Fixed block-based lossless compression of digital mammograms

Abstract

Breast cancer is a leading cause of death among women in Canada. Computer-aided diagnosis of mammograms (X-ray films of breast tissue) is a noninvasive and an inexpensive way of diagnosing breast cancer. The objective of this project is to investigate image compression schemes for faithful transmission and reproduction of digital mammography data over a communication link. A fixed block-based (FBB) near lossless compression scheme for mammograms has been developed which runs in conjunction with traditional compression schemes such as Huffman coding and Lempel-Ziv Welch (1978) coding. The algorithm codes blocks of pixels within the image that contain the same intensity value (the odds of having blocks of the same pixel values in a mammography image are very high), thus reducing the size of the image substantially while encoding the image at the same time. The proposed compression scheme was applied on 44 mammograms (22 benign and 22 malignant), and the compression scheme provided a compression ratio of 1.7:1. When Huffman (1952) coding and LZW coding were used in conjunction with the FBB compression scheme, the compression ratio was 3.81:1 for Huffman, and 5:1 for LZW coding. The proposed FBB lossless compression technique seems to be promising for teleradiology applications.