Our deep learning–based automatic detection algorithm outperformed physicians in radiograph classification and nodule detection performance for malignant pulmonary nodules on chest radiographs, and when used as a second reader, it enhanced physicians’ performances. Purpose To develop and validate a deep learning–based automatic detection algorithm (DLAD) for malignant pulmonary nodules on chest radiographs and to compare its performance with physicians including thoracic radiologists. Materials and Methods For this retrospective study, DLAD was developed by using 43 292 chest radiographs (normal radiograph–to–nodule radiograph ratio, 34 067:9225) in 34 676 patients (healthy-to-nodule ratio, 30 784:3892; 19 230 men [mean age, 52.8 years; age range, 18–99 years]; 15 446 women [mean age, 52.3 years; age range, 18–98 years]) obtained between 2010 and 2015, which were labeled and partially annotated by 13 board-certified radiologists, in a convolutional neural network. Radiograph classification and nodule detection performances of DLAD were validated by using one internal and four external data sets from three South Korean hospitals and one U.S. hospital. For internal and external validation, radiograph classification and nodule detection performances of DLAD were evalua...

Chest radiographs (CRs) have been used as a first-line examination for the evaluation of various thoracic diseases worldwide.^1,2 In fact, CR is the most commonly performed radiologic examination today, accounting for up to 26% of all diagnostic radiologic examinations.³ Interpretation of CR, however, remains a challenging task requiring both experience and expertise, as various anatomic structures can overlap in a single 2-dimensional image, and various physiological and pathological changes may appear similar or a single pathology may exhibit various features.⁴ Thus, interpretation is prone to errors, with a previous study⁵ reporting that 22% of all errors in diagnostic radiology were made in CRs. Compounding this difficulty is an increase in the number of examinations at a rate much faster than the increase in the number of qualified radiologists, which has led to an increased workload for radiologists.⁶

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.

Use of a commercially available deep learning algorithm for evaluating chest radiographs resulted in identification of clinically relevant abnormalities on emergency department radiographs and impr... BackgroundThe performance of a deep learning (DL) algorithm should be validated in actual clinical situations, before its clinical implementation.PurposeTo evaluate the performance of a DL algorith...

Background The impact of artificial intelligence (AI)-based computer-aided detection (CAD) software has not been prospectively explored in real-world populations. Purpose To investigate whether commercial AI-based CAD software could improve the detection rate of actionable lung nodules on chest radiographs in participants undergoing health checkups. Materials and Methods In this single-center, pragmatic, open-label randomized controlled trial, participants who underwent chest radiography between July 2020 and December 2021 in a health screening center were enrolled and randomized into intervention (AI group) and control (non-AI group) arms. One of three designated radiologists with 13-36 years of experience interpreted each radiograph, referring to the AI-based CAD results for the AI group. The primary outcome was the detection rate, that is, the number of true-positive radiographs divided by the total number of radiographs, of actionable lung nodules confirmed on CT scans obtained within 3 months. Actionable nodules were defined as solid nodules larger than 8 mm or subsolid nodules with a solid portion larger than 6 mm (Lung Imaging Reporting and Data System, or Lung-RADS, category 4). Secondary outcomes included the positive-report rate, sensitivity, false-referral rate, and malignant lung nodule detection rate. Clinical outcomes were compared between the two groups using univariable logistic regression analyses. Results A total of 10 476 participants (median age, 59 years [IQR, 50-66 years]; 5121 men) were randomized to an AI group (n = 5238) or non-AI group (n = 5238). The trial met the predefined primary outcome, demonstrating an improved detection rate of actionable nodules in the AI group compared with the non-AI group (0.59% [31 of 5238 participants] vs 0.25% [13 of 5238 participants], respectively; odds ratio, 2.4; 95% CI: 1.3, 4.7; P = .008). The detection rate for malignant lung nodules was higher in the AI group compared with the non-AI group (0.15% [eight of 5238 participants] vs 0.0% [0 of 5238 participants], respectively; P = .008). The AI and non-AI groups showed similar false-referral rates (45.9% [56 of 122 participants] vs 56.0% [56 of 100 participants], respectively; P = .14) and positive-report rates (2.3% [122 of 5238 participants] vs 1.9% [100 of 5238 participants]; P = .14). Conclusion In health checkup participants, artificial intelligence-based software improved the detection of actionable lung nodules on chest radiographs. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Auffermann in this isssue.

To identify the impact of reconstruction algorithms on CT radiomic features of pulmonary tumors and to reveal and compare the intra- and inter-reader and inter-reconstruction algorithm variability of each feature. Forty-two patients (M:F = 19:23; mean age, 60.43±10.56 years) with 42 pulmonary tumors (22.56±8.51mm) underwent contrast-enhanced CT scans, which were reconstructed with filtered back projection and commercial iterative reconstruction algorithm (level 3 and 5). Two readers independently segmented the whole tumor volume. Fifteen radiomic features were extracted and compared among reconstruction algorithms. Intra- and inter-reader variability and inter-reconstruction algorithm variability were calculated using coefficients of variation (CVs) and then compared. Among the 15 features, 5 first-order tumor intensity features and 4 gray level co-occurrence matrix (GLCM)-based features showed significant differences (p<0.05) among reconstruction algorithms. As for the variability, effective diameter, sphericity, entropy, and GLCM entropy were the most robust features (CV≤5%). Inter-reader variability was larger than intra-reader or inter-reconstruction algorithm variability in 9 features. However, for entropy, homogeneity, and 4 GLCM-based features, inter-reconstruction algorithm variability was significantly greater than inter-reader variability (p<0.013). Most of the radiomic features were significantly affected by the reconstruction algorithms. Inter-reconstruction algorithm variability was greater than inter-reader variability for entropy, homogeneity, and GLCM-based features.