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

被引:6
作者
Isensee, Fabian [1 ,3 ]
Wald, Tassilo [1 ,3 ,7 ]
Ulrich, Constantin [1 ,5 ,6 ]
Baumgartner, Michael [1 ,3 ,7 ]
Roy, Saikat [1 ]
Maier-Hein, Klaus [1 ,3 ,4 ,5 ,6 ,7 ]
Jaeger, Paul F. [2 ,3 ]
机构
[1] German Canc Res Ctr, Div Med Image Comp, Heidelberg, Germany
[2] DKFZ, Interact Machine Learning Grp IML, Heidelberg, Germany
[3] DKFZ, Helmholtz Imaging, Heidelberg, Germany
[4] Heidelberg Univ Hosp, Dept Radiat Oncol, Pattern Anal & Learning Grp, Heidelberg, Germany
[5] Natl Ctr Tumor Dis NCT Heidelberg, Heidelberg, Germany
[6] Heidelberg Univ, Med Fac Heidelberg, Heidelberg, Germany
[7] Heidelberg Univ, Fac Math & Comp Sci, Heidelberg, Germany
来源
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2024, PT IX | 2024年 / 15009卷
关键词
Medical Image Segmentation; Validation; Benchmark; TRANSFORMER;
D O I
10.1007/978-3-031-72114-4_47
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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 neglected computational resources. By meticulously avoiding these pitfalls, we conduct a thorough and comprehensive benchmarking of current segmentation methods including CNN-based, Transformer-based, and Mamba-based approaches. In contrast to current beliefs, we find that the recipe for state-of-the-art performance is 1) employing CNN-based U-Net models, including ResNet and ConvNeXt variants, 2) using the nnU-Net framework, and 3) scaling models to modern hardware resources. These results indicate an ongoing innovation bias towards novel architectures in the field and underscore the need for more stringent validation standards in the quest for scientific progress.
引用
收藏
页码:488 / 498
页数:11
相关论文
共 50 条
  • [11] MCRformer: Morphological constraint reticular transformer for 3D medical image segmentation
    Li, Jun
    Chen, Nan
    Zhou, Han
    Lai, Taotao
    Dong, Heng
    Feng, Chunhui
    Chen, Riqing
    Yang, Changcai
    Cai, Fanggang
    Wei, Lifang
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 232
  • [12] SegMAE-Net: A Hybrid Method Using Masked Autoencoders for Consistent 3D Medical Image Segmentation
    Liaw, Zheng Kai
    Das, Ankit
    Hussain, Shaista
    Yang, Feng
    Liu, Yong
    Goh, Rick Siow Mong
    2024 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI 2024, 2024, : 1272 - 1277
  • [13] MSA-Net: Multi-scale feature fusion network with enhanced attention module for 3D medical image segmentation
    Wang, Shuo
    Wang, Yuanhong
    Peng, Yanjun
    Chen, Xue
    COMPUTERS & ELECTRICAL ENGINEERING, 2024, 120
  • [14] Mixture 2D Convolutions for 3D Medical Image Segmentation
    Wang, Jianyong
    Zhang, Lei
    Yi, Zhang
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2023, 33 (01)
  • [15] UNETR plus plus : Delving Into Efficient and Accurate 3D Medical Image Segmentation
    Shaker, Abdelrahman
    Maaz, Muhammad
    Rasheed, Hanoona
    Khan, Salman
    Yang, Ming-Hsuan
    Khan, Fahad Shahbaz
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2024, 43 (09) : 3377 - 3390
  • [16] MISSU: 3D Medical Image Segmentation via Self-Distilling TransUNet
    Wang, Nan
    Lin, Shaohui
    Li, Xiaoxiao
    Li, Ke
    Shen, Yunhang
    Gao, Yue
    Ma, Lizhuang
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (09) : 2740 - 2750
  • [17] Large-Kernel Attention for 3D Medical Image Segmentation
    Li, Hao
    Nan, Yang
    Del Ser, Javier
    Yang, Guang
    COGNITIVE COMPUTATION, 2024, 16 (04) : 2063 - 2077
  • [18] FATUnetr:fully attention Transformer for 3D medical image segmentation
    Li, QingFeng
    Tong, Jigang
    Yang, Sen
    Du, Shengzhi
    2024 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, ICMA 2024, 2024, : 1415 - 1419
  • [19] BSANet: High-Performance 3D Medical Image Segmentation
    Huang, Qi
    Su, Jun
    Przystupa, Krzysztof
    Kochan, Orest
    IEEE ACCESS, 2023, 11 : 79213 - 79223
  • [20] nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer
    Zhou, Hong-Yu
    Guo, Jiansen
    Zhang, Yinghao
    Han, Xiaoguang
    Yu, Lequan
    Wang, Liansheng
    Yu, Yizhou
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 4036 - 4045