Colorectal Cancer Segmentation with Adaptive Augmentation and Multi-Resolution Ensemble Models

2026-09-29

AI Summary

This study addresses the heavy reliance on manual effort and low efficiency in colorectal cancer pathological assessment by developing an automated segmentation pipeline for whole-slide images, enabling precise tumor grading and normal mucosa identification. Methodologically, it introduces a novel large language model (LLM)-guided adaptive augmentation strategy, integrated with a dense prediction Transformer, multi-resolution test-time augmentation, soft-voting ensembling, and morphological closing as post-processing. Experimental results demonstrate that this framework substantially improves the F1 score from 62.92 to 69.84. The source code has been made publicly available.

Abstract

Colorectal cancer (CRC) is the second most deadly and third most common cancer, and the leading cause of death among gastrointestinal cancers. Early diagnosis is crucial for the treatment of this cancer and increasing the survival rates. Although CRC is more common in developed regions, its occurrence is also increasing in developing regions as well. CRC diagnosis relies on histopathology assessment post-biopsy. Automated deep learning algorithms can significantly reduce diagnosis time, enhancing efficiency and supporting timely clinical decisions. We present an automated segmentation pipeline for whole-slide histopathology images that labels tumor grades 1-3 and normal mucosa. It utilizes dense prediction transformers with various encoder backbones, overlapping patches, and test-time augmentation. An adaptive augmentation policy, guided by large language models, further improves training. Top models were ensembled via soft voting, and mask refining post-processing steps, Gaussian blurring, morphological closing, and connected components analysis. On a colorectal cancer grade dataset, our method improved the F1 score from 62.92 to 69.84. Code is available here: github.com/caglarmert/ICIP2025

Problem

• Colorectal Cancer
• Histopathology Image Segmentation
• Tumor Grading
• Whole-Slide Images

Innovation

• Dense Prediction Transformers
• Adaptive Augmentation
• Large Language Models
• Multi-Resolution Ensemble
• Histopathology Segmentation