In International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases
OBJECTIVES : This study aims to establish a diagnostic algorithm combining T-SPOT with CT image analysis based on deep learning (DL) for early differential diagnosis of non-tuberculous mycobacteria pulmonary disease (NTM-PD) and pulmonary tuberculosis (PTB).
METHODS : 1049 cases were enrolled including 467 NTM-PD and 582 PTB cases. 320 cases (160 NTM-PD and 160 PTB) were randomized as testing set, and were analyzed using T-SPOT combined with the DL model. The testing cases were first divided into T-SPOT positive and negative groups, and the DL model was then used to further separate the cases into four subgroups.
RESULTS : The precision was found to be 91.7% for the subgroup of T-SPOT negative and DL classified as NTM-PD and 89.8% for T-SPOT positive and DL classified as PTB, which covered 66.9% of the total cases, compared with the accuracy rate of 80.3% of T-SPOT alone. In the other two remaining groups where the T-SPOT prediction was inconsistent with the DL model, the accuracy was 73.0% and 52.2% separately.
CONCLUSIONS : Our study shows that the new diagnostic system combining T-SPOT with DL based CT image analysis can greatly improve the classification precision of NTM-PD and PTB, when the two method predictions were consistent.
Ying Chiqing, Li Xukun, Lv Shuangzhi, Du Peng, Chen Yunzhi, Fu Hongxin, Du Weibo, Xu Kaijin, Zhang Ying, Wu Wei
2022-Sep-27
Artificial intelligence, Computed Tomography, Deep Learning, Non-tuberculous mycobacteria pulmonary disease, Pulmonary tuberculosis, T-SPOT
