Machine Learning-Based Differentiation of Nontuberculous Mycobacteria Lung Disease and Pulmonary Tuberculosis Using CT Images

Figure 5

The performance of disease differentiation via analyzing different regions (TA, cavity; TB, bronchiectasis; TC, combined analysis using automated feature selection; TD, combined analysis using retrieved features from TA and TB). It shows that using bronchiectasis (TB) achieves overall best performance.