Retinal Image Segmentation with a Structure-Texture Demixing Network
This work addresses the problem of biased models in retinal image segmentation for automatic disease diagnosis, representing an incremental improvement over existing methods.
The paper tackled the challenge of retinal image segmentation by proposing a structure-texture demixing network to separate mixed components, resulting in improved segmentation performance on tasks like blood vessel and optic disc/cup segmentation.
Retinal image segmentation plays an important role in automatic disease diagnosis. This task is very challenging because the complex structure and texture information are mixed in a retinal image, and distinguishing the information is difficult. Existing methods handle texture and structure jointly, which may lead biased models toward recognizing textures and thus results in inferior segmentation performance. To address it, we propose a segmentation strategy that seeks to separate structure and texture components and significantly improve the performance. To this end, we design a structure-texture demixing network (STD-Net) that can process structures and textures differently and better. Extensive experiments on two retinal image segmentation tasks (i.e., blood vessel segmentation, optic disc and cup segmentation) demonstrate the effectiveness of the proposed method.