TY  - CHAP
T3  - Lecture Notes in Computer Science
SP  - 162
A1  - Mukhopadhyay, Anirban
A1  - Oksuz, Ilkay
A1  - Tsaftaris, Sotirios A.
PB  - Springer
Y1  - 2016///
M1  - 9534
N2  - Our submission to the STACOM Challenge at MICCAI 2015 is based on the supervised learning of functional map representation between End Systole (ES) and End Diastole (ED) phases of Left Ventricle (LV), for classifying infarcted LV from the healthy ones. The Laplace-Beltrami eigen-spectrum of the LV surfaces at ES and ED, represented by their triangular meshes, are used to compute the functional maps. Multi-scale distortions induced by the mapping, are further calculated by singular value decomposition of the functional map. During training, the information of whether an LV surface is healthy or diseased is known, and this information is used to train an SVM classifier for the singular values at multiple scales corresponding to the distorted areas augmented with surface area difference of epicardium and endocardium meshes. At testing similar augmented features are calculated and fed to the SVM model for classification. Promising results are obtained on both cross validation of training data as well as on testing data, which encourages us in believing that this algorithm will perform favourably in comparison to state of the art methods.
SN  - 978-3-319-28711-9
UR  - http://dx.doi.org/10.1007/978-3-319-28712-6_18
TI  - Supervised Learning of Functional Maps for Infarct Classification
AV  - none
KW  - Infarct
KW  -  Cardiac remodeling
KW  -  Laplace-Beltrami
KW  -  SV
KW  -  SVD
T2  - Statistical Atlases and Computational Models of the Heart. Imaging and Modelling Challenges
EP  - 170
ID  - eprints3025
ER  -