mlsanityData to 7 Oct 2026

An attempt at beating the 3D U-Net

arXiv 1908.02182 ↗First posted 6 Aug 2019eess.IV cs.CV cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

The U-Net is arguably the most successful segmentation architecture in the medical domain. Here we apply a 3D U-Net to the 2019 Kidney and Kidney Tumor Segmentation Challenge and attempt to improve upon it by augmenting it with residual and pre-activation residual blocks. Cross-validation results on the training cases suggest only very minor, barely measurable improvements. Due to marginally higher dice scores, the residual 3D U-Net is chosen for test set prediction. With a Composite Dice score of 91.23 on the test set, our method outperformed all 105 competing teams and won the KiTS2019 challenge by a small margin.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 5; 2024: 4; 2025: 1; 2026: 2.

21 papers.

Sort:

  1. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  2. 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentationcited by 235
  3. 2021A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstructioncited by 47
  4. 2023MultiTalent: A Multi-Dataset Approach to Medical Image Segmentationcited by 45
  5. 2022Learning Whole Heart Mesh Generation From Patient Images For Computational Simulationscited by 21
  6. 2021Using Out-of-the-Box Frameworks for Contrastive Unpaired Image Translation for Vestibular Schwannoma and Cochlea Segmentation: An approach for the crossMoDA Challengecited by 7
  7. 2024LNQ 2023 challenge: Benchmark of weakly-supervised techniques for mediastinal lymph node quantificationcited by 6
  8. 2022Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directionscited by 5
  9. 2021Self-Supervised Learning for Segmentationcited by 4
  10. 2023Look Ma, no code: fine tuning nnU-Net for the AutoPET II challenge by only adjusting its JSON planscited by 2
  11. 2023BeSt-LeS: Benchmarking Stroke Lesion Segmentation using Deep Supervisioncited by 1
  12. 2024SE3D: A Framework For Saliency Method Evaluation In 3D Imagingcited by 1
9 more
  1. 2024Automated Segmentation of Ischemic Stroke Lesions in Non-Contrast Computed Tomography Images for Enhanced Treatment and Prognosiscited by 1
  2. 2025Decomposition Sampling for Efficient Region Annotations in Active Learningcited by 1
  3. 2021Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutionscited by 0
  4. 2022Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CTcited by 0
  5. 2022Kidney and Kidney Tumour Segmentation in CT Imagescited by 0
  6. 2023TransCC: Transformer Network for Coronary Artery CCTA Segmentationcited by 0
  7. 2023Segmentation of Kidney Tumors on Non-Contrast CT Images using Protuberance Detection Networkcited by 0
  8. 2026From Convolution to Transformer: A Comparative Study of U-Net Variants for Brain Tumor and Retinal Vessel Segmentationcited by 0
  9. 2026Deep Learning Segmentation of Diffusion-Weighted MRI Acute Ischaemic Stroke: A Pragmatic Evaluation Across Three Datasetscited by 0