Chronic kidney disease (CKD) is a major global health issue, affecting over 10% of the population and causing significant mortality. While kidney biopsy remains the gold standard for CKD diagnosis and treatment, the lack of comprehensive benchmarks for kidney pathology segmentation hinders progress in the field. To address this, we organized the Kidney Pathology Image Segmentation (KPIs) Challenge, introducing a dataset that incorporates preclinical rodent models of CKD with over 10,000 annotated glomeruli from 60+ Periodic Acid Schiff (PAS)-stained whole slide images. The challenge includes two tasks, patch-level segmentation and whole slide image segmentation and detection, evaluated using the Dice Similarity Coefficient (DSC) and F1-score. By encouraging innovative segmentation methods that adapt to diverse CKD models and tissue conditions, the KPIs Challenge aims to advance kidney pathology analysis, establish new benchmarks, and enable precise, large-scale quantification for disease research and diagnosis.
@article{arxiv.2502.07288,
title = {KPIs 2024 Challenge: Advancing Glomerular Segmentation from Patch- to Slide-Level},
author = {Ruining Deng and Tianyuan Yao and Yucheng Tang and Junlin Guo and Siqi Lu and Juming Xiong and Lining Yu and Quan Huu Cap and Pengzhou Cai and Libin Lan and Ze Zhao and Adrian Galdran and Amit Kumar and Gunjan Deotale and Dev Kumar Das and Inyoung Paik and Joonho Lee and Geongyu Lee and Yujia Chen and Wangkai Li and Zhaoyang Li and Xuege Hou and Zeyuan Wu and Shengjin Wang and Maximilian Fischer and Lars Kramer and Anghong Du and Le Zhang and Maria Sanchez Sanchez and Helena Sanchez Ulloa and David Ribalta Heredia and Carlos Perez de Arenaza Garcia and Shuoyu Xu and Bingdou He and Xinping Cheng and Tao Wang and Noemie Moreau and Katarzyna Bozek and Shubham Innani and Ujjwal Baid and Kaura Solomon Kefas and Bennett A. Landman and Yu Wang and Shilin Zhao and Mengmeng Yin and Haichun Yang and Yuankai Huo},
journal= {arXiv preprint arXiv:2502.07288},
year = {2025}
}