Abstract

One of the most common diseases affecting women is breast cancer. As a result, diagnosis and monitoring of breast health is viewed as a lifesaving procedure. Thermography shows promise for diagnosing breast cancer especially for dense breasts on which mammography does not work well. It is a noninvasive and inexpensive method based on the principle that malignant tumors have a higher metabolic rate and therefore emit more heat. A new segmentation algorithm was developed for a recent database of thermal images obtained from patients lying in the prone position. The algorithm was successful in isolating the breast from rest of the body and background. The resulting segmentation was then analyzed using temperature profiles, where significant peaks in the profile indicated a region of interest. Lastly, approximate hot spots were found that indicated the location of a possible tumor.

Publication Date

12-2019

Document Type

Thesis

Student Type

Graduate

Degree Name

Mechanical Engineering (MS)

Department, Program, or Center

Mechanical Engineering (KGCOE)

Advisor

Satish G. Kandlikar

Advisor/Committee Member

Kathleen Lamkin-Kennard

Advisor/Committee Member

Majid Rabbani

Campus

RIT – Main Campus

Share

COinS