SEGMENTATION OF BREAST THERMOGRAM : IMPROVED BOUNDARY DETECTION WITH MODIFIED SNAKE ALGORITHM

Background: Breast cancer is a common and dreadful disease in women. One in five cancers in Singaporean women is due to breast cancer. Breast health is every woman’s right and responsibility. In average, every $100 spent on breast mammogram screening, an additional $33 was spent on evaluating possible false-positive results. Thermography, with its non-radiation, non-contact and low-cost basis has been demonstrated to be a valuable and safe early risk marker of breast pathology, and an excellent case management tool available today in the ongoing monitoring and treatment of breast disease. The surface temperature and the vascularization pattern of the breast could indicate breast diseases and early detection saves lives. To establish the surface isotherm pattern of the breast and the normal range of cyclic variations of temperature distribution can assist in identifying the abnormal infrared images of diseased breasts. Before these thermograms can be analyzed objectively via computer algorithm, they must be digitized and segmented. The authors present a method to segment thermograms and extract useful region from the background. Thermography could detect the presence of tumors much earlier and of much smaller size than mammography. This paper thus aims to develop an intelligent diagnostic system based on thermography for the detection of tumors in breast. Methods: We have examined about 50 normal, healthy female volunteers in Nanyang Technological University and 130 patients in Singapore General Hospital. We did the examinations for some of them continuously for two months. From these examinations, we obtained about 1000 thermograms for contact and 800 thermograms for non-contact approaches. Standard ambient conditions were observed for all examinations. The thermograms obtained were analyzed. The first step in processing these thermograms is image segmentation. Its aim is to discern the useful region from the background. In general, autonomous segmentation is one of the most difficult tasks in image