Full end-to-end diagnostic workflow automation of 3D OCT via foundation model-driven AI for retinal diseases

2026-02-03

AI Summary

This work addresses the limitations of existing fully automated diagnostic approaches for 3D optical coherence tomography (OCT) imaging, which are hindered by multi-stage pipelines and single-slice, single-task models that impede efficient end-to-end analysis. The authors propose FOCUS, the first foundation-model-based framework enabling fully automated, end-to-end 3D OCT diagnosis. FOCUS integrates image quality assessment, anomaly detection, and multi-disease classification within a unified architecture, and introduces a novel adaptive aggregation strategy to effectively fuse 2D slice-level predictions into patient-level diagnoses. On an internal test set, FOCUS achieves F1 scores of 99.01%, 97.46%, and 94.39% for quality assessment, anomaly detection, and patient-level diagnosis, respectively. External multicenter validation demonstrates robust performance with F1 scores ranging from 90.22% to 95.24%, matching expert-level accuracy while significantly improving diagnostic efficiency.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Other Foundations of Machine Learning

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Optical coherence tomography (OCT) has revolutionized retinal disease diagnosis with its high-resolution and three-dimensional imaging nature, yet its full diagnostic automation in clinical practices remains constrained by multi-stage workflows and conventional single-slice single-task AI models. We present Full-process OCT-based Clinical Utility System (FOCUS), a foundation model-driven framework enabling end-to-end automation of 3D OCT retinal disease diagnosis. FOCUS sequentially performs image quality assessment with EfficientNetV2-S, followed by abnormality detection and multi-disease classification using a fine-tuned Vision Foundation Model. Crucially, FOCUS leverages a unified adaptive aggregation method to intelligently integrate 2D slices-level predictions into comprehensive 3D patient-level diagnosis. Trained and tested on 3,300 patients (40,672 slices), and externally validated on 1,345 patients (18,498 slices) across four different-tier centers and diverse OCT devices, FOCUS achieved high F1 scores for quality assessment (99.01%), abnormally detection (97.46%), and patient-level diagnosis (94.39%). Real-world validation across centers also showed stable performance (F1: 90.22%-95.24%). In human-machine comparisons, FOCUS matched expert performance in abnormality detection (F1: 95.47% vs 90.91%) and multi-disease diagnosis (F1: 93.49% vs 91.35%), while demonstrating better efficiency. FOCUS automates the image-to-diagnosis pipeline, representing a critical advance towards unmanned ophthalmology with a validated blueprint for autonomous screening to enhance population scale retinal care accessibility and efficiency.

Problem

• 3D OCT
• retinal diseases
• diagnostic automation
• end-to-end workflow
• clinical AI

Innovation

• foundation model
• end-to-end automation
• 3D OCT
• adaptive aggregation
• retinal disease diagnosis