Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation
This work addresses the need for accurate gland segmentation in digital pathology, particularly for colorectal cancer diagnosis, but it is incremental as it builds on existing deep learning and regularization techniques.
The paper tackled the problem of segmenting colon glands in histopathology images by developing a learning-based algorithm that combines deep convolutional neural networks with total variation regularization, achieving tissue classification accuracies of 98% and 94% on test sets.
Segmentation of histopathology sections is an ubiquitous requirement in digital pathology and due to the large variability of biological tissue, machine learning techniques have shown superior performance over standard image processing methods. As part of the GlaS@MICCAI2015 colon gland segmentation challenge, we present a learning-based algorithm to segment glands in tissue of benign and malignant colorectal cancer. Images are preprocessed according to the Hematoxylin-Eosin staining protocol and two deep convolutional neural networks (CNN) are trained as pixel classifiers. The CNN predictions are then regularized using a figure-ground segmentation based on weighted total variation to produce the final segmentation result. On two test sets, our approach achieves a tissue classification accuracy of 98% and 94%, making use of the inherent capability of our system to distinguish between benign and malignant tissue.