# Colon cancer survival prediction from gland shapes within histology slides using deep learning

## TL;DR

This paper uses deep learning to analyze gland shapes in colon cancer tissue images to predict patient survival and identify high-risk groups.

## Contribution

The study introduces a deep learning-based gland segmentation approach that improves survival prediction in colorectal cancer using morphological features.

## Key findings

- DCAN outperformed U-Net in gland segmentation accuracy across diverse histology datasets.
- A Cox model using gland morphology features achieved a high concordance index for survival prediction.
- Stratification into high- and low-risk groups showed significant survival differences (log-rank p-value: 0.01317).

## Abstract

This study investigates the application of deep learning techniques for segmenting glands in histopathological images of colorectal cancer. We trained two convolutional neural network models, U-Net and DCAN, on a combination of the GlaS and CRAG datasets to enhance generalization across diverse histological appearances, selecting DCAN for its superior accuracy in delineating gland boundaries. The goal was to achieve robust gland segmentation applicable to whole slide images (WSIs) from The Cancer Genome Atlas (TCGA). Using the segmented glands, we extracted patient-level morphological features and used them to predict survival outcomes. A Cox proportional hazards model was trained on these features and achieved a high concordance index, indicating strong predictive performance. Patients were then stratified into high- and low-risk groups, with significant differences in survival distributions (log-rank p-value: 0.01317). In addition, we benchmarked our models against state-of-the-art gland segmentation methods on GlaS and CRAG, highlighting the trade-off between domain-specific accuracy and cross-dataset robustness.