Robust Detection of Retinal Neovascularization in Widefield Optical Coherence Tomography

2025-11-21

AI Summary

This study addresses the clinical challenge of detecting vision-threatening retinal neovascularization (RNV) in diabetic retinopathy (DR) using wide-field optical coherence tomography angiography (OCTA). We propose the first end-to-end automated detection and quantitative analysis framework specifically designed for wide-field OCTA images. Departing from conventional multi-layer retinal segmentation–based approaches, we reformulate RNV identification as a binary localization task, enabling direct lesion detection and pixel-level segmentation. The model is trained and validated on a large-scale, multi-center, multi-device OCTA dataset. It achieves robust cross-device performance with AUCs of 0.96–0.99 and segmentation mIoUs of 0.76–0.88—substantially outperforming existing methods. The framework supports high-throughput clinical screening and longitudinal quantification of RNV growth, thereby facilitating precise DR staging and timely therapeutic intervention.

Technology Category

• Computer Vision: Segmentation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Hardware-aware ML

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Retinal neovascularization (RNV) is a vision threatening development in diabetic retinopathy (DR). Vision loss associated with RNV is preventable with timely intervention, making RNV clinical screening and monitoring a priority. Optical coherence tomography (OCT) angiography (OCTA) provides high-resolution imaging and high-sensitivity detection of RNV lesions. With recent commercial devices introducing widefield OCTA imaging to the clinic, the technology stands to improve early detection of RNV pathology. However, to meet clinical requirements these imaging capabilities must be combined with effective RNV detection and quantification, but existing algorithms for OCTA images are optimized for conventional, i.e. narrow, fields of view. Here, we present a novel approach for RNV diagnosis and staging on widefield OCT/OCTA. Unlike conventional methods dependent on multi-layer retinal segmentation, our model reframes RNV identification as a direct binary localization task. Our fully automated approach was trained and validated on 589 widefield scans (17x17-mm to 26x21-mm) collected from multiple devices at multiple clinics. Our method achieved a device-dependent area under curve (AUC) ranging from 0.96 to 0.99 for RNV diagnosis, and mean intersection over union (IOU) ranging from 0.76 to 0.88 for segmentation. We also demonstrate our method's ability to monitor lesion growth longitudinally. Our results indicate that deep learning-based analysis for widefield OCTA images could offer a valuable means for improving RNV screening and management.

Problem

• Detecting retinal neovascularization in widefield OCTA images
• Addressing limitations of existing narrow field algorithms
• Automating RNV diagnosis and lesion growth monitoring

Innovation

• Direct binary localization for RNV detection
• Automated deep learning on widefield OCTA scans
• Multi-device multi-clinic validation of algorithm performance