Image stitching and computer-aided diagnosis for whole breast ultrasound image

Breast cancer is one of the most common cancers among women all over the world The early detection provides a better chance of proper treatment. In the last decade, ultrasound (US) imaging plays an important role in the field of breast cancer diagnosis because of its convenience and non-invasive. However, the US probe does not fully cover the breast width; it is not a convenient screening tool when adjunct with screening mammography. In this paper, an image stitching technique is proposed to stitch multi-pass images into a full-view image. Besides, a fully automatic screening system for full-view breast image is also developed. By examining the US test database consisted of 25 cases, almost all the tumors or cysts can successfully be detected. A free-response operative characteristics (FROC) curve is also used to evaluate the performance. In our experimental results, the proposed CAD scheme yields a 92.3% detection sensitivity at a FP rate of 1.76 FP per case.