Breast cancer detection enhanced through computer algorithm analysis of thermal images
Straightforward imaging of the breast with an infrared, thermal camera can detect cancer early without the discomfort or inconvenience of mammography or biomolecular tests.
Up to now, breast thermography has only achieved an average sensitivity and specificity, with approximately 90% of malignant tissue detected. The technique has the advantage of being painless, as it requires no contact between the patient and instrumentation, and it is entirely noninvasive. However, the 90% accuracy rate means that improvement is needed before such a technique could become a mainstream clinical diagnostic for the early stages of breast cancer.
The researchers, from Federal Fluminense University in Brazil, developed new software that allows them to acquire thermal images in a computer database. The software helps with diagnosis after it automatically extracts the regions of interest. The same tool combines storage with extracting and recognizing features. This approach can detect the presence of problems through symmetric analysis and numerical simulations using finite element analysis. This allows the software to analyze the relationships between internal temperature and the temperature on the breast surface during image acquisition.
So far, the research team has tested their approach on thermal images from 28 patients, which includes four healthy patients, eight with cysts, 11 with fibroadenoma, and five with carcinoma. Their approach improved the accuracy of breast thermography to 96%. Their next step will be to test their approach in a larger group of at least 2,000 patients.This study was published in the International Journal of Innovative Computing and Applications (2012;4:163-183).