Advanced Assessment of Stroke in Retinal Fundus Imaging with Deep Multi-view Learning

2025-01-31

AI Summary

Current clinical practice lacks rapid, non-invasive screening tools for stroke and transient ischemic attack (TIA). Method: We propose MVS-Net, an end-to-end multi-view deep learning framework leveraging dual-eye retinal fundus images. It innovatively establishes a joint modeling framework centered on the macula and optic disc—enabling cross-eye feature relationship learning and end-to-end co-optimization of a dual-input convolutional neural network—thereby overcoming the limitations of single-eye, single-view diagnosis. Results: Evaluated on a real-world clinical dataset, MVS-Net achieves an AUC of 0.84, robustly demonstrating the feasibility and effectiveness of retinal imaging for non-invasive, rapid, and cost-efficient stroke/TIA screening. This work introduces a novel paradigm for early risk identification in primary care settings.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance

Abstract

Stroke is globally a major cause of mortality and morbidity, and hence accurate and rapid diagnosis of stroke is valuable. Retinal fundus imaging reveals the known markers of elevated stroke risk in the eyes, which are retinal venular widening, arteriolar narrowing, and increased tortuosity. In contrast to other imaging techniques used for stroke diagnosis, the acquisition of fundus images is easy, non-invasive, fast, and inexpensive. Therefore, in this study, we propose a multi-view stroke network (MVS-Net) to detect stroke and transient ischemic attack (TIA) using retinal fundus images. Contrary to existing studies, our study proposes for the first time a solution to discriminate stroke and TIA with deep multi-view learning by proposing an end-to-end deep network, consisting of multi-view inputs of fundus images captured from both right and left eyes. Accordingly, the proposed MVS-Net defines representative features from fundus images of both eyes and determines the relation within their macula-centered and optic nerve head-centered views. Experiments performed on a dataset collected from stroke and TIA patients, in addition to healthy controls, show that the proposed framework achieves an AUC score of 0.84 for stroke and TIA detection.

Problem

• Stroke Detection
• Transient Ischemic Attack
• Eye Image Analysis

Innovation

• MVS-Net
• Stroke Detection
• Binocular Image Analysis