Automated Analysis of Chest Radiographs for Cystic Fibrosis Scoring

Abstract

We present a framework to analyze chest radiographs for cystic fibro-sis using machine learning methods. We compare the representational power of deep learning features with traditional texture features. Specifically, we respec-tively employ VGG-16 based deep learning features, Tamura and Gabor filter based textural features to represent the cystic fibrosis images. We demonstrate that VGG-16 features perform best, with a maximum agreement of 82%. In ad-dition, due to limited dimensionality, Tamura features for unsegmented images achieve no more than 50% agreement; however, after segmentation, the accuracy of Tamura can reach 78%. In combination with using the deep learning features, we also compare back propagation neural network and sparse coding classifiers to the typical SVM classifier with polynomial kernel function. The result shows that neural network and sparse coding classifiers outperform SVM in most cases. Only with insufficient training samples does SVM demonstrate higher accuracy.