Spaces:
Sleeping
Apply for community grant: Academic project (gpu)
This space is a demo following the paper "GANcMRI: Cardiac magnetic resonance video generation and physiologic guidance using latent space prompting" that will be presented at ML4H 2023 collocated with NeurIPS and published in the PMLR (Proceedings of Machine Learning).
The demo shows that GANcMRI can generate cMRI videos of high quality, it demonstrates our two methods ED-to-ES and Frame-to-Frame, and allows the user to apply semantic editing of sphericity index and left ventricular volume using the sliders."
About the approach:
We utilized a generative machine learning approach, the substantial UK Biobank cMRI data, and latent space calculus to generate cMRI images and videos. Nearing the level of being indistinguishable by clinicians, optimally generated cMRI videos can open new avenues in cardiac imaging research and clinical practice. We were able to generate individual synthetic cMRI frames of a quality indistinguishable from real ones. By interpreting videos as continuous signals within the image latent space, we model time trajectories on a frame-to-frame basis to produce cMRI videos of higher temporal resolution and superior quality compared to other video generation methods, although they remain distinguishable from the real ones. Finally, we demonstrate physiologic guidance can be applied to synthetic cMRIs to generate clinically relevant changes in the synthetic videos.