Obesity has become a significant concern for severe health risks and has caused millions of deaths globally. It is defined as excess accumulation of adipose tissue in the body. Cardiac adipose tissue deposited around the myocardium has been recognized as a significant contributor to several non-communicable diseases such as metabolic syndrome, cardiovascular diseases, coronary artery diseases, insulin resistance, hypertension and even some forms of cancer. As a preventive measure, quantification of the amount of adipose tissue deposited around the myocardium is vital to understand the severity of the health risk it poses. The study presented here aims to investigate spectral analysis techniques for ultrasonic tissue characterization of cardiac adipose tissue, myocardium, and blood. Autoregressive spectral estimation techniques were used in this study to compute the power spectral densities of the raw ultrasound radiofrequency data obtained from echocardiography of seven volunteer participants. Thirteen spectral features were computed from the power spectral densities of three different bandwidth ranges and random forest classifiers were generated using these spectral features. Seventy-five percent of the available data were divided into the training set to train the classifier, and the remaining data was used as a test set. The classifiers were tested on the test set data and yielded an overall average accuracy of 94.1%. This result in the preliminary study shows the capability of ultrasound radiofrequency data in tissue characterization and lays the foundation for further investigation of cardiac tissue characterization techniques.
|Advisor:||Klingensmith, Jon D.|
|Commitee:||Noble, Bradley, Wang, Yadong|
|School:||Southern Illinois University at Edwardsville|
|School Location:||United States -- Illinois|
|Source:||MAI 58/04M(E), Masters Abstracts International|
|Subjects:||Engineering, Electrical engineering|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be