Chalcroft, Liam; Crinion, Jenny; Price, Cathy J; Ashburner, John; (2026) Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning. In: Fernandez, Virginia and Wiesner, David and Zuo, Lianrui and Casamitjana, Adrià and Remedios, Samuel W, (eds.) Simulation and Synthesis in Medical Imaging. (pp. pp. 63-74). Springer: Cham, Switzerland.

Text 2501.12057v3.pdf - Accepted Version Access restricted to UCL open access staff until 22 September 2026. Download (2MB)

Abstract

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.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item