Multimodality based Tissue Classification Technique for Malignant Anomaly Detection

Date created: 
2014-08-11
Identifier: 
etd8609
Keywords: 
Clinical Exam
Palpation
Electrical Impedance Spectroscopy
Skin Surface Thermometry
Decision Making
Multiple Modality Integration
Abstract: 

A multi-sensor based tool has been developed to aid physicians performing clinical exams, focusing on cancer applications. Current research envisions improvement in sensor based measurement technologies to differentiate malignant and benign lesions in human subjects. The tool integrates (initially) three different modalities to detect malignant anomalies: electrical impedance spectroscopy, electronic palpation and skin surface thermometry. These methods each exploit different physical phenomena of tumors that aid in the early detection of cancers but individually are limited for accuracy and reliability. The multimodality tool has been tested over phantoms (tissue equivalent material), in vitro animal tissue (for establishing multi-modality tissue relationships; e.g. tissue mechanical, impedance properties etc.), in vivo healthy human tissue (for tissue characterization confirmation) and in vivo malignant human tissue (tested on skin cancer subjects). Additional decision making algorithms have further resulted in a more objective anomaly detection tool. As a long-term goal, the development of a low cost, non-invasive, multimodality tool for clinical examination will be a valuable tool in physicians’ office. This potentially will reduce health care costs by reducing unwanted diagnostic tests by providing more objective screening examination and will be very useful in improving rural health or in developing countries where screening/diagnostic resources are scarce.

Document type: 
Thesis
Rights: 
Copyright remains with the author. The author has not granted permission for the file to be printed nor for the text to be copied and pasted. If you would like a printable copy of this thesis, please contact summit-permissions@sfu.ca.
File(s): 
Supervisor(s): 
Farid Golnaraghi
Department: 
Applied Sciences: School of Mechatronic Systems Engineering
Thesis type: 
(Thesis) Ph.D.
Statistics: