Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915415436820480 |
|---|---|
| author | Chalcroft, Liam Crinion, Jenny Price, Cathy J. Ashburner, John |
| author_facet | Chalcroft, Liam Crinion, Jenny Price, Cathy J. Ashburner, John |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12057 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning Chalcroft, Liam Crinion, Jenny Price, Cathy J. Ashburner, John Computer Vision and Pattern Recognition Medical Physics 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 |
| title | Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning |
| topic | Computer Vision and Pattern Recognition Medical Physics |
| url | https://arxiv.org/abs/2501.12057 |