A deep learning model using chest X-ray for identifying TB and NTM-LD patients: a cross-sectional study

Abstract

Background Timely differentiating between pulmonary tuberculosis (TB) and nontuberculous mycobacterial lung disease (NTM-LD), which are radiographically similar, is important because infectiousness and treatment differ. This study aimed to evaluate whether artificial intelligence could distinguish between TB or NTM-LD patients by chest X-rays (CXRs) from suspects of mycobacterial lung disease. Methods A total of 1500 CXRs, including 500 each from patients with pulmonary TB, NTM-LD, and patients with clinical suspicion but negative mycobacterial culture (Imitator) from two hospitals, were retrospectively collected and evaluated in this study. We developed a deep neural network (DNN) and evaluated model performance using the area under the receiver operating characteristic curves (AUC) in both internal and external test sets. Furthermore, we conducted a reader study and tested our model under three scenarios of different mycobacteria prevalence. Results Among the internal and external test sets, the AUCs of our DNN model were 0.83 ± 0.005 and 0.76 ± 0.006 for pulmonary TB, 0.86 ± 0.006 and 0.64 ± 0.017 for NTM-LD, and 0.77 ± 0.007 and 0.74 ± 0.005 for Imitator. The DNN model showed higher performance on the internal test set in classification accuracy (66.5 ± 2.5%) than senior (50.8 ± 3.0%, p < 0.001) and junior pulmonologists (47.5 ± 2.8%, p < 0.001). Among different prevalence scenarios, the DNN model has stable performance in terms of AUC to detect TB and mycobacterial lung disease. Conclusion DNN model had satisfactory performance and a higher accuracy than pulmonologists on classifying patients with presumptive mycobacterial lung diseases. DNN model could be a complementary first-line screening tool.

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

“…The pre-trained model was successfully applied to retinal optical coherence tomography and pneumonia diagnosis [34]. In our previous studies, we also successfully demonstrated the capability of fine-tuning in improving model performance on external cohort [10,18].…”

“…Deep learning involving convoluted neural network (CNN) is novel and emerging technique for breathprint analysis [8,9]. Some analytic approaches such as transfer learning and data augmentation have been applied in other aspects of biomedical imaging researches [10]. These methods could potentially propagate sample size, enhance performance and ameliorate the drop of performance in domain shift [11,12].…”

Next-Generation TB Vaccines: Progress, Challenges, and Prospects

“…For instance, a cross-sectional study published in Insights Imaging in 2023 developed a deep neural network (DNN) algorithm to detect the X-ray results of TB patients, distinguishing between active PTB and nontuberculous mycobacterial lung disease (NTM-LD). The study demonstrated that the DNN model exhibited stable performance in detecting TB and mycobacterial lung disease based on the area under the curve (AUC) [ 258 ]. Furthermore, various deep learning algorithms, including decision trees, random forests, support vector machines, Bayesian methods, logistic regression, and hierarchical clustering, have been applied in the differentiation and diagnosis of LTBI and ATB, substantially enhancing the diagnostic efficacy [ 259 , 260 , 261 , 262 , 263 , 264 , 265 ].…”