Bi-temporal 3D active appearance models with applications to unsupervised ejection fraction estimation

Mikkel Bille Stegmann, Dorthe Pedersen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    165 Downloads (Pure)


    Rapid and unsupervised quantitative analysis is of utmost importance to ensure clinical acceptance of many examinations using cardiac magnetic resonance imaging (MRI). We present a framework that aims at fulfilling these goals for the application of left ventricular ejection fraction estimation in four-dimensional MRI. The theoretical foundation of our work is the generative two-dimensional Active Appearance Models by Cootes et al., here extended to bi-temporal, three-dimensional models. Further issues treated include correction of respiratory induced slice displacements, systole detection, and a texture model pruning strategy. Cross-validation carried out on clinical-quality scans of twelve volunteers indicates that ejection fraction and cardiac blood pool volumes can be estimated automatically and rapidly with accuracy on par with typical inter-observer variability.
    Original languageEnglish
    Title of host publicationInternational Symposium on Medical Imaging 2005, San Diego, CA, Proc. of SPIE
    Publication date2005
    Publication statusPublished - 2005
    Event2005 International Symposium on Medical Imaging - San Diego, CA, United States
    Duration: 13 Feb 200515 Feb 2005


    Conference2005 International Symposium on Medical Imaging
    CountryUnited States
    CitySan Diego, CA

    Cite this