A Generalized Motion Pattern and FCN based approach for retinal fluid detection and segmentation
This work addresses the need for efficient analysis of disease progression in ophthalmology, though it appears incremental as it builds on existing FCN methods with a novel motion-based feature.
The paper tackles the problem of automated detection and segmentation of retinal fluids in SD-OCT scans for diagnosing macular defects, achieving mean Dice scores of 0.61 to 0.73 and mean AUCs of 0.84 to 0.87 across three fluid types.
SD-OCT is a non-invasive cross-sectional imaging modality used for diagnosis of macular defects. Efficient detection and segmentation of the abnormalities seen as biomarkers in OCT can help in analyzing the progression of the disease and advising effective treatment for the associated disease. In this work, we propose a fully automated Generalized Motion Pattern(GMP) based segmentation method using a cascade of fully convolutional networks for detection and segmentation of retinal fluids from SD-OCT scans. General methods for segmentation depend on domain knowledge-based feature extraction, whereas we propose a method based on Generalized Motion Pattern (GMP) which is derived by inducing motion to an image to suppress the background.The proposed method is parallelizable and handles inter-scanner variability efficiently. Our method achieves a mean Dice score of 0.61,0.70 and 0.73 during segmentation and a mean AUC of 0.85,0.84 and 0.87 during detection for the 3 types of fluids IRF, SRF and PDE respectively.