Performance testing of several classifiers for differentiation among obstructive lung diseases based on texture feature at HRCT

摘要

We have compared the performance of several machine classifiers for differentiating among obstructive lung diseases based on features from texture analysis using HRCT images. HRCT can provide accurate information for the detection of various obstructive lung diseases. Features on HRCT images can be subtle, however, particularly in the early stages of disease, and image-based diagnosis is subject to inter-observer variation. To automate the diagnosis and improve the accuracy, we compared four types of automated classification systems, naive Bayesian, Bayesian, ANN and SVM. SVM showed the best performance, with 91.5% overall sensitivity, significantly different from the other classifiers (one-way ANOVA, p<0.01). We address the characteristics of each classifier affecting performance and the issue of which classifier is the most suitable for clinical applications. These results can be applied to classifiers for differentiation of other diseases.