Digital mammographic image analysis and data compression

This paper proposes a digital mammogram segmentation method for mammographic images, which is based on the gradient detection between breast tissue and non-tissue area. Virtually, detection of tissue edge in medical image is closely related to the correctness of image segmentation. In this paper, we focus on digital mammograms and develop an edge detection method to extract breast tissue against background with noise and/or random artifacts, as a preprocess of image compression. The results show that the developed method performs a precise recovery of boundary between breast tissue and non-tissue area, which is then removed for increasing compression rate. Therefore, problems of image transmission efficiency and data storage amount can be greatly improved. The compression rate is promoted from 3:1 to 5-6:1 by a non-lossy compression method.