Neural Network based classification for orthopedic conditions diagnosis using grey level co-occurrence probabilities

Medical imaging has become a major tool in clinical experiments due to its ability in rapid diagnosis with visualization and quantitative assessment. Fractal and texture analysis are the computer techniques used to discriminate between the orthopedic conditions such as broken, dislocated and injured bones. The main focus is to perform texture segmentation and classification for the medical images. The textural features are extracted based on the grey level cooccurrence probabilities generated. In this paper, we have used the Back Propagation Algorithm of Artificial Neural Networks for segmentation and classification of the medical images. Neural Networks classification saves the radiologist time, increases accuracy and yield of diagnosis.