KPIs 2024挑战：从切片级到整块级推进肾小球分割
计算机视觉与模式识别
2025-02-12 v1 人工智能
摘要
慢性肾病（CKD）是全球主要的健康问题，影响全球人口的10%以上，导致显著死亡率。虽然肾脏活检是CKD诊断和治疗的金标准，但缺乏为肾病理学分割提供全面的基准制度，阻碍了该领域的进展。为此，我们组织了肾脏病理图像分割（KPIs）挑战，介绍了一个包含60多个周期苏酸氢染色（PAS）染色whole slide images（整块切片图像）的、超过10,000个标注肾小球的数据集。挑战包括两个任务：切片级分割和整块图像分割与检测，使用Dice相似系数（DSC）和F1分数进行评估。通过鼓励创新方法适应多样化的CKD模型和组织条件，KPIs挑战旨在推进肾脏病理分析，建立新的基准，並在疾病研究和诊断中实现精确的大规模量化。
引用
@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}
}