program to evaluate the patient's brain; and
generating results based upon the analysis that provide an assessment of the patient's brain.

### Claim 2 (depends on 1)

The method of claim 1, wherein capturing CTA images comprises capturing the CTA images within 24 hours of the patient experiencing the onset of stroke symptoms.

### Claim 3 (depends on 1)

The method of claim 1, wherein analyzing the CTA images comprises determining an extent of an existing infarction.

### Claim 4 (depends on 1)

The method of claim 1, wherein analyzing the CTA images comprises determining an amount of brain tissue at risk of infarction.

### Claim 5 (depends on 1)

The method of claim 1, wherein analyzing the CTA images comprises determining the presence or absence of large vessel occlusion.

### Claim 6 (depends on 1)

The method of claim 1, wherein analyzing the CTA images comprises determining the presence or absence of brain hemorrhage.

### Claim 7 (depends on 1)

The method of claim 1, wherein generating results comprises presenting an indication as to whether or not endovascular stroke therapy is advisable for the patient.

### Claim 8 (depends on 1)

The method of claim 1, wherein the CTA image analysis program comprises a machine-learning algorithm that has been trained on results of perfusion imaging analysis.

### Claim 9 (depends on 8)

The method of claim 8, wherein the machine-learning algorithm comprises a convolutional neural network.

### Claim 10 (depends on 9)

The method of claim 9, wherein the convolutional neural network is configured to compare the two hemispheres of the patient's brain both in the presence and in the absence of blood vessels in the CTA images to identify and characterize the patient's brain.

### Claim 11 (depends on 10)

The method of claim 10, wherein the convolutional neural network comprises a merge layer that calculates an absolute difference between high-level convolution filter outputs common to the two hemispheres, which provides information as to the asymmetry of the two hemispheres.

### Claim 12 (depends on 1)

The method of claim 1, further comprising, prior to analyzing the CTA images, processing the CTA images to remove undesired anatomical features from the images.

### Claim 13 (depends on 1)

The method of claim 1, further comprising, prior to analyzing the CTA images, registering the CTA images to a brain atlas.

### Claim 14

A non-transitory computer-readable medium that stores a computed tomography angiography (CTA) image analysis program comprising computer-executable instructions configured to:
receive CTA images of a patient's brain;
analyze the CTA images to evaluate the patient's brain; and
generate results based upon the analysis that provide an assessment of the patient's brain.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the CTA image analysis program is configured to determine an extent of an existing infarction.

### Claim 16 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the CTA image analysis program is configured to determine an amount of brain tissue at risk of infarction.

### Claim 17 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the CTA image analysis program is configured to determine the presence or absence of large vessel occlusion.

### Claim 18 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the CTA image analysis program is configured to determine the presence or absence of brain hemorrhage.

### Claim 19 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the CTA image analysis program comprises a machine-learning algorithm that has been trained on results of perfusion imaging analysis.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein the machine-learning algorithm comprises a convolutional neural network.

### Claim at position 21

-24. (canceled)
