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

Pranab Samanta, Nitin Singhal
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1019-1033, 2022.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-samanta22a, title = {YAMU: Yet Another Modified U-Net Architecture for Semantic Segmentation}, author = {Samanta, Pranab and Singhal, Nitin}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1019--1033}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/samanta22a/samanta22a.pdf}, url = {https://proceedings.mlr.press/v172/samanta22a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T YAMU: Yet Another Modified U-Net Architecture for Semantic Segmentation %A Pranab Samanta %A Nitin Singhal %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-samanta22a %I PMLR %P 1019--1033 %U https://proceedings.mlr.press/v172/samanta22a.html %V 172 %X 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.
APA
Samanta, P. & Singhal, N.. (2022). YAMU: Yet Another Modified U-Net Architecture for Semantic Segmentation. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1019-1033 Available from https://proceedings.mlr.press/v172/samanta22a.html.

Related Material