A 3D Visualization System for Computer-Aided Mammogram Analysis

The most frequent symptoms of ductal carcinoma recognized by mammography are clusters of microcalcifications. Their detection from mammograms is difficult, especially for glandular breasts. We present a new system for computer-aided diagnosis of breast carcinoma, from digital mammograms. The images are processed in several steps. First, we filter the original picture with a filter that is sensitive to microcalcification contrast shape. Then we enhance the mammogram contrast by using wavelet-based sharpening algorithm. We present to radiologist for visual analysis, such a contrast-enhanced mammogram, with the suggested positions of microcalcification clusters. Finally, the radiologist, makes a more sophisticated diagnosis based on 3D visualization environment. We have evaluated the usefulness of this system with the help of four experienced radiologists, who found that this approach produces a significant improvement in the diagnosis.