A clustering-based approach for prediction of cardiac resynchronization therapy

Authors:
Heng Huang;Li Shen;Fillia Makedon;Sheng Zhang;Mark Greenberg;Ling Gao;Justin Pearlman
Affiliations:
Dartmouth College, Hanover, NH;University of Massachusetts Dartmouth, MA;Dartmouth College, Hanover, NH;Dartmouth College, Hanover, NH;Dartmouth Medical School, Lebanon, NH;Dartmouth Medical School, Lebanon, NH;Dartmouth College, Hanover, NH
Venue:
Proceedings of the 2005 ACM symposium on Applied computing
Year:
2005

Citing 2
Cited 1

Information retrieval: data structures and algorithms

Information retrieval: data structures and algorithms
Introduction to Machine Learning (Adaptive Computation and Machine Learning)

Introduction to Machine Learning (Adaptive Computation and Machine Learning)

Surface alignment of 3d spherical harmonic models: application to cardiac MRI analysis

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method for predicting pacing sites in the left ventricle of a heart and its result can be used to assist device programming in cardiac resynchronization therapy (CRT), which is a widely adopted therapy for heart failure patients. In a traditional CRT device deployment, pacing sites are selected without quantitative prediction. That runs the risk of suboptimal benefits. In this work, a surface tracking method is proposed to describe the ventricular wall motion and a hierarchical agglomerative clustering technique is applied to radial motion series to find candidate pacing sites. Using clinical MRI data in our experiments, we show that the proposed method performs as well as we expect. Our approach can not only effectively identify suitable pacing sites, but also distinguish patients from normals perfectly to help medical diagnosis.