Differentiating nontuberculous mycobacterium pulmonary disease from pulmonary tuberculosis through the analysis of the cavity features in CT images using radiomics.

To differentiate nontuberculous mycobacteria (NTM) pulmonary diseases from pulmonary tuberculosis (PTB) by analyzing the CT radiomics features of their cavity. 73 patients of NTM pulmonary diseases and 69 patients of PTB with the cavity in Shandong Province Chest Hospital and Qilu Hospital of Shandong University were retrospectively analyzed. 20 patients of NTM pulmonary diseases and 20 patients of PTB with the cavity in Jinan Infectious Disease Hospitall were collected for external validation of the model. 379 cavities as the region of interesting (ROI) from chest CT images were performed by 2 experienced radiologists. 80% of cavities were allocated to the training set and 20% to the validation set using a random number generated by a computer. 1409 radiomics features extracted from the Huiying Radcloud platform were used to analyze the two kinds of diseases' CT cavity characteristics. Feature selection was performed using analysis of variance (ANOVA) and least absolute shrinkage and selection operator (LASSO) methods, and six supervised learning classifiers (KNN, SVM, XGBoost, RF, LR, and DT models) were used to analyze the features. 29 optimal features were selected by the variance threshold method, K best method, and Lasso algorithm.and the ROC curve values are obtained. In the training set, the AUC values of the six models were all greater than 0.97, 95% CI were 0.95-1.00, the sensitivity was greater than 0.92, and the specificity was greater than 0.92. In the validation set, the AUC values of the six models were all greater than 0.84, 95% CI were 0.76-1.00, the sensitivity was greater than 0.79, and the specificity was greater than 0.79. In the external validation set, The AUC values of the six models were all greater than 0.84, LR classifier has the highest precision, recall and F1-score, which were 0.92, 0.94, 0.93. The radiomics features extracted from cavity on CT images can provide effective proof in distinguishing the NTM pulmonary disease from PTB, and the radiomics analysis shows a more accurate diagnosis than the radiologists. Among the six classifiers, LR classifier has the best performance in identifying two diseases.

Yan Q ，Wang W ，Zhao W ，Zuo L ，Wang D ，Chai X ，Cui J ... -  《BMC Pulmonary Medicine》

A retrospective study differentiating nontuberculous mycobacterial pulmonary disease from pulmonary tuberculosis on computed tomography using radiomics and machine learning algorithms.

Zhou L ，Wang Y ，Zhu W ，Zhao Y ，Yu Y ，Hu Q ，Yu W ... -  《-》

CT‑based radiomics analysis of consolidation characteristics in differentiating pulmonary disease of non‑tuberculous mycobacterium from pulmonary tuberculosis.

Global incidence rate of non-tuberculous mycobacteria (NTM) pulmonary disease has been increasing rapidly. In some countries and regions, its incidence rate is higher than that of tuberculosis. It is easily confused with tuberculosis. The topic of this study is to identify two diseases using CT radioomics. The aim in the present study was to investigate the value of CT-based radiomics to analyze consolidation features in differentiation of non-tuberculous mycobacteria (NTM) from pulmonary tuberculosis (TB). A total of 156 patients (75 with NTM pulmonary disease and 81 with TB) exhibiting consolidation characteristics in Shandong Public Health Clinical Center were retrospectively analyzed. Subsequently, 305 regions of interest of CT consolidation were outlined. Using a random number generated via a computer, 70 and 30% of consolidations were allocated to the training and the validation cohort, respectively. By means of variance threshold, when investigating the effective radiomics features, SelectKBest and the least absolute shrinkage and selection operator regression method were employed for feature selection and combined to calculate the radiomics score. K-nearest neighbor (KNN), support vector machine (SVM) and logistic regression (LR) were used to analyze effective radiomics features. A total of 18 patients with NTM pulmonary disease and 18 with TB possessing consolidation characteristics in Jinan Infectious Disease Hospital were collected for external validation of the model. A total of three methods was used in the selection of 52 optimal features. For KNN, the area under the curve (AUC; sensitivity, specificity) for the training and validation cohorts were 0.98 (0.93, 0.94) and 0.90 (0.88, 083), respectively; for SVM, AUC was 0.99 (0.96, 0.96) and 0.92 (0.86, 0.85) and for LR, AUC was 0.99 (0.97, 0.97) and 0.89 (0.88, 0.85). In the external validation cohort, AUC values of models were all >0.84 and LR classifier exhibited the most significant precision, recall and F1 score (0.87, 0.94 and 0.88, respectively). LR classifier possessed the best performance in differentiating diseases. Therefore, CT-based radiomics analysis of consolidation features may distinguish NTM pulmonary disease from TB.

Yan Q ，Zhao W ，Kong H ，Chi J ，Dai Z ，Yu D ，Cui J ... -  《-》

Development and Validation of Contrast-Enhanced CT-Based Deep Transfer Learning and Combined Clinical-Radiomics Model to Discriminate Thymomas and Thymic Cysts: A Multicenter Study.

