Locate before Segment: Topology-Guided Retinal Layer Segmentation in Optical Coherence Tomography Images

Optical Coherence Tomography (OCT) is a non- invasive imaging technique that is instrumental in retinal disease diagnosis and treatment. Segmentation of retinal layers in OCT is an essential step, but remains challenging for common pixel-wise segmentation methods usually fail to obtain the correct layer topology. To tackle this challenge, we propose a novel Locate-to-Segment (L2S) framework to provide a layer region location guidance for pixel-wise labeling learning so as to obtain better segmentation with the correct topology and smooth boundaries. Specifically, a Structured Boundary Regression Network (SBRNet) is devised to first predict the surface positions. For effective learning on normal-size images, we design two regression branches to regress the top surface and eight layer widths separately in SBRNet to locate each layer region with absolutely correct orderings. Then, we take the prediction of SBRNet as an additional input for a common pixel-wise segmentation network to provide the guidance of correct topology. In this L2S manner, our framework takes merits of regression-based methods and pixel-wise labeling- based methods to obtain accurate segmentation with the correct topology and smooth continuous boundaries. Experimental results on a public retinal OCT dataset demonstrate the effectiveness of our method, outperforming state-of-the-art segmentation methods with the highest average Dice score of 90.29% and the lowest average MAD score of 0.782.