mlsanityData to 7 Oct 2026

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

arXiv 2107.09559 ↗First posted 20 Jul 2021eess.IV cs.CVcited by 235

Not on the map. Why?

Cited by 33 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive to changes in resolution and contrast: even within the same MRI modality, performance can decrease across datasets. Here we introduce SynthSeg, the first segmentation CNN robust against changes in contrast and resolution. SynthSeg is trained with synthetic data sampled from a generative model conditioned on segmentations. Crucially, we adopt a domain randomisation strategy where we fully randomise the contrast and resolution of the synthetic training data. Consequently, SynthSeg can segment real scans from a wide range of target domains without retraining or fine-tuning, which enables straightforward analysis of huge amounts of heterogeneous clinical data. Because SynthSeg only requires segmentations to be trained (no images), it can learn from labels obtained by automated methods on diverse populations (e.g., ageing and diseased), thus achieving robustness to a wide range of morphological variability. We demonstrate SynthSeg on 5,000 scans of six modalities (including CT) and ten resolutions, where it exhibits unparalleled generalisation compared with supervised CNNs, state-of-the-art domain adaptation, and Bayesian segmentation. Finally, we demonstrate the generalisability of SynthSeg by applying it to cardiac MRI and CT scans.

Key facts. Cited by 235 papers in the map (data through 7 Oct 2026). Builds on 31 of its 77 references that are in the map. First posted on arXiv 20 Jul 2021.

Builds on

31 of 77 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  10. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  11. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  12. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
19 more
  1. 2016Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentationcited by 263
  2. 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
  3. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  4. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  5. 2019Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentationcited by 121
  6. 2016HeMIS: Hetero-Modal Image Segmentationcited by 102
  7. 2020Test-Time Adaptable Neural Networks for Robust Medical Image Segmentationcited by 102
  8. 2019Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challengecited by 100
  9. 2018Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Networkcited by 97
  10. 2018SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truthcited by 68
  11. 2017Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentationcited by 66
  12. 2018Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Imagescited by 55
  13. 2018A Lifelong Learning Approach to Brain MR Segmentation Across Scanners and Protocolscited by 49
  14. 2020Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrastcited by 45
  15. 2019Semi-Supervised and Task-Driven Data Augmentationcited by 40
  16. 2020A Learning Strategy for Contrast-agnostic MRI Segmentationcited by 35
  17. 2020Partial Volume Segmentation of Brain MRI Scans of any Resolution and Contrastcited by 16
  18. 2018A probabilistic atlas of the human thalamic nuclei combining ex vivo MRI and histologycited by 10
  19. 2018Pulse Sequence Resilient Fast Brain Segmentationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 24; 2024: 55; 2025: 85; 2026: 69.

235 papers.

Sort:

By area:

  1. 2024Towards Generalizable Tumor Synthesiscited by 65
  2. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  3. 2023The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiographycited by 48
  4. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  5. 2023MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Imagescited by 41
  6. 2024Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledgecited by 35
  7. 2025Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planningcited by 31
  8. 2024Learning General-Purpose Biomedical Volume Representations using Randomized Synthesiscited by 27
  9. 2022One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesiscited by 22
  10. 2023Anatomy-aware and acquisition-agnostic joint registration with SynthMorphcited by 19
  11. 2024vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentationcited by 18
  12. 2025Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusioncited by 17
38 more
  1. 2023Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRIcited by 15
  2. 2024LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Modelscited by 15
  3. 2023AnyStar: Domain randomized universal star-convex 3D instance segmentationcited by 14
  4. 2024FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesiscited by 14
  5. 2023CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomycited by 13
  6. 2024MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidancecited by 11
  7. 2023Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imagingcited by 10
  8. 2023SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRIcited by 10
  9. 2024MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registrationcited by 9
  10. 2025Synthesizing Individualized Aging Brains in Health and Disease with Generative Models and Parallel Transportcited by 9
  11. 2025MultiMorph: On-demand Atlas Constructioncited by 9
  12. 2025Building a General SimCLR Self-Supervised Foundation Model Across Neurological Diseases to Advance 3D Brain MRI Diagnosescited by 9
  13. 2024Boosting Skull-Stripping Performance for Pediatric Brain Imagescited by 8
  14. 2024PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRIcited by 8
  15. 2024Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlasescited by 8
  16. 2024Unified Cross-Modal Medical Image Synthesis with Hierarchical Mixture of Product-of-Expertscited by 8
  17. 2025Regression is all you need for medical image translationcited by 8
  18. 2023Comprehensive analysis of synthetic learning applied to neonatal brain MRI segmentationcited by 7
  19. 2025A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learningcited by 7
  20. 2026From Performance to Practice: Knowledge-Distilled Segmentator for On-Premises Clinical Workflowscited by 7
  21. 2023Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learningcited by 6
  22. 20247T MRI Synthesization from 3T Acquisitionscited by 6
  23. 2024VMambaMorph: a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Modulecited by 6
  24. 2024HyperSpace: Hypernetworks for spacing-adaptive image segmentationcited by 6
  25. 2024Recon-all-clinical: Cortical surface reconstruction and analysis of heterogeneous clinical brain MRIcited by 6
  26. 2024VoxelPrompt: A Vision Agent for End-to-End Medical Image Analysiscited by 6
  27. 2025Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomizationcited by 6
  28. 2025Domain-randomized deep learning for neuroimage analysiscited by 6
  29. 2025ECLARE: Efficient cross-planar learning for anisotropic resolution enhancementcited by 5
  30. 2025WASABI: A Metric for Evaluating Morphometric Plausibility of Synthetic Brain MRIscited by 5
  31. 2025CoCoLIT: ControlNet-Conditioned Latent Image Translation for MRI to Amyloid PET Synthesiscited by 5
  32. 2025A Modality-agnostic Multi-task Foundation Model for Human Brain Imagingcited by 5
  33. 2024IGUANe: a 3D generalizable CycleGAN for multicenter harmonization of brain MR imagescited by 4
  34. 2024Synthetic Data for Robust Stroke Segmentationcited by 4
  35. 2024Neurovascular Segmentation in sOCT with Deep Learning and Synthetic Training Datacited by 4
  36. 2024Unpaired Volumetric Harmonization of Brain MRI with Conditional Latent Diffusioncited by 4
  37. 2024Shape-intensity knowledge distillation for robust medical image segmentationcited by 4
  38. 2024Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimagingcited by 4

50 most cited of 235 All 235 (JSON)