Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning
This addresses the problem of data scarcity and lack of volumetric context in 3D MRI for researchers and clinicians, offering a scalable solution with incremental improvements over existing self-supervised methods.
The paper tackles the challenge of applying self-supervised learning to 3D MRI data by introducing a sequence-invariant framework that simulates multiple MRI contrasts from a single scan to learn anatomy-centric features, resulting in a 3D encoder that achieves up to +8.3% Dice and +4.2 dB PSNR gains over baselines in tasks like segmentation and denoising.
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 \emph{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