Circumscribed Mass Detection in Digital Mammograms

The incidence of breast cancer in women has increased significantly in recent years. This paper proposes a computer aided diagnostic system for mammographic circumscribed mass detection. The propose method can distinguish between tumours and healthy tissue among various parenchymal tissue patterns. In the first stage the preprocessing and features extraction of the image is done. In this way image segmentation, filtering, contrast improvement and gray level thresholding techniques are applied for enhancing the whole image, and then the features are extracted from the resultant image. In the second part a k-means clustering algorithm is applied. The evaluation of the propose methodology is carried out on Mammography Image Analysis Society (MIAS) dataset.