Share Email Print
cover

Proceedings Paper

Learning distance function for regression-based 4D pulmonary trunk model reconstruction estimated from sparse MRI data
Author(s): Dime Vitanovski; Alexey Tsymbal; Razvan Ionasec; Bogdan Georgescu; Shaohua K. Zhou; Joachim Hornegger; Dorin Comaniciu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Congenital heart defect (CHD) is the most common birth defect and a frequent cause of death for children. Tetralogy of Fallot (ToF) is the most often occurring CHD which affects in particular the pulmonary valve and trunk. Emerging interventional methods enable percutaneous pulmonary valve implantation, which constitute an alternative to open heart surgery. While minimal invasive methods become common practice, imaging and non-invasive assessment tools become crucial components in the clinical setting. Cardiac computed tomography (CT) and cardiac magnetic resonance imaging (cMRI) are techniques with complementary properties and ability to acquire multiple non-invasive and accurate scans required for advance evaluation and therapy planning. In contrary to CT which covers the full 4D information over the cardiac cycle, cMRI often acquires partial information, for example only one 3D scan of the whole heart in the end-diastolic phase and two 2D planes (long and short axes) over the whole cardiac cycle. The data acquired in this way is called sparse cMRI. In this paper, we propose a regression-based approach for the reconstruction of the full 4D pulmonary trunk model from sparse MRI. The reconstruction approach is based on learning a distance function between the sparse MRI which needs to be completed and the 4D CT data with the full information used as the training set. The distance is based on the intrinsic Random Forest similarity which is learnt for the corresponding regression problem of predicting coordinates of unseen mesh points. Extensive experiments performed on 80 cardiac CT and MR sequences demonstrated the average speed of 10 seconds and accuracy of 0.1053mm mean absolute error for the proposed approach. Using the case retrieval workflow and local nearest neighbour regression with the learnt distance function appears to be competitive with respect to "black box" regression with immediate prediction of coordinates, while providing transparency to the predictions made.

Paper Details

Date Published: 2 March 2011
PDF: 7 pages
Proc. SPIE 7964, Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling, 79640L (2 March 2011); doi: 10.1117/12.878195
Show Author Affiliations
Dime Vitanovski, Siemens Corporate Research (United States)
Siemens Corporate Technology (Germany)
Alexey Tsymbal, Siemens Corporate Technology (Germany)
Razvan Ionasec, Siemens Corporate Research (United States)
Bogdan Georgescu, Siemens Corporate Research (United States)
Shaohua K. Zhou, Siemens Corporate Research (United States)
Joachim Hornegger, Friedrich-Alexander-Univ. Erlangen-Nürnberg (Germany)
Dorin Comaniciu, Siemens Corporate Research (United States)


Published in SPIE Proceedings Vol. 7964:
Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling
Kenneth H. Wong; David R. Holmes, Editor(s)

© SPIE. Terms of Use
Back to Top