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

arXiv:2609.38419 · eess.IV, cs.AI, cs.CV · Submitted 2026-09-29 · Read on arXiv

eess.IV, cs.AI, cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: SPIE Eighteenth International Conference on Machine Vision (ICMV 2025), Paris, France

Journal ref: Proc. SPIE 14114, Eighteenth International Conference on Machine Vision (ICMV 2025), 141140I (25 Feb 2026)

DOI: 10.1117/12.3096537

Code: https://github.com/caglarmert/ICIP2025

License: http://creativecommons.org/licenses/by/4.0/

The gist: Colorectal cancer (CRC) is the second most deadly and third most common cancer, and the leading cause of death among gastrointestinal cancers.

Terminology

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

Sources

Related papers