Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs.

BACKGROUND: Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance. METHODS: We developed a deep learning-based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation. RESULTS: DLAD demonstrated classification performance of 0.977-1.000 and localization performance of 0.973-1.000. Sensitivities and specificities for classification were 94.3%-100% and 91.1%-100% using the high-sensitivity cutoff and 84.1%-99.0% and 99.1%-100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746-0.971) and localization (0.993 vs 0.664-0.925) compared to all groups of physicians. CONCLUSIONS: Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.

Deep Learning Analysis of CT Images Reveals High-Grade Pathological Features to Predict Survival in Lung Adenocarcinoma.

We aimed to develop a deep learning (DL) model for predicting high-grade patterns in lung adenocarcinomas (ADC) and to assess the prognostic performance of model in advanced lung cancer patients who underwent neoadjuvant or definitive concurrent chemoradiation therapy (CCRT). We included 275 patients with 290 early lung ADCs from an ongoing prospective clinical trial in the training dataset, which we split into internal-training and internal-validation datasets. We constructed a diagnostic DL model of high-grade patterns of lung ADC considering both morphologic view of the tumor and context view of the area surrounding the tumor (MC3DN; morphologic-view context-view 3D network). Validation was performed on an independent dataset of 417 patients with advanced non-small cell lung cancer who underwent neoadjuvant or definitive CCRT. The area under the curve value of the DL model was 0.8 for the prediction of high-grade histologic patterns such as micropapillary and solid patterns (MPSol). When our model was applied to the validation set, a high probability of MPSol was associated with worse overall survival (probability of MPSol >0.5 vs. <0.5; 5-year OS rate 56.1% vs. 70.7%), indicating that our model could predict the clinical outcomes of advanced lung cancer patients. The subgroup with a high probability of MPSol estimated by the DL model showed a 1.76-fold higher risk of death (HR 1.76, 95% CI 1.16-2.68). Our DL model can be useful in estimating high-grade histologic patterns in lung ADCs and predicting clinical outcomes of patients with advanced lung cancer who underwent neoadjuvant or definitive CCRT.

Development and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs.

Importance: Interpretation of chest radiographs is a challenging task prone to errors, requiring expert readers. An automated system that can accurately classify chest radiographs may help streamline the clinical workflow. Objectives: To develop a deep learning-based algorithm that can classify normal and abnormal results from chest radiographs with major thoracic diseases including pulmonary malignant neoplasm, active tuberculosis, pneumonia, and pneumothorax and to validate the algorithm's performance using independent data sets. Design, Setting, and Participants: This diagnostic study developed a deep learning-based algorithm using single-center data collected between November 1, 2016, and January 31, 2017. The algorithm was externally validated with multicenter data collected between May 1 and July 31, 2018. A total of 54 221 chest radiographs with normal findings from 47 917 individuals (21 556 men and 26 361 women; mean [SD] age, 51 [16] years) and 35 613 chest radiographs with abnormal findings from 14 102 individuals (8373 men and 5729 women; mean [SD] age, 62 [15] years) were used to develop the algorithm. A total of 486 chest radiographs with normal results and 529 with abnormal results (1 from each participant; 628 men and 387 women; mean [SD] age, 53 [18] years) from 5 institutions were used for external validation. Fifteen physicians, including nonradiology physicians, board-certified radiologists, and thoracic radiologists, participated in observer performance testing. Data were analyzed in August 2018. Exposures: Deep learning-based algorithm. Main Outcomes and Measures: Image-wise classification performances measured by area under the receiver operating characteristic curve; lesion-wise localization performances measured by area under the alternative free-response receiver operating characteristic curve. Results: The algorithm demonstrated a median (range) area under the curve of 0.979 (0.973-1.000) for image-wise classification and 0.972 (0.923-0.985) for lesion-wise localization; the algorithm demonstrated significantly higher performance than all 3 physician groups in both image-wise classification (0.983 vs 0.814-0.932; all P < .005) and lesion-wise localization (0.985 vs 0.781-0.907; all P < .001). Significant improvements in both image-wise classification (0.814-0.932 to 0.904-0.958; all P < .005) and lesion-wise localization (0.781-0.907 to 0.873-0.938; all P < .001) were observed in all 3 physician groups with assistance of the algorithm. Conclusions and Relevance: The algorithm consistently outperformed physicians, including thoracic radiologists, in the discrimination of chest radiographs with major thoracic diseases, demonstrating its potential to improve the quality and efficiency of clinical practice.