Abstract
This paper presents an approach for breast cancer diagnosis in digital mammogram using curvelet transform. The motivation of this approach is the desire of using the advantages of curvelet transform into mammogram analysis. Curvelet provide stable, efficient and near-optimal representation of otherwise smooth objects having discontinuities along smooth curves. Since medical images have several objects and curved shaped, it is expected that the curvelet transform would be better for classification of cancer classes in digital mammogram. To construct and evaluate a supervised classifier for this problem, by transforming the data of the images in curvelet basis and then using a special set of coefficients as the features tailored towards separating each of those classes. The experimental results indicate that using curvelet transform significantly improves the classification of cancer classes.