Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning
Not on the map. Why?
Abstract (arXiv)
Self-supervised deep learning has accelerated 2D natural image analysis but remains difficult to translate into 3D MRI, where data are scarce and pre-trained 2D backbones cannot capture volumetric context. We present a sequence-invariant self-supervised framework leveraging quantitative MRI (qMRI). By simulating multiple MRI contrasts from a single 3D qMRI scan and enforcing consistent representations across these contrasts, we learn anatomy-centric rather than sequence-specific features. The result is a single 3D encoder that excels across tasks and protocols. Experiments on healthy brain segmentation (IXI), stroke lesion segmentation (ARC), and MRI denoising show significant gains over baseline SSL approaches, especially in low-data settings (up to +8.3% Dice, +4.2 dB PSNR). It also generalises to unseen sites, supporting scalable clinical use. Code and trained models are publicly available at https://github.com/liamchalcroft/contrast-squared
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 21 Jan 2025.
Builds on
26 of 44 references.
References · 26
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
- 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
- 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
- 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
- 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 422
14 more
- 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
- 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
- 2020Tent: Fully Test-time Adaptation by Entropy Minimizationcited by 69
- 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
- 2024Large-Scale 3D Medical Image Pre-training with Geometric Context Priorscited by 36
- 2023SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentationcited by 35
- 2022Decoder Denoising Pretraining for Semantic Segmentationcited by 20
- 2024A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysiscited by 14
- 2024Robust image representations with counterfactual contrastive learningcited by 14
- 2024PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRIcited by 8
- 2023Large-kernel Attention for Efficient and Robust Brain Lesion Segmentationcited by 5
- 2024Free Form Medical Visual Question Answering in Radiologycited by 4
- 2021Acquisition-invariant brain MRI segmentation with informative uncertaintiescited by 3
- 2024Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Datacited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.