# US 2022/0036553 A1 · Cranial ct-based grading method and system

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

- Number: US 2022/0036553 A1
- Document ID: US20220036553A1
- Status: Published application
- Kind: A1
- Application number: 17/299,685
- Filed: 2019-11-14
- Published: 2022-02-03
- Earliest claimed: 2018-12-14
- Assignees: Union Strong (Beijing) Technology Co. Ltd.
- Applicants: Union Strong (Beijing) Technology Co. Ltd.
- Inventors: Hailan JIN; Ling SONG; Yin YIN; Guangming YANG; Yangyang YAO; Pengxiang LI; Lan QIN
- Web page: https://patentgrep.com/patent/US20220036553A1

## CPC

- G06V 10/82: using neural networks
- G16H 30/40: for processing medical images, e.g. editing
- G06F 18/2413: based on distances to training or reference patterns
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/0014: {using an image reference approach}
- G06V 10/764: using classification, e.g. of video objects
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- 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 2207/30168: Image quality inspection
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06V 2201/031: of internal organs
- G06V 2201/033: of skeletal patterns
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Disclosed are a cranial CT-based grading method and a corresponding system, which relate to the field of medical imaging. The cranial CT-based grading method as disclosed solves the problems of relatively great subjective disparities and poor operability in eye-balling ASPECTS assessment. The grading method includes: determining frames where target image slices are located from to-be-processed multi-frame cranial CT data; extracting target areas; performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area; and outputting a grading outcome based on infarct judgment outcomes regarding all target areas. The grading method and system as disclosed may eliminate or mitigate the diagnosis disparities caused by human factors and imaging deviations due to different imaging devices, and shorten the time taken by human observation, consideration, and bared-eye grading, thereby serving as a computer-aided method to provide reference for medical studies on stoke.

## Claims

### Claim 1

A cranial CT-based grading method, comprising:
determining frames where target image slices are located from to-be-processed multi-frame cranial CT data, wherein the target image slices refer to the slices, where the cranial CT data for being graded are located, in the cranial CT;
extracting target areas based on the frames where the target image slices are located, wherein the target areas refer to areas for being graded in the cranial CT data;
performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area; and
outputting a grading outcome based on infarct judgment outcomes regarding all target areas.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining frames where target image slices are located from to-be-processed multi-frame cranial CT data specifically comprises:
extracting image features of the to-be-processed multi-frame cranial CT data, and determining distances from respective frames of cranial CT data in the multi-frame cranial CT data to respective target image slices; and
determining the frames where the target image slices are located based on the distances from the respective frames of cranial CT data to the respective target image slices.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the extracting target areas based on the frames where the target image slices are located specifically comprises:
classifying each pixel point in the cranial CT data using digital labels based on the frames where the target image slices are located and outputting a two-dimensional matrix with digital labels corresponding to respective pixel points in the frames where the target image slices are located, wherein the digital labels are in one-to-one correspondence with the target areas, and the two-dimensional matrix is in correspondence with the frames where the target image slices are located.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area specifically comprises:
performing infarct judgment on each pixel point included in the target area to output an infarct judgment outcome regarding the target area.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area further comprises:
judging, based on the infarct judgment outcome regarding the target area, whether infarct is indicated in the target areas in both left and right cerebral hemispheres; and
if infarct is indicated in the target areas in both left and right cerebral hemispheres, further determining which specific side is infarcted, and correcting the infarct judgment outcome regarding the target area as an update infarct judgment outcome regarding the target area.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the outputting a grading outcome based on infarct judgment outcomes regarding all target areas specifically comprises:
determining all infarcted target areas based on the infarct judgment outcomes regarding all target areas;
subtracting, based on weights allotted to respective target areas, weights of the infarcted target areas from the total score to output a resulting value as the grading outcome.

### Claim 7

A cranial CT-based grading system, comprising:
an area extracting module configured for extracting target areas from to-be-processed multi-frame cranial CT data, wherein the target areas refer to areas for being graded in the cranial CT data;
an infarct identifying module configured for performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area; and
a grading module configured for outputting a grading outcome based on infarct judgment outcomes regarding all target areas.

### Claim 8 (depends on 7)

The system according to claim 7, wherein the extracting target areas from to-be-processed multi-frame cranial CT data specifically comprises:
determining frames where target image slices are located from the to-be-processed multi-frame cranial CT data, wherein the target image slices refer to the slices, where the cranial CT data for being graded are located, in the cranial CT; and
extracting the target areas based on the frames where the target image slices are located, wherein the target areas refer to areas for being graded in the cranial CT data.

### Claim 9 (depends on 8)

The system according to claim 8, wherein the determining frames where target image slices are located from the to-be-processed multi-frame cranial CT data specifically comprises:
extracting image features of the to-be-processed multi-frame cranial CT data, and determining distances from respective frames of cranial CT data in the multi-frame cranial CT data to respective target image slices; and
determining the frames where the target image slices are located based on the distances from the respective frames of cranial CT data to the respective target image slices.

### Claim 10 (depends on 8)

The system according to claim 8, wherein the extracting the target areas based on the frames where the target image slices are located specifically comprises:
classifying each pixel point in the cranial CT data using digital labels based on the frames where the target image slices are located and outputting a two-dimensional matrix with digital labels corresponding to respective pixel points in the frames where the target image slices are located, wherein the digital labels are in one-to-one correspondence with the target areas, and the two-dimensional matrix is in correspondence with the frames where the target image slices are located.

### Claim 11 (depends on 7)

The system according to claim 7, wherein the performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area specifically comprises:
performing infarct judgment on each pixel point included in the target area to output an infarct judgment outcome regarding the target area.

### Claim 12 (depends on 7)

The system according to claim 7, wherein the performing infarct judgment on each target area included in the target areas to output an infarct judgment outcome regarding the target area further comprises:
judging, based on the infarct judgment outcome regarding the target area, whether infarct is indicated in the target areas in both left and right cerebral hemispheres; and
if infarct is indicated in the target areas in both left and right cerebral hemispheres, further determining which specific side is infarcted, and correcting the infarct judgment outcome regarding the target area as an update infarct judgment outcome regarding the target area.

### Claim 13 (depends on 7)

The system according to claim 7, wherein the outputting a grading outcome based on infarct judgment outcomes regarding all target areas specifically comprises:
determining all infarcted target areas based on the infarct judgment outcomes regarding all target areas; and
subtracting, based on weights allotted to respective target areas, weights of the infarcted target areas from the total score to output a resulting value as the grading outcome.
