System for deep venous thrombosis detection using objective compression measures

TitleSystem for deep venous thrombosis detection using objective compression measures
Publication TypeJournal Article
Year of Publication2006
AuthorsGuerrero, J., E. Salcudean, A. McEwen, B. A. Masri, and S. Nicolaou
JournalBiomedical Engineering, IEEE Transactions on
Volume53
Pagination845 -854
Date Publishedmay.
ISSN0018-9294
Keywords16 Hz, applied force, biomechanics, biomedical ultrasonics, blood vessels, compressibility, deep venous thrombosis detection, diseases, feature detection, feature extraction, image representation, image segmentation, medical image processing, modified star-Kalman algorithm, objective vessel compression assessment, paired t-tests, phantoms, sensitivity, sensorized ultrasound probe, specificity, statistical analysis, three-dimensional shape model, tissue phantom, transverse vessel area, ultrasound image, vessel compressibility, vessel segmentation, virtual representation
Abstract

A system for objective vessel compression assessment for deep venous thrombosis characterization using ultrasound image data and a sensorized ultrasound probe is presented. Two new objective measures calculated from applied force and transverse vessel area are also presented and used to describe vessel compressibility. A modified star-Kalman algorithm is used for feature detection in acquired ultrasound images, and objective measures of vessel compressibility are calculated from the detected features and acquired force and location data from the sensorized probe. A three-dimensional shape model of the examined vessel that includes compressibility measures mapped as colors to its surface is presented on the user interface, as well as a virtual representation of the image plane. The compressibility measures were validated using expert segmentation of healthy and diseased vessels and compared using paired t-tests, which showed a significant difference between healthy and diseased cases for both measures. 100% sensitivity and specificity were obtained for both measures. The system was implemented in real-time (16 Hz) and evaluated using a tissue phantom and on healthy human subjects. Sensitivity was 100% and 60%, while specificity was 97% for both measures when implemented. The initial results for the system and its components are promising

URLhttp://dx.doi.org/10.1109/TBME.2005.863878
DOI10.1109/TBME.2005.863878

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia