|
|
--- |
|
|
language: en |
|
|
tags: |
|
|
- medical-imaging |
|
|
- mri |
|
|
- self-supervised |
|
|
- 3d |
|
|
- neuroimaging |
|
|
license: apache-2.0 |
|
|
library_name: pytorch |
|
|
datasets: |
|
|
- custom |
|
|
--- |
|
|
|
|
|
# SimCLR-MRI Pre-trained Encoder (SeqInv) |
|
|
|
|
|
This repository contains a pre-trained 3D CNN encoder for MRI analysis. The model was trained using contrastive learning (SimCLR) with explicit sequence invariance enforced through paired multi-contrast images. |
|
|
|
|
|
## Model Description |
|
|
|
|
|
The encoder is a 3D CNN with 5 convolutional blocks (64, 128, 256, 512, 768 channels), outputting 768-dimensional features. This SeqInv variant was trained on paired sequences generated through Bloch simulations, explicitly enforcing sequence invariance in the learned representations. |
|
|
|
|
|
### Training Procedure |
|
|
- **Pre-training Data**: 51 qMRI datasets (22 healthy, 29 stroke subjects) |
|
|
- **Training Strategy**: Paired sequence views + standard augmentations |
|
|
- **Input**: 3D MRI volumes (96×96×96) |
|
|
- **Output**: 768-dimensional sequence-invariant feature vectors |
|
|
|
|
|
## Intended Uses |
|
|
|
|
|
This encoder is particularly suited for: |
|
|
- Sequence-agnostic analysis tasks |
|
|
- Multi-sequence registration |
|
|
- Cross-sequence synthesis |
|
|
- Tasks requiring sequence-invariant features |
|
|
|
|
|
[arXiv](https://arxiv.org/abs/2501.12057) |
|
|
|