This study aims to evaluate the feasibility and effectiveness of deep transfer learning (DTL) and clinical-radiomics in differentiating thymoma from thymic cysts. Clinical and imaging data of 196 patients pathologically diagnosed with thymoma and thymic cysts were retrospectively collected from center 1. (training cohort: n = 137; internal validation cohort: n = 59). An independent external validation cohort comprised 68 thymoma and thymic cyst patients from center 2. Region of interest (ROI) delineation was performed on contrast-enhanced chest computed tomography (CT) images, and eight DTL models including Densenet 169, Mobilenet V2, Resnet 101, Resnet 18, Resnet 34, Resnet 50, Vgg 13, Vgg 16 were constructed. Radiomics features were extracted from the ROI on the CT images of thymoma and thymic cyst patients, and feature selection was performed using intra-observer correlation coefficient (ICC), Spearman correlation analysis, and least absolute shrinkage and selection operator (LASSO) algorithm. Univariate analysis and multivariable logistic regression (LR) were used to select clinical-radiological features. Six machine learning classifiers, including LR, support vector machine (SVM), k-nearest neighbors (KNN), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), and Multilayer Perceptron (MLP), were used to construct Radiomics and Clinico-radiologic models. The selected features from the Radiomics and Clinico-radiologic models were fused to build a Combined model. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical utility of the models, respectively. The Delong test was used to compare the AUC between different models. K-means clustering was used to subdivide the lesions of thymomas or thymic cysts into subregions, and traditional radiomics methods were used to extract features and compare the ability of Radiomics and DTL models to reflect intratumoral heterogeneity using correlation analysis. The Densenet 169 based on DTL performed the best, with AUC of 0.933 (95% CI: 0.875-0.991) in the internal validation cohort and 0.962 (95% CI: 0.923-1.000) in the external validation cohort. The AdaBoost classifier achieved AUC of 0.965 (95% CI: 0.923-1.000) and 0.959 (95% CI: 0.919-1.000) in the internal and external validation cohorts, respectively, for the Radiomics model. The LightGBM classifier achieved AUC of 0.805 (95% CI: 0.690-0.920) and 0.839 (95% CI: 0.736-0.943) in the Clinico-radiologic model. The AUC of the Combined model in the internal and external validation cohorts was 0.933 (95% CI: 0.866-1.000) and 0.945 (95% CI: 0.897-0.994), respectively. The results of the Delong test showed that the Radiomics model, DTL model, and Combined model outperformed the Clinico-radiologic model in both internal and external validation cohorts (p-values were 0.002, 0.004, and 0.033 in the internal validation cohort, while in the external validation cohort, the p-values were 0.014, 0.006, and 0.015, respectively). But there was no statistical difference in performance among the three models (all p-values <0.05). Correlation analysis showed that radiomics performed better than DTL in quantifying intratumoral heterogeneity differences between thymoma and thymic cysts. The developed DTL model and the Combined model based on radiomics and clinical-radiologic features achieved excellent diagnostic performance in differentiating thymic cysts from thymoma. They can serve as potential tools to assist clinical decision-making, particularly when endoscopic biopsy carries a high risk.

Yang Y ，Cheng J ，Peng Z ，Yi L ，Lin Z ，He A ，Jin M ，Cui C ，Liu Y ，Zhong Q ，Zuo M ... -  《-》

Building a model for the differential diagnosis of non-tuberculous mycobacterial lung disease and pulmonary tuberculosis: A case-control study based on immunological and radiological features.

Although the incidence of non-tuberculous mycobacterial pulmonary disease (NTM-PD) is increasing annually, it is easily misdiagnosed as pulmonary tuberculosis (PTB). This study aimed to screen and identify the immunological and radiological characteristics that differentiate NTM-PD from PTB and to construct a discriminatory diagnostic model for NTM-PD, providing new tools for its differential diagnosis. Hospitalised patients diagnosed with NTM-PD or PTB between January 2019 and June 2023 were included in the study. Immunological and radiological characteristics were compared between the two groups. Based on the selected differential features, a logistic regression algorithm was used to construct a discriminatory diagnostic model for NTM-PD, and its diagnostic performance was preliminarily analysed. Patients with NTM-PD were significantly older than those with PTB and the tuberculosis-specific interferon-gamma release assay (TB-IGRA) positivity rate was significantly lower in the NTM-PD group. Moreover, the absolute counts of total T lymphocytes, CD4+ T lymphocytes, CD8+ T lymphocytes, NK cells, and B lymphocytes were significantly lower in patients with NTM-PD and PTB than in healthy controls. Additionally, patients with NTM-PD had a significantly lower absolute count of B lymphocytes than the PTB group. Radiological analysis revealed significant differences between patients with NTM-PD and PTB in terms of cavity wall thickness, bronchial dilation, lung consolidation, pulmonary nodule size, pulmonary emphysema, lung bullae, lymph node calcification, pleural effusion, mediastinal and hilar lymphadenopathy, and the tree-in-bud sign. Bronchial dilation was identified as the predominant risk factor of NTM-PD, whereas TB-IGRA positivity, lymph node calcification, pleural effusion, and mediastinal and hilar lymphadenopathies were protective factors. Based on this, we constructed a discriminatory diagnostic model for NTM-PD. Its receiver operating characteristic curve demonstrated good diagnostic performance, with an area under the curve of 0.938. At the maximum Youden index of 0.746, the sensitivity and specificity were 0.835 and 0.911, respectively. Patients with NTM-PD and PTB exhibited impaired humoral and cellular immune functions as well as significant differences in radiological features. The constructed NTM-PD diagnostic model demonstrated good diagnostic performance. This study provides a new tool for the differential diagnosis of NTM-PD.

Liu Q ，Pan X ，An H ，Du J ，Li X ，Sun W ，Gao Y ，Li Y ，Niu H ，Gong W ，Liang J ... -  《-》