mlsanityData to 7 Oct 2026

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

arXiv 2404.09556 ↗First posted 15 Apr 2024cs.CVcited by 235

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 235 papers in the map (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 15 Apr 2024.

Builds on

29 of 38 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  5. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  6. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  7. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 823
  8. 2021The Medical Segmentation Decathloncited by 620
  9. 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 597
  10. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 507
  11. 2019The Liver Tumor Segmentation Benchmark (LiTS)cited by 504
  12. 2022MONAI: An open-source framework for deep learning in healthcarecited by 438
17 more
  1. 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 418
  2. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 412
  3. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 324
  4. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  5. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  6. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  7. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  8. 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
  9. 2023MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentationcited by 161
  10. 2021UTNet: A Hybrid Transformer Architecture for Medical Image Segmentationcited by 116
  11. 2023The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CTcited by 101
  12. 2023STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-trainingcited by 96
  13. 2021LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentationcited by 85
  14. 2021DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentationcited by 47
  15. 2022D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentationcited by 35
  16. 2019An attempt at beating the 3D U-Netcited by 21
  17. 2023Transformer Utilization in Medical Image Segmentation Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 41; 2025: 109; 2026: 85.

235 papers.

Sort:

By area:

  1. 2025nnInteractive: Redefining 3D Promptable Segmentationcited by 39
  2. 2024Large-Scale 3D Medical Image Pre-training with Geometric Context Priorscited by 34
  3. 2024Revisiting MAE pre-training for 3D medical image segmentationcited by 33
  4. 2024Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?cited by 31
  5. 2024Learning General-Purpose Biomedical Volume Representations using Randomized Synthesiscited by 27
  6. 2024The ULS23 Challenge: a Baseline Model and Benchmark Dataset for 3D Universal Lesion Segmentation in Computed Tomographycited by 26
  7. 2025MedDINOv3: How to adapt vision foundation models for medical image segmentation?cited by 25
  8. 2024An OpenMind for 3D medical vision self-supervised learningcited by 23
  9. 2025Primus: Enforcing Attention Usage for 3D Medical Image Segmentationcited by 22
  10. 2025Comprehensive language-image pre-training for 3D medical image understandingcited by 20
  11. 2024AMAES: Augmented Masked Autoencoder Pretraining on Public Brain MRI Data for 3D-Native Segmentationcited by 16
  12. 2024From FDG to PSMA: A Hitchhiker's Guide to Multitracer, Multicenter Lesion Segmentation in PET/CT Imagingcited by 16
38 more
  1. 2025PanTS: The Pancreatic Tumor Segmentation Datasetcited by 15
  2. 2024EchoFM: Foundation Model for Generalizable Echocardiogram Analysiscited by 14
  3. 2025Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Datacited by 13
  4. 2025LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body Imagingcited by 11
  5. 2025Learning Segmentation from Radiology Reportscited by 11
  6. 2026ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentationcited by 10
  7. 2024LoG-VMamba: Local-Global Vision Mamba for Medical Image Segmentationcited by 8
  8. 2025Regression is all you need for medical image translationcited by 8
  9. 2025BraTS orchestrator : Democratizing and Disseminating state-of-the-art brain tumor image analysiscited by 8
  10. 2024Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CTcited by 7
  11. 2025A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learningcited by 7
  12. 2026From Performance to Practice: Knowledge-Distilled Segmentator for On-Premises Clinical Workflowscited by 7
  13. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  14. 2025MedicoSAM: Robust Improvement of SAM for Medical Imagingcited by 6
  15. 2025MSWAL: 3D Multi-class Segmentation of Whole Abdominal Lesions Datasetcited by 6
  16. 2025Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?cited by 6
  17. 2025Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformerscited by 6
  18. 2024Yucca: A Deep Learning Framework For Medical Image Analysiscited by 5
  19. 2024MIST: A Simple and Scalable End-To-End 3D Medical Imaging Segmentation Frameworkcited by 5
  20. 2024An Ensemble Approach for Brain Tumor Segmentation and Synthesiscited by 5
  21. 2025Expectation-Maximization as the Engine of Scalable Medical Intelligencecited by 5
  22. 2025Automated Muscle and Fat Segmentation in Computed Tomography for Comprehensive Body Composition Analysiscited by 5
  23. 2025You Point, I Learn: Online Adaptation of Interactive Segmentation Models for Handling Distribution Shifts in Medical Imagingcited by 5
  24. 2025Progressive Test Time Energy Adaptation for Medical Image Segmentationcited by 5
  25. 2025MedNeXt-v2: Scaling 3D ConvNeXts for Large-Scale Supervised Representation Learning in Medical Image Segmentationcited by 5
  26. 2024Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretationcited by 4
  27. 2024Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentationcited by 4
  28. 2024Scaling nnU-Net for CBCT Segmentationcited by 4
  29. 2025UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentationcited by 4
  30. 2025Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AIcited by 4
  31. 2026U-VLM: Hierarchical Vision Language Modeling for Report Generationcited by 4
  32. 2025Automating RT Planning at Scale: High Quality Data For AI Trainingcited by 3
  33. 2025Generative augmentations for improved cardiac ultrasound segmentation using diffusion modelscited by 3
  34. 2025Federated nnU-Net for Privacy-Preserving Medical Image Segmentationcited by 3
  35. 2025Zero-shot Domain Generalization of Foundational Models for 3D Medical Image Segmentation: An Experimental Studycited by 3
  36. 2025nnLandmark: A Self-Configuring Method for 3D Medical Landmark Detectioncited by 3
  37. 2025Robust Renal Mass Segmentation on CT: A Validation Study of an AI-Based Frameworkcited by 3
  38. 2025Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Renderingcited by 3

50 most cited of 235 All 235 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026DAMamba-UNet3D: A Parameter-Efficient Mamba State Space U-Net with Dynamic Adaptive Scan for 3D Medical Image Segmentation
  2. 2024MambaClinix: Hierarchical Gated Convolution and Mamba-Based U-Net for Enhanced 3D Medical Image Segmentation
  3. 2024nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model
  4. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation
  5. 2025A Comprehensive Analysis of Mamba for 3D Volumetric Medical Image Segmentation
  6. 2025Med-URWKVdag: Toward Enhanced Pretrained Pure VRWKV Models for Medical Image Segmentation
  7. 2026Benchmarking Foundation and Large Language Models for Few-Shot Medical Image Segmentation
  8. 2025Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches