# Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning

arXiv: https://arxiv.org/abs/2501.12057 · HTML: https://mlsanity.com/paper/2501.12057/

## Key facts

- Cited by 1 papers 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 (most cited first, 26 of 26)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Tent: Fully Test-time Adaptation by Entropy Minimization](https://mlsanity.com/paper/2006.10726/) (2020)
- [CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2201.02831/) (2022)
- [Large-Scale 3D Medical Image Pre-training with Geometric Context Priors](https://mlsanity.com/paper/2410.09890/) (2024)
- [SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2307.12591/) (2023)
- [Decoder Denoising Pretraining for Semantic Segmentation](https://mlsanity.com/paper/2205.11423/) (2022)
- [A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis](https://mlsanity.com/paper/2405.14839/) (2024)
- [Robust image representations with counterfactual contrastive learning](https://mlsanity.com/paper/2409.10365/) (2024)
- [PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRI](https://mlsanity.com/paper/2403.06227/) (2024)
- [Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation](https://mlsanity.com/paper/2308.07251/) (2023)
- [Free Form Medical Visual Question Answering in Radiology](https://mlsanity.com/paper/2401.13081/) (2024)
- [Acquisition-invariant brain MRI segmentation with informative uncertainties](https://mlsanity.com/paper/2111.04094/) (2021)
- [Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data](https://mlsanity.com/paper/2412.03318/) (2024)

## Built on by (most cited first, 1 of 1)

- [Large-scale modality-invariant foundation models for brain MRI analysis: Application to lesion segmentation](https://mlsanity.com/paper/2511.11311/) (2025)

## 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