Chest Radiograph Interpretation with Deep Learning Models: Assessment with Radiologist-adjudicated Reference Standards and Population-adjusted Evaluation
The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Background Deep learning has the potential to augment the use of chest radiography in clinical radiology, but challenges include poor generalizability, spectrum bias, and difficulty comparing across studies. Purpose To develop and evaluate deep learning models for chest radiograph interpretation by using radiologist-adjudicated reference standards. Materials and Methods Deep learning models were developed to detect four findings (pneumothorax, opacity, nodule or mass, and fracture) on frontal chest radiographs. This retrospective study used two data sets. Data set 1 (DS1) consisted of 759 611 images from a multicity hospital network and ChestX-ray14 is a publicly available data set with 112 120 images. Natural language processing and expert review of a subset of images provided labels for 657 954 training images. Test sets consisted of 1818 and 1962 images from DS1 and ChestX-ray14, respectively. Reference standards were defined by radiologist-adjudicated image review. Performance was evaluated by area under the receiver operating characteristic curve analysis, sensitivity, specificity, and positive predictive value. Four radiologists reviewed test set images for performance comparison. Inverse probability weighting was applied to DS1 to account for positive radiograph enrichment and estimate population-level performance. Results In DS1, population-adjusted areas under the receiver operating characteristic curve for pneumothorax, nodule or mass, airspace opacity, and fracture were, respectively, 0.95 (95% confidence interval [CI]: 0.91, 0.99), 0.72 (95% CI: 0.66, 0.77), 0.91 (95% CI: 0.88, 0.93), and 0.86 (95% CI: 0.79, 0.92). With ChestX-ray14, areas under the receiver operating characteristic curve were 0.94 (95% CI: 0.93, 0.96), 0.91 (95% CI: 0.89, 0.93), 0.94 (95% CI: 0.93, 0.95), and 0.81 (95% CI: 0.75, 0.86), respectively. Conclusion Expert-level models for detecting clinically relevant chest radiograph findings were developed for this study by using adjudicated reference standards and with population-level performance estimation. Radiologist-adjudicated labels for 2412 ChestX-ray14 validation set images and 1962 test set images are provided. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Chang in this issue.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Only eight studies in ophthalmology imaging14,21,32,33,43,55,108,109, ten studies in respiratory imaging64,66,70,72,75,79,82,87,89,110 and six studies in breast imaging62,91,97,104,106,111 mentioned adherence to the STARD-2015 guidelines or had a STARD flow diagram in the manuscript.”
From Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis (2021) · cites this paper as [82]
Citations
Cites
Fleischner Society: Glossary of Terms for Thoracic Imaging
Hansell, D. M., Bankier, A. A., MacMahon, H., McLoud, T. C., Müller, N. L., & Remy, J. (2008) · Radiology · doi:10.1148/radiol.2462070712 · Cited by 4,198 · cited 1×
“Clinical definitions for these categories were on the basis of the Fleischner Society Glos-sary of Terms for Thoracic Imaging, except for osseous fracture, which was defined as visible rib, clavicle, humeral, or vertebral body fractures (20).”
MethodArmato, S. G., McLennan, G., Bidaut, L., McNitt‐Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., et al. (2011) · Medical Physics · doi:10.1118/1.3528204 · Cited by 2,887
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484 · cited 1×
“We used Xception (22) as the convolutional neural network architecture that was pretrained on 300 000 000 natural images (23).”
MethodRajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C. P., et al. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002686 · Cited by 1,449 · cited 2×
“Recent advances in deep learning offer promise for improving chest radiograph interpretation (1–4) and there are several recent reports of machine learning models achieving radiologist-level performance for different chest radiograph findings (5–7).”
BackgroundVery Deep Convolutional Networks for Text Classification
Conneau, A., Schwenk, H., Barrault, L., & Lecun, Y. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers · doi:10.18653/v1/e17-1104 · Cited by 1,046
Park, S. H., & Han, K. (2018) · Radiology · doi:10.1148/radiol.2017171920 · Cited by 894 · cited 1×
“However, because such data do not necessarily reflect real-world prevalence or diversity (33,34), such enrichment can also prevent meaningful clinical interpretation of diagnostic performance.”
