Model-based generation of large databases of cardiac images: synthesis of pathological cine MR sequences from real healthy cases

Nicolas Duchateau 1, 2 Maxime Sermesant 2, 3 Hervé Delingette 2, 3 Nicholas Ayache 2, 3
1 MOTIVATE - Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales
CREATIS - Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé : 139739
2 ASCLEPIOS - Analysis and Simulation of Biomedical Images
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : 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 our methodology (i) improves state-of-the-art algorithms in terms of realism and accuracy of the simulated images, and (ii) is well-suited for the generation of large databases at small computational cost.
Document type :
Journal articles
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal.inria.fr/hal-01533788
Contributor : Nicolas Duchateau <>
Submitted on : Tuesday, June 6, 2017 - 6:38:00 PM
Last modification on : Tuesday, March 19, 2019 - 4:58:39 PM
Long-term archiving on : Thursday, September 7, 2017 - 2:23:09 PM

File

jDuchateau_TMI_2017_FINAL.pdf
Files produced by the author(s)

Identifiers

Citation

Nicolas Duchateau, Maxime Sermesant, Hervé Delingette, Nicholas Ayache. Model-based generation of large databases of cardiac images: synthesis of pathological cine MR sequences from real healthy cases. IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2018, 37, pp.755-766. ⟨10.1109/TMI.2017.2714343⟩. ⟨hal-01533788⟩

Share

Metrics

Record views

493

Files downloads

449