# A versatile foundation model for cine cardiac magnetic resonance image analysis tasks

arXiv: https://arxiv.org/abs/2506.00679 · HTML: https://mlsanity.com/paper/2506.00679/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 31 May 2025.

## Builds on (most cited first, 15 of 15)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [Resnet in Resnet: Generalizing Residual Architectures](https://mlsanity.com/paper/1603.08029/) (2016)
- [Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks](https://mlsanity.com/paper/1711.06753/) (2017)
- [ConvMAE: Masked Convolution Meets Masked Autoencoders](https://mlsanity.com/paper/2205.03892/) (2022)
- [Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence](https://mlsanity.com/paper/2410.11199/) (2024)
- [MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images](https://mlsanity.com/paper/2201.03186/) (2022)
- [Towards a vision foundation model for comprehensive assessment of Cardiac MRI](https://mlsanity.com/paper/2410.01665/) (2024)
- [Towards Cardiac MRI Foundation Models: Comprehensive Visual-Tabular Representations for Whole-Heart Assessment and Beyond](https://mlsanity.com/paper/2504.13037/) (2025)
- [A Generalizable Deep Learning System for Cardiac MRI](https://mlsanity.com/paper/2312.00357/) (2023)

## Built on by (most cited first, 12 of 12)

- [Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database](https://mlsanity.com/paper/2512.21652/) (2025)
- [Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based Applications](https://mlsanity.com/paper/2507.12945/) (2025)
- [PRISM: A Framework Harnessing Unsupervised Visual Representations and Textual Prompts for Explainable MACE Survival Prediction from Cardiac Cine MRI](https://mlsanity.com/paper/2508.19325/) (2025)
- [Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI](https://mlsanity.com/paper/2603.10967/) (2026)
- [CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis](https://mlsanity.com/paper/2603.25194/) (2026)
- [Motion-Guided Causal Disentanglement for Robust Multi-View Cine Cardiac MRI Diagnosis](https://mlsanity.com/paper/2606.04414/) (2026)
- [Development of an automated, reliable, and clinically meaningful artificial intelligence (AI) tool for diagnosing cardiac disease from conventional cardiovascular magnetic resonance (CMR) images](https://mlsanity.com/paper/2607.20087/) (2026)
- [MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI](https://mlsanity.com/paper/2608.30975/) (2026)
- [CMRVision: A Foundation Model for Cardiac MR Image Analysis](https://mlsanity.com/paper/2609.01308/) (2026)
- [Leveraging Cardiac Imaging to Improve ECG-Based Detection of Chagas Disease in Resource-Constrained Settings](https://mlsanity.com/paper/2609.08582/) (2026)
- [SV-Cine: Diagnosis-Conditioned Segmentation of Single Ventricle Physiology via Generative Data Augmentation](https://mlsanity.com/paper/2609.12997/) (2026)
- [CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessment](https://mlsanity.com/paper/2610.01166/) (2026)

## Abstract (arXiv)

Here we present a versatile foundation model that can perform a range of clinically-relevant image analysis tasks, including segmentation, landmark localisation, diagnosis, and prognostication. A multi-view convolution-transformer masked autoencoder, named as CineMA, was trained on 15 million cine images from 74,916 subjects. The model was validated on multiple image analysis tasks and compared to existing models on >4,500 images from eight independent datasets with diverse population characteristics, representing the largest benchmark study for cine CMR so far. CineMA consistently outperformed conventional convolutional neural networks (CNNs) in delineating ventricular boundaries and estimating ejection fraction, a key measure of cardiac function. The improved performance was preserved, even when the model only used half of fine-tuning data. CineMA also surpassed CNNs in disease detection and matched their performance in long-axis function measurement. Interestingly, we found that CineMA can also detect cardiac changes in systemic diseases, such as diabetes, hypertension and cancer, and can also predict mortality. Finally, we assessed model fairness and demonstrated consistent model performance across demographic subgroups. These findings highlight CineMA's accuracy, learning efficiency, adaptability, and fairness, underscoring its potential as a foundation model for automated cardiac image analysis to support clinical workflow and cardiovascular research. All training and inference code and models are made publicly available at https://github.com/mathpluscode/CineMA.