Objective To analyze the clinical value of multi-slice spiral CT (MSCT) in the diagnosis of nontuberculous mycobacteria (NTM) lung disease. Methods 59 patients with NTM lung disease admitted to the hospital from January 2014 to December 2018 were enrolled in the NTM lung disease group. The other 59 patients with pulmonary tuberculosis admitted in the same period were enrolled in pulmonary tuberculosis group. The distribution of lesions and MSCT signs in the two groups were compared. Binary Logistic regression prediction model was established. The diagnostic value of MSCT signs for NTM lung disease was analyzed. Results In the NTM lung disease group, the proportion of patients with distribution of lesions in the II area was significantly higher than that of the pulmonary tuberculosis group (P<0.05). The proportion of patients with bronchiectasis, bronchoconstriction or occlusion and lung damage was significantly higher than that of the pulmonary tuberculosis group, while the proportion of patients with acinar nodules and consolidation was significantly lower than that of pulmonary tuberculosis group (P<0.05). Binary Logistic regression analysis showed that bronchiectasis, bronchial center stenosis, centrilobular nodules and lung damage were independent risk factors for NTM lung disease (P<0.05). After the above factors were included in the predictive model, the analysis of ROC curve was performed. The sensitivity and specificity by MSCT for diagnosis of NTM lung disease were 88.10% and 83.10%, respectively. Conclusion MSCT examination combined with the signs of bronchiectasis, bronchial center stenosis, centrilobular nodules and lung damage may indicate NTM lung disease.