Cephalometric analysis for finding facial growth abnormalities

Cephalometric analysis of lateral radiographs of the head is an important diagnosis tool in orthodontics. Based on physically locating specific landmarks, it is a boring, lengthy and error prone task. The objective of this work is to calculate the SNA angle, SNB angle and ANB angle between the landmarks to identify the input and output parameters pertaining to skeletal abnormalities. By doing so the patients data for training and testing the backpropagation neural network (BPNN), generalized regression neural network (GRNN), support vector machine (SVM) and extreme learning machine (ELM) classifiers by nine fold cross validation. The performance of skeletal is found out using the BPNN, GRNN, SVM and ELM models. This will be useful to identify whether the patient is normal or abnormal (need for treatment). This will classify condition of the different patients with severity of abnormalities in skeletal. Keywordsbackpropogation neural network (BPNN), generalized regression neural network (GRNN), support vector machine (SVM), extreme learning machine (ELM)