BackgroundKrause, J., Gulshan, V., Rahimy, E., Karth, P., Widner, K., Corrado, G. S., Peng, L., & Webster, D. R. (2018) · Ophthalmology · doi:10.1016/j.ophtha.2018.01.034 · Cited by 564 · cited 1×
“…adjudicated labels, extensive work has been performed on the value of multiple interpretations in mammography (30) and other clinical settings (31,32). the most obviously positive and negative for pneumothorax, opacity, nodule or mass, or fracture for training, which can fail to address the…”
BackgroundSelf-citationMazurowski, M. A., Buda, M., Saha, A., & Bashir, M. R. (2019) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.26534 · Cited by 554 · cited 1×
“Recent advances in deep learning offer promise for improving chest radiograph interpretation (1–4) and there are several recent reports of machine learning models achieving radiologist-level performance for different chest radiograph findings (5–7).”
BackgroundNam, J. G., Park, S., Hwang, E. J., Lee, J. H., Jin, K.-N., Lim, K. Y., Vu, T. H., Sohn, J. H., Hwang, S., Goo, J. M., et al. (2019) · Radiology · doi:10.1148/radiol.2018180237 · Cited by 539 · cited 1×
“Recent advances in deep learning offer promise for improving chest radiograph interpretation (1–4) and there are several recent reports of machine learning models achieving radiologist-level performance for different chest radiograph findings (5–7).”
BackgroundMcBee, M. P., Awan, O. A., Colucci, A. T., Ghobadi, C. W., Kadom, N., Kansagra, A. P., Tridandapani, S., & Auffermann, W. F. (2018) · Academic Radiology · doi:10.1016/j.acra.2018.02.018 · Cited by 496
Research works printed but not linked: 3
- Auffermann WF, 2019, AJR Am J Roentgenol, 1
- Summers RM, NIH Chest X-ray Dataset of 14 Common Thorax Disease Categories
- Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, July 21–26, 2017. Piscataway, NJ: IEEE, 2017; 1800–1807.
Cited by
Items 201–300 of 337
Mosquera, C., Binder, F., Díaz, F. N., Seehaus, A., Ducrey, G., Ocantos, J., Aineseder, M., Rubin, L., Rabinovich, D., Quiroga, A. E., et al. (2021) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2021.100039 · Cited by 7
Understanding Dataset Bias in Medical Imaging: A Case Study on Chest X-rays
Dack, E., & Dai, C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00066 · Cited by 7
“There have been many different X-ray datasets released in the last few years [15, 36, 40].”
Analytical Review of Task Allocation Methods for Human and AI Model Collaboration
Ponomarev, A., & Agafonov, A. (2025) · Informatics and Automation · doi:10.15622/ia.24.1.9 · Cited by 6
Goyal, M., Austin-Strohbehn, J. A., Sun, S., Rodriguez, K., Sin, J. M., Cheung, Y. Y., & Hassanpour, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77211-6_35 · Cited by 6
Smart interpretable model (SIM) enabling subject matter experts in rule generation
Christianto, H., Lee, G. K. K., Jair, Z. W., Kasim, H., & Rajan, D. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117945 · Cited by 6
Label Noise-Robust Learning using a Confidence-Based Sieving Strategy
Torkzadehmahani, R., Nasirigerdeh, R., Rueckert, D., & Kaissis, G. A. (2023) · Transactions on machine learning research · doi:10.48550/arxiv.2210.05330 · Cited by 6
“In medical applications, for instance, there might be a disagreement between the labels assigned by radiology experts and those from the corresponding medical reports (Majkowska et al., 2020; Bernhardt et al., 2022), yielding datasets with noisy labels.”
BackgroundStatheros, J. M., Wang, H., & Klein, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.16700 · Cited by 6
“Even when classification performance matches radiologists (Rajpurkar et al., 2018; Majkowska et al., 2020), localization accuracy often lags behind (Saporta et al., 2022).”
Rep-GLS: Report-Guided Generalized Label Smoothing for Robust Disease DetectionPreprint
Zhang, K., Ge, F., Wang, B., Chen, Y., Kobayashi, K., Gu, L., Bi, J., & Zhu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.02495 · Cited by 6
“Clinical expert uncertainty represents a fundamental characteristic of radiological practice [3, 24].”
Wu, Y., Fong, S. J., & Yu, J. (2025) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-24-1745 · Cited by 5
“For example, in the work of Majkowska et al. (15), they proposed deep learning models for chest radiograph interpretations, along with their validations and evaluations using XAI techniques.”
