Leveraging Spectrum to Enhance the Accuracy of Retinal Layer Segmentation

In the early development of many fundus diseases, changes in retinal layer thickness occur, and optical coherence tomography (OCT) serves as the gold standard for detecting variations in retinal layer thickness. Consequently, extensive research has been conducted on retinal layer segmentation (RLS) based on OCT images. However, current breakthroughs in RLS primarily focus on innovations in deep learning (DL) models and improvements in training strategies, which constrains the means to enhance the accuracy of RLS. We have discovered a new dimension of spectral information that can be utilized to improve the precision of RLS. Experimental results demonstrate that the accuracy of RLS, measured by the mIoU metric, can be maximized with an improvement of up to 1.57 percentage points, and that different combinations of spectral images vary in their effectiveness at enhancing segmentation outcomes. Our study will introduce novel research avenues in the domain of RLS based on DL.