Segmentation, alignment and statistical analysis of biosignals with application to disease classification

Sebastian Kurtek; Wei Wu; Gary E Christensen; Anuj Srivastava

doi:10.1080/02664763.2013.785492

Back

Segmentation, alignment and statistical analysis of biosignals with application to disease classification

Journal article

Peer reviewed

Segmentation, alignment and statistical analysis of biosignals with application to disease classification

Sebastian Kurtek, Wei Wu, Gary E Christensen and Anuj Srivastava

Journal of applied statistics, Vol.40(6), pp.1270-1288

06/01/2013

DOI: 10.1080/02664763.2013.785492

View Online

Abstract

We present a novel methodology for a comprehensive statistical analysis of approximately periodic biosignal data. There are two main challenges in such analysis: (1) the automatic extraction (segmentation) of cycles from long, cyclostationary biosignals and (2) the subsequent statistical analysis, which in many cases involves the separation of temporal and amplitude variabilities. The proposed framework provides a principled approach for statistical analysis of such signals, which in turn allows for an efficient cycle segmentation algorithm. This is achieved using a convenient representation of functions called the square-root velocity function (SRVF). The segmented cycles, represented by SRVFs, are temporally aligned using the notion of the Karcher mean, which in turn allows for more efficient statistical summaries of signals. We show the strengths of this method through various disease classification experiments. In the case of myocardial infarction detection and localization, we show that our method compares favorably to methods described in the current literature.

cyclostationary biosignal segmentation

disease classification

functional data analysis

gait

myocardial infarction

Details

Title: Subtitle: Segmentation, alignment and statistical analysis of biosignals with application to disease classification
Creators: Sebastian Kurtek - The Ohio State University
Wei Wu - Florida State University
Gary E Christensen - University of Iowa
Anuj Srivastava - Florida State University
Resource Type: Journal article
Publication Details: Journal of applied statistics, Vol.40(6), pp.1270-1288
Publisher: Taylor & Francis
DOI: 10.1080/02664763.2013.785492
ISSN: 0266-4763
eISSN: 1360-0532
Language: English
Date published: 06/01/2013
Academic Unit: Radiation Research Laboratory; Electrical and Computer Engineering; Radiation Oncology; The Iowa Institute for Biomedical Imaging; Advanced Pulmonary Physiomic Imaging Laboratory; Holden Comprehensive Cancer Center
Record Identifier: 9984197180802771

Metrics

10 Record Views

11 Times Cited - Web of Science