Welcome to the Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation (COSAS 2024) challenge!

📌Overview¶

Workshop Time and Venue¶

• 📆Date: October 6, 2024

• ⏰Time: 3:30 PM to 5:30 PM (Local Time)

• 📍Location: Palmeraie Palace - Opale

The field of digital pathology has made significant strides in tumor diagnosis and segmentation, driven by various challenges. Despite these advancements, the efficacy of current algorithms encounters a significant challenge due to the inherent diversity present in digital pathology images and tissues. The variances arise from diverse organs, tissue preparation methods, and image acquisition processes, resulting in what is termed as domain-shift. The primary goal of COSAS is to develop strategies that enhance the resilience of computer aided semantic segmentation solutions against domain-shift, ensuring consistent performance across different organs and scanners. This challenge seeks to advance the development of artificial intelligence and machine learning algorithms for routine diagnostic use in laboratories. Notably, COSAS marks the first challenge in computational histopathology, providing a platform for evaluating domain adaptation methods on a comprehensive dataset featuring diverse organs and scanners from various manufacturers.

✍️Challenge Tasks¶

COSAS 2024 contains two tasks for participating teams to contribute their findings. Both tasks focus on segmenting normal gland and adenocarcinoma regions. For detailed information, please refer to the 'Tasks' page.

🎯Task 1: Cross-Organ Adenocarcinoma Segmentation¶

Task 1 centres around assessing the generalization capacity of machine learning algorithms in adenocarcinoma segmentation tasks across various organs. It assesses algorithm performance in segmenting multiple organs using image patches extracted from whole slide images of six distinct adenocarcinomas, all acquired from the same scanner.

🎯Task 2: Cross-Scanner Adenocarcinoma Segmentation¶

Task 2 focuses on evaluating the generalisation capabilities of machine learning algorithms in adenocarcinoma segmentation across diverse whole slide image scanners. The dataset comprises image patches extracted from whole slide image scans of invasive breast carcinoma tissues, acquired with six different scanners of different manufacturers. 

📆Important Dates¶

• 8th May 2024: Webpage Go-Live, registration open for participants
• 18th June 2024: Release of training data and evaluation code
• 17th August 2024: Deadline for registration of participants
• 18th August 2024: Preliminary test submission opens
• 5st Sep 2024: Deadline for docker container submission of the preliminary test set
• 6st Sep 2024: Final test submission opens
• 8rd Sep 2024: Deadline for docker container submission of final test
• 20th Sep 2024: Deadline for three-page arxiv abstract submission