Tooth Decay Diagnosis using Back Propagation Neural Network

Artificial neural network (ANN), with its high performances in handling complex problems, has been widely used in medical image processing for clinical diagnostic application. In this paper, an ANN tooth decay diagnostic strategy was proposed and carefully experimented. A back propagation (BP) neural network was formed to analyze the X-ray image of patient's teeth. With inter-pixel autocorrelation coefficients as its input feature vector, the network achieved considerable good performance in making differential diagnoses between decayed and normal teeth. The tooth decay detection accuracy was significantly improved comparing to the diagnosis made by a "rule-based" computer assisted program and a group of dentists