Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation

TL;DR

This paper introduces a deep learning approach combining CNNs and total variation segmentation to accurately segment colon glands in histopathology images, effectively distinguishing benign from malignant tissues.

Contribution

The novel integration of CNN-based pixel classification with total variation regularization improves gland segmentation accuracy in colorectal cancer histopathology images.

Findings

Achieved 98% accuracy on one test set and 94% on another.

Effectively distinguished benign from malignant tissue.

Outperformed standard image processing methods.

Abstract

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.