nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation

arXiv:2404.09556v1 Announce Type: new
Abstract: The release of nnU-Net marked a paradigm shift in 3D medical image segmentation, demonstrating that a properly configured U-Net architecture could still achieve state-of-the-art results. Despite this, the pursuit of novel architectures, and the respective claims of superior performance over the U-Net baseline, continued. In this study, we demonstrate that many of these recent claims fail to hold up when scrutinized for common validation shortcomings, such as the use of inadequate baselines, insufficient datasets, and …

abstract architecture architectures art arxiv call cs.cv image medical novel paradigm performance release results segmentation shift state type validation