# US 10,765,316 B2 · Ophthalmic information processing system, ophthalmic information processing method, and recording medium

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

- Number: US 10,765,316 B2
- Document ID: US10765316B2
- Status: Granted
- Kind: B2
- Application number: 15/925,922
- Filed: 2018-03-20
- Published: 2018-12-27
- Granted: 2020-09-08
- Earliest claimed: 2017-06-27
- Assignees: Topcon Corporation; Tohoku University; Riken
- Applicants: Topcon Corporation; Tohoku University; Riken
- Inventors: Guangzhou An; Masahiro Akiba; Toru Nakazawa; Kazuko Omodaka; Hideo Yokota
- Web page: https://patentgrep.com/patent/US10765316B2

## CPC

- A61B 3/14: Arrangements specially adapted for eye photography
- A61B 3/0025: {characterised by electronic signal processing, e.g. eye models}
- A61B 3/102: {for optical coherence tomography [OCT]}
- A61B 3/1233: {for measuring blood flow, e.g. at the retina}
- G06T 7/0012: {Biomedical image inspection}
- G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT]
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30041: Eye; Retina; Ophthalmic
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An ophthalmic information processing system according to an embodiment includes a receiver and a processor. The receiver receives morphological data of an eye fundus of a subject. In addition, the receiver receives background data of the subject. The processor executes optic nerve head shape classification based on the morphological data and the background data received by the receiver.

## Claims

### Claim 1

An ophthalmic information processing system comprising:
a receiver that receives morphological data of an eye fundus of a subject and background data of the subject; and
a processor that executes optic nerve head shape classification, using an artificial intelligence-based classifier, based on the morphological data and the background data.

### Claim 2 (depends on 1)

The ophthalmic information processing system of claim 1, further comprising a storage that pre-stores learning information generated by machine learning based on a same type of data group as the morphological data and a same type of data group as the background data,
wherein the processor executes the optic nerve head shape classification based on the learning information, the morphological data and the background data.

### Claim 3 (depends on 2)

The ophthalmic information processing system of claim 2, wherein
the morphological data comprises at least one of cupping area, average cupping depth, maximum cupping depth, nasal rim-to-disc area ratio, horizontal disc angle, superior nasal circumpapillary retinal nerve fiber layer average thickness, and superior circumpapillary retinal nerve fiber layer average thickness,
the background data comprises at least one of age and spherical equivalent,
the learning information comprises a classification model generated by learning using an artificial neural network, and
the processor comprises a neural network classifier.

### Claim 4 (depends on 2)

The ophthalmic information processing system of claim 2, wherein
the morphological data comprises at least one of horizontal disc angle, nasal rim-to-disc area ratio, average cupping depth, cup-to-disc area ratio, and superior nasal circumpapillary retinal nerve fiber layer average thickness,
the background data comprises at least one of age and spherical equivalent,
the learning information comprises a classification model generated by learning using a gradient boosting decision tree, and
the processor comprises a gradient boosting decision tree classifier.

### Claim 5 (depends on 2)

The ophthalmic information processing system of claim 2, wherein
the morphological data comprises at least one of horizontal disc diameter, average cupping depth, nasal rim-to-disc area ratio, horizontal disc angle, superior nasal circumpapillary retinal nerve fiber layer average thickness, superior circumpapillary retinal nerve fiber layer average thickness, and disc retinal pigment epithelium height difference,
the background data comprises at least one of age and spherical equivalent,
the learning information comprises a classification model generated by learning using a support vector machine, and
the processor comprises a support vector machine classifier.

### Claim 6 (depends on 2)

The ophthalmic information processing system of claim 2, wherein
the morphological data comprises at least one of superior circumpapillary retinal nerve fiber layer average thickness, nasal rim-to-disc area ratio, horizontal disc angle, and average cupping depth,
the background data comprises at least one of age and spherical equivalent,
the learning information comprises a classification model generated by learning using Bayes, and
the processor comprises a Bayes classifier.

### Claim 7 (depends on 2)

The ophthalmic information processing system of claim 2, further comprising a learner that executes machine learning based on the same type of data group as the morphological data and the same type of data group as the background data to generate the learning information.

### Claim 8 (depends on 1)

The ophthalmic information processing system of claim 1, wherein
the processor executes the optic nerve head shape classification to determine confidence for each of one or more types of optic nerve head shape, and
the system further comprising a display controller that displays the confidence of the one or more types on a display device.

### Claim 9 (depends on 1)

The ophthalmic information processing system of claim 1, wherein at least part of the morphological data is generated by analyzing data of the eye fundus acquired using optical coherence tomography.

### Claim 10 (depends on 9)

The ophthalmic information processing system of claim 9, further comprising an analysis processor that analyzes data of the eye fundus acquired using optical coherence tomography to generate morphological data.

### Claim 11 (depends on 10)

The ophthalmic information processing system of claim 10, further comprising an optical coherence tomography apparatus that acquires data of the eye fundus using optical coherence tomography.

### Claim 12 (depends on 1)

The ophthalmic information processing system of claim 1, wherein the receiver receives at least part of the background data directly or indirectly from an electronic medical record system.

### Claim 13

A method of processing ophthalmic information executed by a computer, the method comprising:
receiving morphological data of an eye fundus of a subject and background data of the subject; and
executing optical nerve head shape classification, using an artificial intelligence-based classifier, based on the morphological data and the background data.

### Claim 14 (depends on 13)

A non-transitory computer-readable recording medium storing a program that causes a computer to execute the ophthalmic information processing method of claim 13.