The nature of statistical learning theory
The nature of statistical learning theory
LIBLINEAR: A Library for Large Linear Classification
The Journal of Machine Learning Research
Detection of left ventricular motion abnormality via information measures and Bayesian filtering
IEEE Transactions on Information Technology in Biomedicine
| Hi-index | 0.00 |
Regional wall motion and infarct scoring of MR images are routine clinical tools to grade performance and scarring in the heart. The aim of this paper is to provide a framework for automatic scoring to alert the diagnostician to potential regions of abnormality. We investigated different shape and motion configurations of a finite-element cardiac atlas of the left ventricle. Two patient populations were used: 300 asymptomatic volunteers and 105 patients with myocardial infarction, both randomly selected from the Cardiac Atlas Project database. Support vector machines were employed to estimate the boundaries between the asymptomatic control and patient groups for each of 16 standard anatomical regions in the heart. Ground truth visual wall motion scores from standard cines and infarct scoring from late enhancement were provided by experienced observers. From all configurations, end-systolic shape best predicted wall motion abnormalities (global accuracy 78%, positive predictive value 85%, specificity 91%, sensitivity 60%) and infarct scoring (74%, 72%, 91%, 44%). In conclusion, computer assisted wall motion and infarct scoring has the potential to provide robust identification of those segments requiring further clinical attention; in particular, the high specificity and relatively low sensitivity could help avoid unnecessary late gadolinium rescanning of patients.