King's College London

Research portal

Myocardial infarction detection from left ventricular shapes using a random forest

Research output: Chapter in Book/Report/Conference proceedingConference paper

Jack Allen, Ernesto Zacur, Erika Dall'Armellina, Pablo Lamata de la Orden, Vicente Grau

Original languageEnglish
Title of host publication6th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2015
Number of pages10
StatePublished - 2016

King's Authors


Understanding myocardial remodelling, and developing tools for its accurate quantification, is fundamental for improving the diagnosis and treatment of myocardial infarction patients. Conventional clinical metrics, such as blood pool volume or ejection fraction, are not always distinctive. Here we describe a method for the classification of myocardial infarction from 3D diastolic and systolic left ventricle shapes, represented by point sets. Classification features included global geometric, shape and thickness descriptors, and a random forest was used for classification. Results from cross validation show an accuracy of 92.5% (leave-one-out) and 91.5% (5-fold), improving the 87% obtained with ejection fraction thresholds. These results suggest that refined remodelling metrics provide information beyond standard clinical descriptors.

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454