Knowledge Acquisition by Symbolic Decision Tree Induction for Interpretation of Digital Images in Radiology

Knowledge Acquisition is an important task when developing image interpretation systems. Whereas in the past this task has been done by interviewing an expert, the current trend is to collect large data bases of images associated with expert description ( known as picture archiving systems). This makes it possible to use inductive machine learning techniques for knowledge acquisition of image interpretation systems. We use decision tree induction in order to learn the symbolic knowledge for image interpretation. We applied the method to interpretation of xray images for lung cancer diagnosis. In the paper, we present our methodology for applying inductive machine learning. We discuss our results and compare it to other knowledge acquisition methods.