Test UWF image datasets

<b>Background</b>Retinal breaks are critical lesions that can lead to retinal detachment and vision loss if not detected and treated early. Automated and precise delineation of retinal breaks using ultra-widefield (UWF) fundus images remains a significant challenge in ophthalmology.<b>Objective</b>This study aimed to develop and validate a deep learning model based on the PraNet architecture for the accurate delineation of retinal breaks in UWF images, with a particular focus on segmentation performance in retinal break–positive cases..<b>Methods</b>We developed a deep learning segmentation model based on the PraNet architecture. Unlike previous studies, we used a comprehensive dataset of UWF fundus images with no exclusion criteria, reflecting the diversity and complexity of real-world clinical practice. The model was trained and validated on this dataset. Model performance was evaluated using both image-wise segmentation metrics (accuracy, precision, recall, Intersection over Union (IoU), dice score, centroid distance score) and lesion-wise detection metrics (sensitivity, positive predictive value).<b>Results</b>The PraNet-based model achieved an accuracy of 0.996, a precision of 0.635, a recall of 0.756 , an IoU of 0.539, a dice score of 0.652, and a centroid distance score of 0.081 for pixel-level detection of retinal breaks. The lesion-wise sensitivity was calculated as 0.885, and the positive predictive value (PPV) was 0.742.<b>Conclusions</b>To our knowledge, this is the first study to present pixel-level localization of retinal breaks using deep learning on UWF images. Our findings demonstrate that the PraNet-based model provides precise and robust pixel-level segmentation of retinal breaks in UWF fundus images. This approach offers a clinically applicable tool for the precise delineation of retinal breaks, with the potential to improve patient outcomes. Future work should focus on external validation across multiple institutions and integration of additional annotation strategies to further enhance model performance and generalizability.<br>The full dataset is pseudonymized and may be shared upon approval by the Ethics Committee of Jichi Medical University following a reasonable request for collaborative research. Here, “pseudonymized” refers to data processed such that individuals cannot be identified without the use of separately kept correspondence tables.