CineMA: A Foundation Model for Cine Cardiac MRI 🎥🫀
🚀 The following demonstrations showcase the capabilities of CineMA in multiple tasks. Click the button to launch the inference.
⏱️ The examples may take 10-60 seconds, if not cached, to download data and model, perform inference, and render plots.
💾 This research has been conducted using the UK Biobank Resource under Application Number 71702.
❤️ The authors acknowledge the use of resources provided by the Isambard-AI National AI Research Resource (AIRR).
🔗 For more details, check out our manuscript and GitHub repository.
This page illustrates the spatial orientation of short-axis (SAX) and long-axis (LAX) views in 3D.
Views
Data Settings
This page demonstrates the masking and reconstruction process. The model was trained with a mask ratio of 0.75. Click the button below to launch the inference. ⬇️
Reconstruction
Data Settings
This page demonstrates the segmentation of cardiac structures in the short-axis (SAX) view. Click the button below to launch the inference. ⬇️
Data Settings
Model Settings
Visualisation
The left figure shows the segmentation at every n time step across all SAX slices. The right figure shows the volumes across time frames and estimates the ejection fraction (EF) for the left ventricle (LV) and right ventricle (RV).
This page demonstrates the segmentation of cardiac structures in the long-axis (LAX) four-chamber (4C) view. Click the button below to launch the inference. ⬇️
Description
Data
There are four example images from the UK Biobank. Models were not trained supervisedly on these images.
Model
The available models are finetuned on M&Ms2. There are three models finetuned with seeds: 0, 1, 2.
Data Settings
Model Settings
Visualisation
The left figure shows the segmentation across time frames. The right figure shows the volumes across time frames and estimates the ejection fraction (EF).
This page demonstrates landmark localisation in the long-axis (LAX) two-chamber (2C) and four-chamber (4C) views. Click the button below to launch the inference. ⬇️
Description
Data
There are four example images from the UK Biobank. Models were not trained supervisedly on these images.
Model
The available models are finetuned on data from Xue et al. There are two types of landmark localisation models:
- Heatmap: predicts dense probability maps of landmarks (more accurate)
- Coordinate: predicts landmark coordinates directly
For each type, there are three models finetuned with seeds: 0, 1, 2.
Data Settings
Model Settings
Visualisation
The left figure shows the landmark positions across time frames. The right figure shows the length of the left ventricle across time frames and estimates mitral annular plane systolic excursion (MAPSE) and global longitudinal shortening (GLS).