Giri, L., Regmi, P. R., Gurung, G., Gurung, G., Aryal, S., Mandal, S., Giri, S., Chaulagain, S., Acharya, S., & Umair, M. (2025) · Diagnostics · doi:10.3390/diagnostics16010066 · Cited by 5
“…rarer conditions such as ILD, enlargement, and other lesions exhibited low sensitivity, reflecting limited training examples and the inherent difficulty of recognizing subtle or heterogeneous imaging patterns, consistent with prior reports (Majkowska 2020; Seyyed-Kalantari et al., 2021) [25,26].”
Pulmonary nodule detection in x-ray images by feature augmentation and context aggregation
Liu, C., Wu, Z., Wang, B., & Zhu, M. Q. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad2013 · Cited by 5
Deep learning prediction of survival in patients with heart failure using chest radiographs
Han, J., Liao, S., Zhu, X., Liu, W., Xu, Y., Ge, R., & Zhu, Y. (2024) · The International Journal of Cardiovascular Imaging · doi:10.1007/s10554-024-03177-w · Cited by 5
A Simple and Provable Approach for Learning on Noisy Labeled Medical Images
Wang, N., Di, Z., He, H., Jiang, Q., & Li, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681274 · Cited by 5
Hong, W., Hwang, E. J., Park, C. M., & Goo, J. M. (2023) · Korean Journal of Radiology · doi:10.3348/kjr.2023.0255 · Cited by 5
“Owing to its excellent performance in experimental studies [1-6], AI is increasingly used in daily practice [7-9].”
BackgroundA Causal Framework for Evaluating Deferring SystemsPreprint
Palomba, F., Pugnana, A., Álvarez, J. M., & Ruggieri, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.18902 · Cited by 6
“Regarding the real data, we consider four datasets used in the LtD literature: cifar10h (Battleday et al., 2020), a hard-labelled version of galaxyzoo (Astro-Dave et al., 2013), hatespeech (Davidson et al., 2017), and xray-airspace (Wang et al., 2017; Majkowska et al., 2020).”
Who Should Predict? Exact Algorithms For Learning to Defer to Humans
Mozannar, H., Lang, H., Wei, D., Sattigeri, P., Das, S., & Sontag, D. (2023) · arXiv · doi:10.48550/arxiv.2301.06197 · Cited by 4
“NIH Chest X-ray (Wang et al., 2017; Majkowska et al., 2020) 4k 2 4 (for different conditions) random annotator pretrained DenseNet121 on non-human labeled data”
BackgroundYang, Y. D., Yu, H., Xiang, Q., Wu, J., Li, J., Du, F., Yang, Y., & Wang, P. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03256-5 · Cited by 4
“Majkowska et al. utilized machine learning methods to automatically detect four abnormalities in X-ray images [33].”
Lin, F. C., Wei, C.-J., Bai, Z.-R., Chang, C., & Chiu, M. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad5e31 · Cited by 4
Rhee, C., Hong, K. J., Kim, K. H., Goo, J. M., & Hwang, E. J. (2025) · Korean Journal of Radiology · doi:10.3348/kjr.2025.0237 · Cited by 4
A Model for the Explainable Malignancy Assessment of Pulmonary Nodules on CT Images
Dumaev, R. I., Molodyakov, S. A., & Владимирович, У. Л. (2025) · Scientific and Technical Information Processing · doi:10.3103/s0147688225700637 · Cited by 4
Khan, H., Gupta, M., Bou-Akl, T. H., & Markel, D. C. (2022) · Spartan Medical Research Journal · doi:10.51894/001c.30158 · Cited by 4
Nkouanga, H. Y., & Vajda, S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412430 · Cited by 4
“This proves that without involving any feature selection, multiple features extraction, pre-trained model, and complex convolutional network [3], [14], [16] we could achieve comparable and even better results with the right selection of an enriched feature and a normal classifier such as Random Forest.”
BackgroundResultInfluentialThe FIX Benchmark: Extracting Features Interpretable to eXpertsPreprint
Jin, H., Havaldar, S., Kim, C., Xue, A., You, W., Qu, H., Gatti, M., Hashimoto, D. A., Jain, B., Madani, A., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.13684 · Cited by 4
“For text, we use BERTopic [Gro22] to obtain the clusters.”
