Colorectal Cancer Tumor Grade Segmentation in Digital Histopathology Images: From Giga to Mini Challenge

TL;DR

This paper presents a challenge for automated segmentation of colorectal cancer tumor grades in histopathology images, introducing a new dataset and benchmarking various methods to improve standardization and accuracy.

Contribution

It introduces the METU CCTGS dataset, organizes a challenge with multiple teams, and provides an overview of top methods for tumor grade segmentation in CRC histopathology images.

Findings

Six teams outperformed the baseline Swin Transformer model.

Top methods achieved higher macro F-score and mIoU metrics.

The challenge promotes development of automated CRC grading solutions.

Abstract

Colorectal cancer (CRC) is the third most diagnosed cancer and the second leading cause of cancer-related death worldwide. Accurate histopathological grading of CRC is essential for prognosis and treatment planning but remains a subjective process prone to observer variability and limited by global shortages of trained pathologists. To promote automated and standardized solutions, we organized the ICIP Grand Challenge on Colorectal Cancer Tumor Grading and Segmentation using the publicly available METU CCTGS dataset. The dataset comprises 103 whole-slide images with expert pixel-level annotations for five tissue classes. Participants submitted segmentation masks via Codalab, evaluated using metrics such as macro F-score and mIoU. Among 39 participating teams, six outperformed the Swin Transformer baseline (62.92 F-score). This paper presents an overview of the challenge, dataset, and the top-performing methods