Assessment of regional myocardial function via statistical features in MR images

Authors:
Mariam Afshin;Ismail Ben Ayed;Kumaradevan Punithakumar;Max W. K. Law;Ali Islam;Aashish Goela;Ian Ross;Terry Peters;Shuo Li
Affiliations:
University of Western Ontario and Robarts Research Institute, London, ON, Canada;GE Healthcare, London, ON, Canada;GE Healthcare, London, ON, Canada;University of Western Ontario and GE Healthcare, London, ON, Canada;St. Joseph's Health Care, London, ON, Canada;London Health Science Center, London, Ontario, Canada;London Health Science Center, London, Ontario, Canada;University of Western Ontario and Robarts Research Institute, London, ON, Canada;University of Western Ontario and GE Healthcare, London, ON, Canada
Venue:
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Year:
2011

Citing 6
Cited 0

Face recognition using LDA mixture model

Pattern Recognition Letters
A Statistical Overlap Prior for Variational Image Segmentation

International Journal of Computer Vision
Biomechanically-Constrained 4D Estimation of Myocardial Motion

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Heart Motion Abnormality Detection via an Information Measure and Bayesian Filtering

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Pattern Recognition of Abnormal Left Ventricle Wall Motion in Cardiac MR

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Regional heart motion abnormality detection via information measures and unscented kalman filtering

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Early and accurate detection of Left Ventricle (LV) regional wall motion abnormalities significantly helps in the diagnosis and followup of cardiovascular diseases. We present a regional myocardial abnormality detection framework based on image statistics. The proposed framework requires a minimal user interaction, only to specify initial delineation and anatomical landmarks on the first frame. Then, approximations of regional myocardial segments in subsequent frames were systematically obtained by superimposing the initial delineation on the rest of the frames. The proposed method exploits the Bhattacharyya coefficient to measure the similarity between the image distribution within each segment approximation and the distribution of the corresponding user-provided segment. Linear Discriminate Analysis (LDA) is applied to find the optimal direction along which the projected features are the most descriptive. Then a Linear Support VectorMachine (SVM) classifier is employed for each of the regional myocardial segments to automatically detect abnormally contracting regions of the myocardium. Based on a clinical dataset of 30 subjects, the evaluation demonstrates that the proposed method can be used as a promising diagnostic support tool to assist clinicians.