mlsanityData to 14 Oct 2026

The Missing Piece: A Case for Pre-Training in 3D Medical Object Detection

arXiv 2509.15947 ↗First posted 19 Sep 2025eess.IV cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Large-scale pre-training holds the promise to advance 3D medical object detection, a crucial component of accurate computer-aided diagnosis. Yet, it remains underexplored compared to segmentation, where pre-training has already demonstrated significant benefits. Existing pre-training approaches for 3D object detection rely on 2D medical data or natural image pre-training, failing to fully leverage 3D volumetric information. In this work, we present the first systematic study of how existing pre-training methods can be integrated into state-of-the-art detection architectures, covering both CNNs and Transformers. Our results show that pre-training consistently improves detection performance across various tasks and datasets. Notably, reconstruction-based self-supervised pre-training outperforms supervised pre-training, while contrastive pre-training provides no clear benefit for 3D medical object detection. Our code is publicly available at: https://github.com/MIC-DKFZ/nnDetection-finetuning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 108 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

51 of 108 references.

References · 51

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  4. 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 613
  5. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  6. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 373
  7. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  8. 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentationcited by 240
  9. 2020AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?cited by 224
  10. 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 201
  11. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 199
  12. 2022Metrics reloaded: Recommendations for image analysis validationcited by 195
38 more
  1. 2015DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentationcited by 159
  2. 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
  3. 2022ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation datasetcited by 106
  4. 2023The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CTcited by 103
  5. 2023Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modelingcited by 94
  6. 2018Why rankings of biomedical image analysis competitions should be interpreted with carecited by 91
  7. 2021MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluationcited by 88
  8. 2021Joint Learning of Localized Representations from Medical Images and Reportscited by 81
  9. 2019Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithmcited by 77
  10. 2024VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysiscited by 75
  11. 2022Masked Image Modeling Advances 3D Medical Image Analysiscited by 72
  12. 2024The 2024 Brain Tumor Segmentation (BraTS) Challenge: Glioma Segmentation on Post-treatment MRIcited by 69
  13. 2024AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarkingcited by 65
  14. 2020An automatic multi-tissue human fetal brain segmentation benchmark using the Fetal Tissue Annotation Datasetcited by 59
  15. 2024TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRIcited by 59
  16. 2023PRIOR: Prototype Representation Joint Learning from Medical Images and Reportscited by 55
  17. 2023The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningiomacited by 53
  18. 2023The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiographycited by 50
  19. 2018Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detectioncited by 47
  20. 2023MultiTalent: A Multi-Dataset Approach to Medical Image Segmentationcited by 45
  21. 2023M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimizationcited by 43
  22. 2020Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CTcited by 42
  23. 2023The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRIcited by 36
  24. 2024Revisiting MAE pre-training for 3D medical image segmentationcited by 35
  25. 2019Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multi-Sequence MRIcited by 30
  26. 2020Volumetric Attention for 3D Medical Image Segmentation and Detectioncited by 29
  27. 2021Tracked 3D Ultrasound and Deep Neural Network-based Thyroid Segmentation reduce Interobserver Variability in Thyroid Volumetrycited by 29
  28. 2023SegRap2023: A Benchmark of Organs-at-Risk and Gross Tumor Volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinomacited by 29
  29. 2021A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Datacited by 28
  30. 2022Fetal Brain Tissue Annotation and Segmentation Challenge Resultscited by 20
  31. 2023Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Imagescited by 16
  32. 2024Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challengecited by 14
  33. 2024The Brain Tumor Segmentation in Pediatrics (BraTS-PEDs) Challenge: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)cited by 14
  34. 2021AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quocited by 12
  35. 2020Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slicescited by 10
  36. 2023Zero-shot Nuclei Detection via Visual-Language Pre-trained Modelscited by 10
  37. 2023AeroPath: An airway segmentation benchmark dataset with challenging pathologycited by 10
  38. 2025Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challengecited by 8

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025In search of truth: Evaluating concordance of AI-based anatomy segmentation modelscited by 0
  2. 2026CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encodingcited by 0