Ensemble Systems for Automatic Fracture Detection

Abstract

Fracture detection based on image classification is an area of research which has proved to be challenging for the past several decades. This field has gained more attention due to the new challenges posed by voluminous image databases. In this research work, fusion-based classifiers are constructed, which extracts features from the images, use these features to train and test the classifiers for the purpose of detecting fractures in X-Ray images. The various features extracted are Contrast, Homogeneity, Energy, Entropy, Mean, Variance, Standard Deviation, Correlation, Gabor orientation (GO), Markov Random Field (MRF), and intensity gradient direction (IGD). Three classifiers, BPNN, SVM and NB classifiers are used. Using these features and classifiers, three single classifiers and four multiple classifiers were developed. All the classifiers were tested vigorously with the test dataset for evaluating the winner combination of classifiers and features that correctly identifies fractures in a bone image. The performance metrics used are sensitivity, specificity, positive predictive value, negative predictive value, accuracy and execution time. The experimental results showed that usage of fusion classifiers enhances the detection capacity and the combination SVM and BPNN produces the best result.