YAMU: Yet Another Modified U-Net Architecture for Semantic Segmentation

Digital histopathology images must be examined accurately and quickly as part of a pathologist’s clinical procedure. For histopathology image segmentation, different variants of U-Net and fully convolutional networks (FCN) are state-of-the-art. HistNet or histopathology network for semantic labelling in histopathology images, for example, is one of them. We improve our previously proposed model HistNet in this paper by introducing new skip pathways to the decoder stage to aggregate multiscale features and incorporate a feature pyramid to keep the contextual information. In addition, to boost performance, we employ a deep supervision training technique. We show that not only does the proposed design outperform the baseline, but it also outperforms state-of-the-art segmentation architectures with much fewer parameters.