Quantification of cardiac bull's-eye map based on principal strain analysis for myocardial wall motion assessment in stress echocardiography

Conference item

In this paper we consider automated myocardial wall motion assessment by quantifying a cardiac bull's eye map derived from principal strain analysis. The objective is to learn a classification model that can classify between normal and abnormal wall motions. A traditional hand-crafted feature approach based on pixel intensities is compared with a deep learning framework, where a Convolutional Neural Network (CNN) automatically learns features. Experiments on a 3D Dobutamine Stress Echo (DSE) dataset with normal and abnormal wall motions shows that both hand-crafted approaches yield comparable accuracy: Random Forests (72.1%), Support Vector Machines (70.5%), and CNN at a slightly higher accuracy (75.0%) and a lower training computational cost.

Authors: Omar, H; Domingos, J; Patra, A; Upton, R; Leeson, P

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
• Journal: Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
• Pages: 1195-1198
• Publication date: 2018-05-24
• Acceptance date: 2018-04-03
• DOI: 10.1109/isbi.2018.8363785
• EISSN: 1945-8452
• ISSN: 1945-7928
• ISBN: 9781538636367
• Keywords: FFR