# US 2023/0410302 A1 · Medical information processing apparatus, medical information processing method, and storage medium

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

- Number: US 2023/0410302 A1
- Document ID: US20230410302A1
- Status: Published application
- Kind: A1
- Application number: 18/329,851
- Filed: 2023-06-06
- Published: 2023-12-21
- Earliest claimed: 2022-06-10
- Assignees: Canon Medical Systems Corporation
- Applicants: Canon Medical Systems Corporation
- Inventors: Kosuke ARITA; Longxun PIAO; Sho SASAKI; Yudai YAMAZAKI; Yuka SHIMOMURA; Asateru KIMURA
- Web page: https://patentgrep.com/patent/US20230410302A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G16H 50/50: for simulation or modelling of medical disorders
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H 40/67: for remote operation
- 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
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30004: Biomedical image processing
- H04N 1/407: Control or modification of tonal gradation or of extreme levels, e.g. background level
- H04N 1/6005: {with luminance or chrominance signals, e.g. LC1C2, HSL or YUV}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A medical information processing apparatus of an embodiment includes processing circuitry. The processing circuitry acquires biometric data regarding a subject. The processing circuitry identifies reference data regarding a first feature amount on the basis of the biometric data. The processing circuitry acquires a second feature amount by inputting the first feature amount included in the biometric data into a model capable of mutually converting the first feature amount and the second feature amount. The processing circuitry derives pseudo-feature data regarding the first feature amount simulated by inputting the second feature amount into the model. The processing circuitry determines reliability scores with respect to the biometric data on the basis of the reference data and the pseudo-feature data.

## Claims

### Claim 1

A medical information processing apparatus comprising processing circuitry configured to:
acquire biometric data regarding a subject;
identify reference data regarding a first feature amount on the basis of the biometric data;
acquire a second feature amount by inputting the first feature amount included in the biometric data into a model capable of mutually converting the first feature amount and the second feature amount;
derive pseudo-feature data regarding the first feature amount simulated by inputting the second feature amount into the model; and
determine reliability scores with respect to the biometric data on the basis of the reference data and the pseudo-feature data.

### Claim 2 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the biometric data is biometric data of a single time phase or a plurality of time phases.

### Claim 3 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the first feature amount is a feature amount derived from the biometric data, and the second feature amount is a feature amount derived from the first feature amount.

### Claim 4 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the processing circuitry is configured to:
identify reference data for each of a plurality of first feature amounts on the basis of the biometric data;
derive a plurality of second feature amounts by inputting the first feature amounts into the model;
derive a plurality of pieces of pseudo-feature data by inputting the plurality of the second feature amounts into the model; and
determine the reliability scores on the basis of the plurality of pieces of reference data and the plurality of pieces of pseudo-feature data.

### Claim 5 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the biometric data includes an image, and the processing circuitry determines a reliability score for each pixel included in the image or in a predetermined image range.

### Claim 6 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the processing circuitry generates an image including information on the reliability scores.

### Claim 7 (depends on 6)

The medical information processing apparatus according to claim 6, wherein the processing circuitry generates an image by masking a region where the reliability scores are less than a threshold value in the area of an image acquired as the biometric data of the subject.

### Claim 8 (depends on 6)

The medical information processing apparatus according to claim 6, wherein the processing circuitry generates an image for inducing re-acquisition of the biometric data if the reliability scores are less than the threshold value.

### Claim 9 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the processing circuitry trains a model using biometric data adjusted on the basis of the reliability scores.

### Claim 10

A medical information processing method, using a computer, comprising:
acquiring biometric data regarding a subject;
identifying reference data regarding a first feature amount on the basis of the biometric data;
acquiring a second feature amount by inputting the first feature amount included in the biometric data into a model capable of mutually converting the first feature amount and the second feature amount;
deriving pseudo-feature data regarding the first feature amount simulated by inputting the second feature amount into the model; and
determining reliability scores with respect to the biometric data on the basis of the reference data and the pseudo-feature data.

### Claim 11

A non-transitory computer-readable recording medium storing a program causing a computer to:
acquire biometric data regarding a subject;
identify reference data regarding a first feature amount on the basis of the biometric data;
acquire a second feature amount by inputting the first feature amount included in the biometric data into a model capable of mutually converting the first feature amount and the second feature amount;
derive pseudo-feature data regarding the first feature amount simulated by inputting the second feature amount into the model; and
determine reliability scores with respect to the biometric data on the basis of the reference data and the pseudo-feature data.