Applications of Multi-Resolution Neural Networks to Mammography

We have previously presented a coarse-to-fine hierarchical pyra(cid:173) mid/neural network (HPNN) architecture which combines multi(cid:173) scale image processing techniques with neural networks. The first application is the detection of microcalcifications. The:oarse-to-fine HPNN was designed to learn large-scale context in(cid:173) formation for detecting small objects like microcalcifications. Re(cid:173) ceiver operating characteristic (ROC) analysis suggests that the hierarchical architecture improves detection performance of a well established CAD system by roughly 50 %. The second application is to detect mammographic masses directly. Since masses are large, extended objects, the coarse-to-fine HPNN architecture is not suit(cid:173) able for this problem.