| Title: | Retinal disease classification from spectral domain optical coherence tomography using lesion attentive fusion |
| Journal: | Scientific Reports |
| Published: | 4 Aug 2026 |
| DOI: | https://doi.org/10.1038/s41598-026-64770-8 |
| URL: | https://www.nature.com/articles/s41598-026-64770-8_reference.pdf |
Publication 21088
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Retinal diseases such as central serous chorioretinopathy (CSC) and neovascular age-related macular degeneration (nAMD) can cause permanent vision loss, and their diagnosis from three-dimensional spectral-domain optical coherence tomography (SD-OCT) volumes is challenging because lesions may appear in only a few critical slices. We developed a lesion-attentive fusion (LAF) model that automatically weights pathological slices for volume-level retinal disease classification. The model, comprising a slice-wise encoder, LAF layer, and classifier, was evaluated on 641 SD-OCT volumes (16,025 B-scans) from 589 patients with nAMD or CSC subtypes or normal retinas. In eight-fold cross-validation, it achieved 84.85% accuracy and an F1-score of 82.16%, outperforming baseline fusion models. On a selected test fold, the model also outperformed all six independent ophthalmologists. Its slice-level attention agreed with expert lesion-slice annotations (Cohen's kappa = 0.67, p < 0.001), and Grad-CAM highlighted disease-relevant regions. We additionally evaluated cross-disease applicability using 626 UK Biobank OCT volumes from 462 patients across five retinal disease categories with patient-level five-fold cross-validation. ConvNeXt-Tiny with LAF achieved the highest macro F1-score of 0.7500 ± 0.0583. These results suggest that lesion-attentive aggregation enables accurate and interpretable classification of retinal diseases from OCT volumes.</p>
13 Authors
- Junseo Ko
- Jinyoung Han
- Jeewoo Yoon
- Seong Choi
- Hyunseon Won
- Migyeong Yang
- Jian Park
- Jee-Eun Kim
- Joon Seo Hwang
- Jeong Mo Han
- Tae Keun Yoo
- Ji In Park
- Daniel Duck-Jin Hwang
Enabling scientific discoveries that improve human health