TIGER

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

AGGC22

Endometrial Carcinoma Detection in Pipelle biopsies

Evaluation platform as reference benchmark for algorithms that can predict endometrial carcinoma on whole-slide images of Pipelle sampled endometrial slides stained in H&E, based on the test data set used in our project.

UNICORN

Grand challenge on benchmarking vision-language foundation models in the digital pathology and radiology domain

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.

HookNet-Breast

Segmentation algorithm for histopathology breast tissue.

Lung Cancer Segmentation

Lung cancer segmentation in H&E stained histopathological images.

Quality assessment of whole-slide images through artifact detection

Quality scoring with artifact detection in whole slide images; out-of-focus, tissue folds, ink, dust, pen mark, and air bubbles.