Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Clinical Assessment of Diabetic Retinopathy Severity
It addresses the need for early and accurate assessment of diabetic retinopathy to prevent vision loss, though it is incremental as it builds on existing deep learning models.
This study tackled the problem of automated segmentation of retinal layers, fluid, and hyperreflective foci in diabetic retinopathy using SD-OCT imaging, achieving a highest overall accuracy of DSC = 0.7719 and NSD = 0.8149 with the SwinUNETR model.
Diabetic retinopathy (DR) is a leading cause of vision loss, requiring early and accurate assessment to prevent irreversible damage. Spectral Domain Optical Coherence Tomography (SD-OCT) enables high-resolution retinal imaging, but automated segmentation performance varies, especially in cases with complex fluid and hyperreflective foci (HRF) patterns. This study proposes an active-learning-based deep learning pipeline for automated segmentation of retinal layers, fluid, and HRF, using four state-of-the-art models: U-Net, SegFormer, SwinUNETR, and VM-UNet, trained on expert-annotated SD-OCT volumes. Segmentation accuracy was evaluated with five-fold cross-validation, and retinal thickness was quantified using a K-nearest neighbors algorithm and visualized with Early Treatment Diabetic Retinopathy Study (ETDRS) maps. SwinUNETR achieved the highest overall accuracy (DSC = 0.7719; NSD = 0.8149), while VM-UNet excelled in specific layers. Structural differences were observed between non-proliferative and proliferative DR, with layer-specific thickening correlating with visual acuity impairment. The proposed framework enables robust, clinically relevant DR assessment while reducing the need for manual annotation, supporting improved disease monitoring and treatment planning.