BackgroundMethodCoverage-Constrained Human-AI Cooperation with Multiple ExpertsPreprint
Zhang, Z., Nguyen, C. C., Wells, K., Do, T.-T., Rosewarne, D., & Carneiro, G. (2024) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.48550/arxiv.2411.11976 · Cited by 4
Cho, H. S., Hwang, E. J., Yi, J., Choi, B., & Park, C. M. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.242835 · Cited by 3
AI-assisted Analysis to Facilitate Detection of Humeral Lesions on Chest Radiographs
Kim, H., Kim, K., Oh, S. J., Lee, S., Woo, J. H., Kim, J. H., Ki, Y., Kim, K., & Chung, M. J. (2024) · Radiology Artificial Intelligence · doi:10.1148/ryai.230094 · Cited by 3
Lee, S., Fox, S., Smith, R., Skrobarcek, K. A., Keyserling, H. F., Phares, C. R., Lee, D., & Posey, D. L. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000612 · Cited by 3
“Studies focusing on tuberculosis have ranged from the narrow evaluation of specific models (typically commercial) on relatively small test sets [25–26] to the development of original algorithms from custom largescale training sets [23,27–28].”
BackgroundMethodSelf-supervised Pretraining for Covid-19 and Other Pneumonia Detection from Chest X-ray Images
Hao, Y., Wang, Y., & Wang, X. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-89698-0_102 · Cited by 3
Pham, H., Nguyễn, N. H., Tran, T. T., Nguyen, T. N. M., & Nguyen, H. Q. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.10612 · Cited by 3
McKinney, S. M. (2022) · medRxiv · doi:10.1101/2022.05.06.22274773 · Cited by 3
“We have used this code in several published papers [2,3,14–16] and are pleased to share it with the broader research community.”
MethodSelf-citationAn Open Access Chest Datasets for Computer– Aided Screening of Chest Diseases
Soni, A., & Rai, A. (2024) · International Conference on Recent Innovation in Smart and Sustainable Technology (ICRISST) · doi:10.1109/icrisst59181.2024.10922046 · Cited by 2
Caturla, S. I., Mestre, J. D. D. B., & Mozos, Ó. M. (2025) · Future Internet · doi:10.3390/fi17070292 · Cited by 2
Early Tuberculosis Detection via Privacy-Preserving, Adaptive-Weighted Deep Models
Gasmi, K., Alanazi, A., Aoun, N. B., Altaieb, M. O., Abdalrahman, A. E. M., Hamid, O. H., Almenwer, S., Ammar, L. B., Yahyaoui, S., & Mrabet, M. (2026) · Diagnostics · doi:10.3390/diagnostics16020204 · Cited by 2
“Steiner et al. [25] investigated the use of deep learning (DL) for the identification of anomalies by employing DLAD (Deep Learning for Abnormality identification) models on chest radiographs.”
Wang, C.-H., Lin, P.-C., Shih, S. L., Tsai, P.-S., & Huang, W.-H. (2026) · Diagnostics · doi:10.3390/diagnostics16020232 · Cited by 2
“This architectural design facilitates explicit localization and visualization techniques, such as Grad-CAM or probability heat maps, which serve to highlight image regions that contribute to classification decisions [5,9,21].”
Cohen, E., Ouertani, M. S., Beaumel, P., Margetic, P., Pedowski, P., Pinatel, F. P., Violeau, M., Brader, P., Bajić, S., Malzy, P., et al. (2026) · Radiography · doi:10.1016/j.radi.2026.103361 · Cited by 2
Coverage-Constrained Human-AI Cooperation with Multiple Experts
Zhang, Z., Nguyen, C. C., Wells, K., Do, T.-T., Rosewarne, D., & Carneiro, G. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i21.38866 · Cited by 2
Haney-Aubert, C. M., Kovàcs, B., Aubert, O., Fattal, W., Mangold, M. H., Thiele, A., Winter, N., Kämpfert, K., Wessendorf, M. P., Brochhausen, C. B. C., et al. (2026) · JU Open Plus · doi:10.1097/ju9.0000000000000441 · Cited by 2
Arzamasov, K. M., Semenov, S. S., Kokina, D. Y., Bobrovskaya, T., Pavlov, N. A., Kirpichev, Y., Андрейченко, А. Е., & Vladzymyrskyy, A. V. (2023) · Meditsinskaya Fizika · doi:10.52775/1810-200x-2022-96-4-56-63 · Cited by 2
Ali, M. A. B. M., Abidin, M. R., Affendi, N. A. N. M., Abdullah, H., Rosman, D. R., Barud'din, N., Kemi, F., & Hayati, F. (2021) · IIUM Engineering Journal · doi:10.31436/iiumej.v22i2.1752 · Cited by 2
Unsupervised Chest X-ray Opacity Classification using Minimal Deep Features
Azemin, M. Z. C., Tamrin, M. I. M., Ali, M. A. M., & Jamaludin, I. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130332 · Cited by 2
“A total of 2,166 “airspace opacity” labels were obtained from previously published Google Health study [7].”
