Communications of the ACM
Enhancing Breast Cancer Detection
Credit: Amiel Weisblum
Federal Fluminense University's Tiago Borchartt and colleagues have developed software to improve imaging with an infrared, thermal camera for the early detection of breast cancer.
Until now, breast thermography has achieved an average sensitivity and specificity of only about 90 percent for the detection of malignant tissue. The technique is painless for patients, requires no contact with instrumentation, and is entirely non-invasive. Borchartt's algorithm enables the researchers to store thermal images in a computer database and apply automatic extraction and recognition toward diagnosis. The approach can detect the presence of problems using symmetric analysis, and numerical simulations using finite element analysis, enables it to analyze the relationships between internal temperature and the temperature on the breast surface during image acquisition.
Thus far the researchers have tested the method on a limited number of thermal images from 28 patients. One test of the technique demonstrated an improvement in the accuracy of breast thermography to 96 percent.
From EurekAlert
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found