CineMA

UCL / Mycardium (Fu et al.)

Cardiac MRI

Filter catalog by Modality:
Cardiac MRI

General Purpose / Multi-task

Filter catalog by Disease / Trait:
General / Foundation

Cardiac chamber segmentation

Filter catalog by Disease / Trait:
Structural Heart & Cardiomyopathy

LVEF estimation

Filter catalog by Disease / Trait:
Cardiac Function & Hemodynamics

Binary classification

Filter catalog by Task Type:
Classification

Segmentation

Filter catalog by Task Type:
Segmentation & Detection

Regression

Filter catalog by Task Type:
Regression

Detection / localization

Filter catalog by Task Type:
Segmentation & Detection

Vision Transformer

Filter catalog by Architecture:
Transformer

PyTorch

Filter catalog by Framework:
PyTorch

MIT

Filter catalog by License:
Permissive

file_copy

View model files code View code

Foundation model for cine cardiac MRI, self-supervised via masked autoencoding on nearly 75,000 UK Biobank scans. Uses a Vision Transformer with a convolutional stem, unified across long-axis and short-axis views. Fine-tuned checkpoints are released for ventricle and myocardium segmentation, ejection-fraction regression, cardiovascular disease classification, and landmark localization across several public benchmark datasets (ACDC, M&Ms, M&Ms2, EMIDEC, and others).

memory Specifications

gavel License

MIT

check_small Open source check_small Commercial use OK check_small Modifications allowed Attribution required No share-alike requirement

License for model weights only. Associated code may be licensed seperately, check code source for specific terms.

description Publication

CineMA: A Foundation Model for Cine Cardiac MRI open_in_new

2025 · original paper

database Training & evaluation data

UK Biobank Cardiac MRI open_in_new

train

public 74,916 subjects · United Kingdom

UK Biobank cardiac MRI imaging substudy; CineMA pretrained on 74,916 cine CMR studies, ukbb_cardiac (Bai et al. 2018) trained on ~4,875 subjects / 93,500 annotated images from an earlier release.

science Capabilities & performance

Cardiac disease present (merged)

Binary classification General Purpose / Multi-task

0.902 Sensitivity / recall ACDC + M&Ms + M&Ms2 (merged) · external

0.6006 Specificity ACDC + M&Ms + M&Ms2 (merged) · external