BackgroundMethodDetecting Multi Thoracic Diseases in Chest X-Ray Images Using Deep Learning Techniques
Quevedo, S., Domínguez, F., & Peláez, E. (2023) · International Conference on Pattern Recognition Systems (ICPRS) · doi:10.1109/icprs58416.2023.10179041 · Cited by 2
“[47].”
Data Appraisal Without Data SharingPreprint
Xu, M., van der Maaten, L. J. P., & Hannun, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06430 · Cited by 2
“Indeed, advances from cancer detection (Majkowska et al., 2020; Shen et al., 2019) to speech recognition (Amodei et al.”
BackgroundDoes Medical Imaging learn different Convolution Filters?Preprint
Gavrikov, P., & Keuper, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.13799 · Cited by 2
“The model trained on the Kaggle RSNA Pneumonia Challenge dataset seems to overrepresent specific coefficients (and therefore filters clusters) by a large amount, while the models trained on other datasets such as MIMIC-CXR [12], NIH [13, 14], and CheXpert [15] tend to learn coefficient distributions that are smoother…”
MethodHou, Z., Zhao, X., Ye, K., Jiang, S., Sheng, X., Xia, J., Luo, D., Zhang, Y., Ban, C., Chen, J., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-8259090/v1 · Cited by 2
Shuaibu, I., Khan, M., Alkhamis, D., & Alkhamis, A. (2026) · medRxiv · doi:10.64898/2026.01.17.26344327 · Cited by 2
FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language AssistantsPreprint
Bhosale, M., Wasi, A., Srivastava, S., Latif, S., Luan, T., Gao, M., Doermann, D., & Gong, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.26008 · Cited by 2
“S4, TorchXRayVision [12] demographic predictors, trained on CheXpert [20] and NIH ChestX-ray14 [32], achieve high AUC and low age MAE (in years) in our evaluation on both MIMIC-CXR and PadChest datasets.”
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical AgentsPreprint
Gan, Y., Pan, T., Guo, K., Han, L., Yu, W., Ye, G., Jiang, C., & Cheng, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.26691 · Cited by 2
“…on six test benchmarks: their held-out test splits, three stratified 1 , 000 -image out-of-domain samples from NIH ChestX-ray14 [36], RSNA Pneumonia Detection [33], and VinDr-CXR [21], plus NIH-Google [19] ( 1 , 962 radiologist-adjudicated images) as a clean-label check against NIH NLP label noise.”
