3D AI OCT Classification for Glaucoma and Myopia

Solution Overview

Problem

Current optical coherence tomography (OCT) systems face challenges in accurately detecting glaucomatous optic neuropathy (GON) and myopic optic disc morphology due to poor image quality, requiring skilled operators and extensive human processing, which is time-consuming and resource-intensive, and may lead to false positives or negatives, especially in busy clinical settings.

Innovation Solution

A 3D artificial intelligence (AI)-aided classification system integrating an information management system, AI image analysis, and user interface, utilizing deep learning models like SE-ResNeXt for image quality control and ResNet-37 for GON and myopic features detection, providing automated image analysis and rapid reporting, including image quality assessment, GON classification, and myopic features classification with AI scores and referral suggestions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If human operators manually assess OCT image quality and classify GON/MF, then diagnostic accuracy can be maintained, but time consumption and labor requirements increase significantly

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidtime consumption

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the OCT scanning device to automatically assess image quality and classify GON/MF without requiring manual intervention from trained operators. The AI-based classification system performs diagnostic functions autonomously, eliminating the time-consuming manual assessment process while maintaining diagnostic accuracy through validated algorithms.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of manual human assessment with an automated AI-based classification system. The deep learning models and image processing algorithms substitute for operator expertise, enabling automatic detection and classification of glaucomatous optic neuropathy and myopic features from OCT scans without human intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If skilled operators manually evaluate OCT scans, then diagnostic reliability is maintained, but operational complexity and resource requirements increase

Engineering Contradiction:

Improvediagnostic reliabilityVSAvoidoperational simplicity

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system enables self-service by allowing the OCT scanning device to automatically assess image quality and classify GON/MF without requiring manual intervention from trained operators. The AI-based classification system performs diagnostic functions autonomously, eliminating the need for skilled operators while maintaining diagnostic reliability through validated algorithms.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of manual human assessment with an automated AI-based classification system. The deep learning models and image processing algorithms substitute for operator expertise, enabling automatic detection and classification of glaucomatous optic neuropathy and myopic features from OCT scans without human intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If comprehensive manual assessment of OCT quality is performed, then measurement precision is improved, but productivity decreases

Engineering Contradiction:

Improveimage quality assessment precisionVSAvoidscreening throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system enables self-service by allowing the OCT scanning device to automatically assess image quality and classify GON/MF without requiring manual intervention from trained operators. The AI-based classification system performs diagnostic functions autonomously, improving productivity by eliminating time-consuming manual assessment while maintaining measurement precision through validated algorithms.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of manual human assessment with an automated AI-based classification system. The deep learning models and image processing algorithms substitute for operator expertise, enabling automatic detection and classification of glaucomatous optic neuropathy and myopic features from OCT scans without human intervention, thereby increasing screening throughput.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240265542A1Three-dimensional artificial intelligence-aided classification system for glaucomatous optic neuropathy and myopic optic disc morphology from optical coherence tomography scans

Publication Date: 2024.08.08 THE CHINESE UNIVERSITY OF HONG KONG

AI summary

The subject invention pertains to an artificial intelligence-aided classification system for glaucomatous optic neuropathy (GON) and myopic optic disc morphology (myopic features, MF) from three-dimensional (3D) optical coherence tomography (OCT) scans, which includes a deep-learning (DL) based “pre-diagnosis model” for image quality control and a multi-task DL-based classification and visualization model for GON and MF detection, including heatmaps for visualizing the identified features. The invention provides an Al-platform with the integration of developed 3D DL algorithms, an information management system, connecting to a commercially available OCT device. This Al-platform includes a user interface for real-time OCT image extraction, input data configuration, image uploading, images analysis via a graphics processing unit (GPU) server, and Al reports generation. The platform provides outputs including image quality, GON classification, MF classification, AI scores, and referral suggestion.