A revised pipeline for synthesizing pathological cardiac cine MR sequences from real healthy cases improved realism and accuracy compared to state-of-the-art algorithms at a small computational cost.
Does the proposed computational pipeline improve the realism and accuracy of synthetic pathological cardiac cine MR sequences compared to state-of-the-art algorithms?
The proposed computational pipeline efficiently generates realistic synthetic pathological cardiac MR images to augment databases for machine learning and statistical analysis.
Collecting large databases of annotated medical images is crucial for the validation and testing of feature extraction, statistical analysis, and machine learning algorithms. Recent advances in cardiac electromechanical modeling and image synthesis provided a framework to generate synthetic images based on realistic mesh simulations. Nonetheless, their potential to augment an existing database with large amounts of synthetic cases requires further investigation. We build upon these works and propose a revised scheme for synthesizing pathological cardiac sequences from real healthy sequences. Our new pipeline notably involves a much easier registration problem to reduce potential artifacts, and takes advantage of mesh correspondences to generate new data from a given case without additional registration. The output sequences are thoroughly examined in terms of quality and usability on a given application: the assessment of myocardial viability, via the generation of 465 synthetic cine MR sequences (15 healthy and 450 with pathological tissue viability random location, extent, and grade, up to myocardial infarct). We demonstrate that: 1) our methodology improves the state-of-the-art algorithms in terms of realism and accuracy of the simulated images and 2) our methodology is well-suited for the generation of large databases at small computational cost.
Duchateau et al. (Fri,) conducted a other in Myocardial viability (n=465). Model-based generation of synthetic pathological cine MR sequences vs. State-of-the-art algorithms was evaluated on Realism and accuracy of simulated images and computational cost. A revised pipeline for synthesizing pathological cardiac cine MR sequences from real healthy cases improved realism and accuracy compared to state-of-the-art algorithms at a small computational cost.