Du-net based Unsupervised Contrastive Learning for Cancer Segmentation in Histology Images
In this paper, we introduce an unsupervised cancer segmentation framework for histology images. The framework involves an effective contrastive learning scheme for extracting distinctive visual representations for segmentation. The encoder is a Deep U-Net (DU-Net) structure which contains an extra fully convolution layer compared to the normal U-Net. A contrastive learning scheme is developed to solve the problem of lacking training sets with high-quality annotations on tumour boundaries. A specific set of data augmentation techniques are employed to improve the discriminability of the learned colour features from contrastive learning. Smoothing and noise elimination are conducted using convolutional Conditional Random Fields. The experiments demonstrate competitive performance in segmentation even better than some popular supervised networks.
National Key Research and Development Program under Grant No. 2019YFC0118404, the Basic Public Welfare Research Project of Zhejiang Province (LGF20H180001)
Author affiliationSchool of Computing and Mathematical Sciences, University of Leicester
SourceICIRA 2022, The 15th International Conference on Intelligent Robotics and Applications. Harbin, China. August 1-3, 2022
- AM (Accepted Manuscript)