Detecção de tumores cerebrais utilizando redes neurais convolucionais guiadas por mapas de saliência
Oliveira, P. H. D. C. (2022) · RIUnB Institutional Repository (University of Brasília) · doi:10.26512/2022.10.d.45968 · Cited by 2
Quality assurance of paediatric lateral chest radiographs
Tsitsiou, Y., Rajkumar, L., Hlabangana, L. T., Naidoo, J., Clark, L. M., Zar, H. J., & Andronikou, S. (2022) · Journal of medical imaging and radiation sciences · doi:10.1016/j.jmir.2022.08.004 · Cited by 1
The Role of Artificial Intelligence in Medicine Applications
Betti, A. A. (2023) · Journal of Al-Qadisiyah for Computer Science and Mathematics · doi:10.29304/jqcm.2023.15.1.1163 · Cited by 1
Pediatric chest X-ray diagnosis using neuromorphic models
Bokhari, S. M., Sohaib, S., & Shafi, M. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110173 · Cited by 1
Empowering Patient Wellness: Automated Radiology Report Generation Using Deep Learning and NLG
Mishra, A., Nauhwar, H., & Jindal, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93982-2_19 · Cited by 1
Lee, G., Cho, H.-H., Jeong, D. Y., Kim, J., Oh, Y. J., Park, S. G., & Lee, H. Y. (2025) · Journal of Thoracic Imaging · doi:10.1097/rti.0000000000000866 · Cited by 1
Bamatraf, M., Alsolami, F., & Saleh, M. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425400087 · Cited by 1
Bundza, P., & Trinkūnas, J. (2026) · Diagnostics · doi:10.3390/diagnostics16040585 · Cited by 1
Visualization methods for explainable medical imaging diagnosis: A survey
Yang, L., Liu, Y., He, L., & Hu, D. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100930 · Cited by 1
Self-citationRecent advances in artificial intelligence across interventional pulmonology: a narrative review
RIZLY, S., Saleh, A., Keshava, K., Reisman, N., Peterson, S. J., Ayuda, J. M., & Weingarten, J. A. (2026) · Journal of Thoracic Disease · doi:10.21037/jtd-2026-1-0204 · Cited by 1
“However, these performances are not consistently reproducible in clinical settings, where external validation studies show marked heterogeneity (39).”
PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling
Lin, Y.-J., Lo, T.-C., Li, P.-C., Cheng, C.-T., Liao, C.-H., & Kao, H. (2026) · doi:10.18653/v1/2026.bionlp-1.20 · Cited by 1
“Machine learning approaches, including CNN-based (Majkowska et al., 2020; Shin et al., 2017) and LSTM-based methods (Dahl et al., 2021; D’Anniballe et al., 2022), have also been explored for report labeling but require large amounts of labeled data.”
Lemke, T., Marka, A. W., Prucker, P., Komenda, A., Weller, D., Mertens, C. J., Kim, S. H., Lammert, J., Huber, T., Graf, M. M., et al. (2026) · Academic Radiology · doi:10.1016/j.acra.2026.08.014 · Cited by 1
Oliveira, B. A. S., Ziviani, H. E., Oliveira, J. J., Viegas, A. M., & Calvo, D. (2021) · Congresso Brasileiro de Inteligência Computacional (CBIC) · doi:10.21528/cbic2021-14 · Cited by 1
Rastogi, A., Sati, A., Abhilash, N., Ahuja, G., Srinivasan, T., & Jain, C. (2022) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme55909.2022.9988570 · Cited by 1
Saidulu, D., & Sasikala, R. (2023) · Soft Computing · doi:10.1007/s00500-023-08282-x · Cited by 1
RetractedWolf, A. L., Hennrich, J., & Buck, C. (2024) · Springer eBooks · doi:10.1007/978-3-658-43860-9_34 · Cited by 1
Implementation Of Convolutional Neural Network For Cardiomegaly Image Classification
Rizalde, A. R., Mustakim, M., Novita, R., & Saputra, E. (2025) · International Conference on Computer Sciences, Engineering, and Technology Innovation (ICoCSETI) · doi:10.1109/icocseti63724.2025.11020118 · Cited by 1
“Although chest X-ray is a commonly used diagnostic tool, interpretation of X-ray images often requires high radiology expertise and can be inherently subjective, so there is a risk of inaccurate diagnosis [7].”
A Complementarity-Enhanced Mixture of Human-AI Teams for Decision-Making
Liang, H., Liu, J., Guo, B., & Yu, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05981-9_17 · Cited by 1
Pneumothorax and chest tube classification on chest x-rays for detection of missed pneumothoraxPreprint
Graf, B. W., Sitek, A., Katouzian, A., Lu, Y.-F., Krishnan, A. V., Rafael, J., Small, K. M. S., & Xie, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.07353 · Cited by 1
Prediction of COVID-19 using chest X-ray imagesPreprint
Darapaneni, N., Maram, S., Singh, H., Subhani, S., Kour, M., Nagam, S., & Paduri, A. R. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.03849 · Cited by 1
“In recent research [11], radiologist-adjudicated labels for the lung X-ray 14 data set [4] were created.”
