Detecting Breast Cancer from Thermal Infrared Images by Asymmetry Analysis
Overview
This is a research effort that helps define thermal infrared (TIR)
imaging as a diagnostic tool in breast cancer detection, which can be
used as a complementary modality to traditional mammography. This
research includes the following innovations: (1) it first proposes a
completely automated segmentation and detection algorithm to analyze
TIR images of breast (thermograms). One of the popular methods used to
detect breast cancer is to make comparisons between contralateral
images. When the images are relatively symmetrical, small asymmetries
may indicate a suspicious region. We propose an automated asymmetry
analysis technique on thermograms, which include automated
segmentation and automated asymmetric abnormality detection. (2) it
develops an experimental plan to apply the proposed algorithm to both
thermogram and mammogram taken from the same patient of cases
including false positive, false negative, true positive, and true
negative to get objective comparison of the sensitivity of these two
imaging procedures in breast cancer detection. Testing images will be
provided by Elliott Mastology Center at Baton Rough, LA, and Ville
Marie Breast Cancer Center in Montreal, Canada. Both of these centers
have state-of-the-art infrared cameras and mammographic equipment and
more than 20 years clinical experience in the use of infrared imaging
of the breast. The PI will develop the proposed algorithm in her lab
equipped with high-speed workstations. PI will also coordinate with
doctors from these two centers to gain clinical/diagnostic and
technical support of the cases developed.
Final Report
Detecting Breast Cancer from Thermal Infrared Images by Asymmetry Analysis (pdf)
