Expert system with an embedded imaging module for diagnosing lung diseases

Lung diseases are one of the biggest killers in the world. Improved survival rate amid be obtained if the diseases can be detected at its early stage. The diagnosis of complex lung problems often requires the use of specialized diagnostic imaging methods such as X-Rays, MRI, CT Scan, etc. Medical consultants and radiologists are scarce in rural areas and mostly based in major hospitals in the cities. In this work, a rule-based expert system with an embedded imaging module has been developed. This system can assist general physicians for the early detection of lung diseases. A chest X-ray image processing tool (CIPT) consisting of imaging functions, a modified greyscale top hat (MGTH) function and a fuzzy inference system (FIS) are incorporated for the analysis of chest X-ray images. MGTH will improve the detectability of lung nodules and the fuzzy inference technique is used to diagnose the level of malignancy. The system was tested with 30 tests cases and was found to have an accuracy level of 90%.