A cascade-learning approach for automated segmentation of tumour epithelium in colorectal cancer

作者：

Highlights：

• A novel formulation for Epithelium segmentation.

• A new set of invariant shape and appearance descriptors.

• Supervised and dimension reduction techniques for tissue classification.

• A thorough experimental study with an application to histology images.

摘要

•A novel formulation for Epithelium segmentation.•A new set of invariant shape and appearance descriptors.•Supervised and dimension reduction techniques for tissue classification.•A thorough experimental study with an application to histology images.

论文关键词：Histology,Colorectal cancer,Tissue classification,Machine learning,Fuzzy pressure force,Axis of least inertia,Feature representation,Neural network

论文评审过程：Received 7 July 2018, Revised 23 September 2018, Accepted 15 October 2018, Available online 15 October 2018, Version of Record 23 October 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.10.030