ICIAR 2018

Can you develop a method for automatic detection of cancerous regions in breast cancer histology images?

PAIP 2019

PAIP2019: Liver Cancer Segmentation Task 1: Liver Cancer Segmentation Task 2: Viable Tumor Burden Estimation

WSSS4LUAD

The WSSS4LUAD dataset contains over 10,000 patches of lung adenocarcinoma from whole slide images from Guangdong Provincial People's Hospital and TCGA with image-level annotations. The goal of this challenge is to perform semantic segmentation for differentiating three important types of tissues in the WSIs of lung adenocarcinoma, including cancerous epithelial region, cancerous stroma region and normal region. Paticipants have to use image-level annotations to give pixel-level prediction.

TIGER

Grand challenge on automate assessment of tumor infiltrating lymphocytes in digital pathology slides of triple negative and Her2-positive breast cancers

CoNIC 2022

Colon Nuclei Identification and Counting Challenge 2022

AGGC22

ACROBAT 2023

The ACROBAT challenge aims to advance the development of WSI registration algorithms that can align WSIs of IHC-stained breast cancer tissue sections to corresponding tissue regions that were stained with H&E. All WSIs originate from routine diagnostic workflows.

Multi-Modality Abdominal Multi-Organ Segmentation Challenge 2022

Cell Segmentation in Multi-modality Microscopy Images

Weakly Supervised Cell Segmentation in Multi-modality High-resolution Microscopy Images

Diagnostic Report Analysis: General Optimization of NLP

PUMA: Panoptic segmentation of nUclei and tissue in MelanomA

The PUMA Challenge aims to enhance nuclei and tissue segmentation in melanoma histopathology, addressing the need for better prognostic biomarkers to predict treatment responses. Melanoma, a highly aggressive skin cancer, often requires immune checkpoint inhibition therapy, but only half of patients respond. Prognostic biomarkers like tumor infiltrating lymphocytes (TILs) correlate with better therapy responses and lower recurrence rate, but manual TIL scoring is subjective and inconsistent. Current deep learning methods underperform. The PUMA dataset includes annotated primary and metastatic melanoma regions to improve segmentation techniques. The challenge includes two tracks with tasks focused on tissue and nuclei segmentation, encouraging advanced methods to improve predictive accuracy.

REport Generation in pathology using Pan-Asia Giga-pixel WSIs

This project focuses on advancing automated pathology report generation using vision-language foundation models. It addresses the limitations of traditional NLP metrics (e.g., BLEU, METEOR, ROUGE) by emphasizing clinically relevant evaluation. The initiative includes standardized datasets, expert comparisons, and medical-domain-specific metrics to assess model performance. It also explores the integration of generated reports into diagnostic workflows with clinical feedback. To support fairness and generalizability, the challenge dataset comprises ~20,500 cases from six medical centers in Korea, Japan, India, Turkey, and Germany, promoting multicultural and multiethnic medical AI development.

Mitosis Domain Generalization Challenge 2025