Relational Dependency Networks
The Journal of Machine Learning Research
A decision support system for breast cancer detection in screening programs
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Hi-index | 0.00 |
Computer-aided detection systems have as aim the increase of detection rates when analysing mammograms, by identifying features that are characteristic for breast cancer. In this research we aimed at using the features extracted from mammographic images in order to analyse the development of suspicious lesions. Different from other approaches, we based our data modelling on object orientation. This allowed not only for a description of domain entities and their intrinsic relationships, but also for the application of relational probabilistic techniques, which can handle heterogeneous data instances both in terms of learning and inference.