ERDES: A Benchmark Video Dataset for Retinal Detachment and Macular Status Classification in Ocular Ultrasound
This addresses the problem of limited expertise in ultrasound interpretation for RD diagnosis, especially in resource-limited settings, by enabling ML model development, though it is incremental as it focuses on dataset creation rather than novel algorithms.
The authors tackled the lack of public data for automated retinal detachment (RD) and macular status classification in ocular ultrasound by introducing ERDES, the first open-access dataset of labeled ultrasound video clips, and provided baseline benchmarks using spatiotemporal CNNs, achieving competitive performance (e.g., up to 0.85 F1-score for RD detection).
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/.