Mining Knowledge in X-Ray Images for Lung Cancer Diagnosis

Availability of digital data within picture archiving and communication systems raises a possibilities of health care and research enhancements associated with manipulation, processing and handling of data by computers. That is a basis for computer-assisted radiology development. Further development of computer-assisted radiology is associated with the use of new intelligent capabilities, such as multimedia support, rule-based processing, computer-assisted diagnosis based on knowledge-based layer, the domain of expert-systems, model definition and codification or reproduction of expert’s decision mode, which are developing to support decision making of radiologist. In the paper, we present our work on data mining for medical image diagnosis. We use decision tree induction in order to learn the symbolic knowledge for computer-assisted image analysis. We apply our method to interpretation of x-ray images for lung cancer diagnosis. We describe our methodology on how to perform data mining on picture archiving systems. Our tool for data mining is described. Results are given and compared to conventional knowledge acquisition method. The method has shown very good results so that we are going on to apply it to other medical image diagnosis tasks like mammography image analysis.