Domain-randomized deep learning for neuroimage analysis
arXiv:2507.13458 · doi:10.1109/MSP.2025.3590806
Abstract
Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute in magnetic resonance imaging (MRI), where image appearance varies widely across pulse sequences and scanner hardware. A recent domain-randomization strategy addresses the generalization problem by training deep neural networks on synthetic images with randomized intensities and anatomical content. By generating diverse data from anatomical segmentation maps, the approach enables models to accurately process image types unseen during training, without retraining or fine-tuning. It has demonstrated effectiveness across modalities including MRI, computed tomography, positron emission tomography, and optical coherence tomography, as well as beyond neuroimaging in ultrasound, electron and fluorescence microscopy, and X-ray microtomography. This tutorial paper reviews the principles, implementation, and potential of the synthesis-driven training paradigm. It highlights key benefits, such as improved generalization and resistance to overfitting, while discussing trade-offs such as increased computational demands. Finally, the article explores practical considerations for adopting the technique, aiming to accelerate the development of generalizable tools that make deep learning more accessible to domain experts without extensive computational resources or machine learning knowledge.
12 pages, 6 figures, 2 tables, deep learning, domain generalization, domain randomization, neuroimaging, medical image analysis, accepted for publication in IEEE Signal Processing Magazine
References in corpus (10)
- Deep Visual Domain Adaptation: A Survey
- VoxelMorph: A Learning Framework for Deformable Medical Image Registration
- Domain Generalization: A Survey
- SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
- Diffusion Probabilistic Models beat GANs on Medical Images
- SynthMorph: learning contrast-invariant registration without acquired images
- Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
- Boosting Skull-Stripping Performance for Pediatric Brain Images
- Improving cross-domain brain tissue segmentation in fetal MRI with synthetic data
- Learning accurate rigid registration for longitudinal brain MRI from synthetic data