@article{touchstonebenchmarkareweontherightway,
  title = {Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?},
  author = {Pedro R. A. S. Bassi and Wenxuan Li and Yucheng Tang and Fabian Isensee and Zifu Wang and Jieneng Chen and Yu-Cheng Chou and Yannick Kirchhoff and Maximilian Rokuss and Ziyan Huang and Jin Ye and Junjun He and Tassilo Wald and Constantin Ulrich and Michael Baumgartner and Saikat Roy and Klaus H. Maier-Hein and Paul Jaeger and Yiwen Ye and Yutong Xie and Jianpeng Zhang and Ziyang Chen and Yong Xia and Zhaohu Xing and Lei Zhu and Yousef Sadegheih and Afshin Bozorgpour and Pratibha Kumari and Reza Azad and Dorit Merhof and Pengcheng Shi and Ting Ma and Yuxin Du and Fan Bai and Tiejun Huang and Bo Zhao and Haonan Wang and Xiaomeng Li and Hanxue Gu and Haoyu Dong and Jichen Yang and Maciej A. Mazurowski and Saumya Gupta and Linshan Wu and Jiaxin Zhuang and Hao Chen and Holger Roth and Daguang Xu and Matthew B. Blaschko and Sergio Decherchi and Andrea Cavalli and Alan L. Yuille and Zongwei Zhou},
  year = {2024},
  eprint = {2411.03670},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.03670v2},
}