Knowledge-base development with a multi-decision-tree induction approach in a medical images database

In this paper, we propose a new decision-tree induction approach called the Multi-Decision-Tree Induction (MDTI) approach and apply it to the development of the knowledge-base of the Image Retrieval Expert System (IRES). We present empirical comparisons of the MDTI approach with Backpropagation network algorithm, and the traditional knowledge acquisition approach using the same set of cases. The results show that the MDTI approach outperforms the Backpropagation network algorithm and is comparable to the traditional approach in all performance measures studied, while requiring much less learning time than either approach.