Search strategies for the automatic delineation of the breast area in a multimedia breast self-examination system

Breast cancer is by far the most common cancer in females. Early detection of lumps in the breast is a key to the successful treatment of this possible fatal disease. Breast self-examination (BSE) is considered as one of the early detection methods that is noninvasive, simple and can be carried out by a woman privately and at any time. However, currently, fully interactive systems do not exist and women depend on their subjective feeling while performing BSE procedures. We aim to develop an intelligent interactive multimedia system incorporating pattern recognition and machine vision techniques, and provide real-time feedback and objective data to assist and guide women to perform BSE accurately. One of the important components of the BSE technique is that the entire breast area is examined, where breast tissue may be encountered, in order to detect all possible lumps. This paper presents two search strategies to delineate the entire breast area which represents the potential boundary for the motion of a hand. This will enable the provision for a woman performing BSE with interactive objective feedback about the area of coverage based on the automatic extraction of her personal and volumetric breast information.