ERDES: A Benchmark Video Dataset for Retinal Detachment and Macular Status Classification in Ocular Ultrasound

2025-08-05

AI Summary

Retinal detachment (RD) is a vision-threatening emergency requiring rapid diagnosis; macular involvement critically determines surgical urgency and visual prognosis, yet primary-care settings lack ophthalmologists skilled in ocular ultrasound interpretation. To address this gap, we introduce the first publicly available ultrasound video dataset jointly annotated for RD detection and macular status classification (intact vs. detached), establishing the first benchmark for this clinically critical task. We pioneer the use of temporal ultrasound video sequences—rather than static B-scans—for automated macular detachment assessment, overcoming limitations of prior image-based approaches. We systematically design and evaluate multiple spatiotemporal convolutional neural networks, establishing robust baseline performance on both RD detection and macular status classification. All data, expert-curated annotations, and training code are fully open-sourced, providing a reproducible foundation and resource infrastructure for AI-assisted acute ophthalmic diagnosis in resource-limited settings.

Technology Category

• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Retinal detachment (RD) is a vision-threatening condition that requires timely intervention to preserve vision. Macular involvement -- whether the macula is still intact (macula-intact) or detached (macula-detached) -- is the key determinant of visual outcomes and treatment urgency. Point-of-care ultrasound (POCUS) offers a fast, non-invasive, cost-effective, and accessible imaging modality widely used in diverse clinical settings to detect RD. However, ultrasound image interpretation is limited by a lack of expertise among healthcare providers, especially in resource-limited settings. Deep learning offers the potential to automate ultrasound-based assessment of RD. However, there are no ML ultrasound algorithms currently available for clinical use to detect RD and no prior research has been done on assessing macular status using ultrasound in RD cases -- an essential distinction for surgical prioritization. Moreover, no public dataset currently supports macular-based RD classification using ultrasound video clips. We introduce Eye Retinal DEtachment ultraSound, ERDES, the first open-access dataset of ocular ultrasound clips labeled for (i) presence of retinal detachment and (ii) macula-intact versus macula-detached status. The dataset is intended to facilitate the development and evaluation of machine learning models for detecting retinal detachment. We also provide baseline benchmarks using multiple spatiotemporal convolutional neural network (CNN) architectures. All clips, labels, and training code are publicly available at https://osupcvlab.github.io/ERDES/.

Problem

• Classify retinal detachment in ocular ultrasound videos
• Determine macula-intact vs macula-detached status
• Address lack of public datasets for RD ultrasound analysis

Innovation

• First open-access ocular ultrasound video dataset
• Spatiotemporal CNNs for retinal detachment classification
• Labels for macula-intact versus macula-detached status