U-Net with Graph Based Smoothing Regularizer for Small Vessel Segmentation on Fundus Image
This work addresses the challenge of accurately detecting small retinal vessels for medical diagnosis, but it is incremental as it builds on the U-Net framework with a novel regularizer.
The paper tackled the problem of segmenting small, low-contrast retinal blood vessels in fundus images, where existing methods focus on large vessels and fail with disconnected small vessels. The result showed that adding a graph-based smoothing regularizer to a U-Net framework improved segmentation of small vessels and reconnected fragmented ones, with numerical and visual evidence of effectiveness.
The detection of retinal blood vessels, especially the changes of small vessel condition is the most important indicator to identify the vascular network of the human body. Existing techniques focused mainly on shape of the large vessels, which is not appropriate for the disconnected small and isolated vessels. Paying attention to the low contrast small blood vessel in fundus region, first time we proposed to combine graph based smoothing regularizer with the loss function in the U-net framework. The proposed regularizer treated the image as two graphs by calculating the graph laplacians on vessel regions and the background regions on the image. The potential of the proposed graph based smoothing regularizer in reconstructing small vessel is compared over the classical U-net with or without regularizer. Numerical and visual results shows that our developed regularizer proved its effectiveness in segmenting the small vessels and reconnecting the fragmented retinal blood vessels.