BackgroundResultXu, Q., Li, Y., Zhan, X., Zhao, Z., Xu, C., Er, A. G., Zhan, X., Dashevsky, B. Z., Alawad, M., von der Stück, M., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.16027 · Cited by 1
Self-citationRamli, P. N. M., & Aizuddin, A. N. (2026) · Diagnostics · doi:10.3390/diagnostics16020209 · Cited by 1
Wei, Y., Flanders, A. E., Colak, E., Mongan, J., Prevedello, L. M. S., Chen, P.-H., Lee, H. M. H., Szarf, G., Shoji, H., Sho, J., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.15129 · Cited by 1
“Second, past annotation efforts typically involved only a small number of radiologists rather than a broader pool of experts, reducing representativeness and increasing the potential for individual biases in the labeling process [6].”
Kovàcs, B. (2026) · heiDOK (Heidelberg University) · doi:10.11588/heidok.00037869 · Cited by 1
Fytas, P., Selby, I., Karner, C., Babar, J. L., Baker, S., Beckford, J., Sadler, T. J., Shahipasand, S., Thavakumar, A., Chen, J. L., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.26333 · Cited by 1
Baclic, O., Tunis, M. C., Young, K., Doan, C., & Swerdfeger, H. (2020) · Relevé des maladies transmissibles au Canada · doi:10.14745/ccdr.v46i06a02f
Mashhaditafreshi, N., Tariq, A., Gichoya, J. W., & Banerjee, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05786
“DCNNs have achieved expert-level performance for various chest pathologies 3,4 .”
Rado, Y. (2021) · Future of business and finance · doi:10.1007/978-3-030-65896-0_9
Exploring Classification Models for COVID-19 Novel Coronavirus Disease
Suneja, R. (2022) · Lecture notes in mechanical engineering · doi:10.1007/978-981-16-7909-4_68
Comparison of Deep Learning Architectures for CXR Opacity Detection
Roslan, S. N. R. B., Azemin, M. Z. C., Ali, M. A. M., Tamrin, M. I. M., & Jamaludin, I. (2022) · International Conference on Software and Computer Applications (ICSCA) · doi:10.1145/3524304.3524316
“This research is the continuation of the previous study [6] but the difference in this study comprises of various models development, and performance comparison of different deep learning convolutional neural network architectures.”
MethodBoullier, D. (2022) · Wiley eBooks · doi:10.1002/9781394163908.ch7
The Deep Learning-Based Framework for Automated Predicting COVID-19 Severity Score
Zheng, Y., & Dong, H. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.09.165
“Literature [18-24] gather 88079 CXRs of pulmonary illnesses, none of which contain COVID-19 cases.”
Location Fusion and Data Augmentation for Thoracic Abnormalites Detection in Chest X-Ray Images
Anh, N.-T. V., Dung, N. D., & Thuy, N. T. P. (2023) · Research and Development on Information and Communication Technology · doi:10.32913/mic-ict-research.v2023.n1.1172
A Lightweight AMResNet Architecture with an Attention Mechanism for Diagnosing COVID-19
Zhou, Q. H., Kowah, J. A. H., Li, H., Yuan, M., Jiang, L., & Liu, X. (2023) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405620666230426121437
Image Classification of Covid Chest X-Rays using a Game Theoretical Approach
Jain, V., Nagpal, S., Aggarwal, A., & Gupta, T. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10306909
Noisy-label problems and datasets
Carneiro, G. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-315441-6.00011-3
Benchmarks, methods, results, and code
Carneiro, G. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-315441-6.00014-9
(2024) · Elsevier eBooks · doi:10.1016/b978-0-44-315441-6.00016-2
Deep Learning for Clinical Practice.
Sogancioglu, E. (2024) · Radboud University Press eBooks · doi:10.54195/9789493296770
A Comparative Assessment of Transfer Learning Approaches in Pneumonia Detection
Kumar, K. C. S., & Shakya, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-7532-3_24
Semi-supervised Learning to Defer Algorithm for Lung Disease Diagnosis
Chen, H., Jin, B., & Wang, X. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825864 · Cited by 1
Gtifa, W., Fradi, M., Sakly, A., & Machhout, M. (2025) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.70044
“To evaluate the effectiveness of the segmentation method on COVID‐19 CT images, we utilise a dataset sourced from various datasets, including CheX (also known as CheXpert) [21], OpenI [22], Google [23], PC (PadChest) [24], and MIMIC‐CXR [25], as provided in [26].”
Upputuri, V. (2025) · INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY · doi:10.34218/ijcet_16_01_145
Vocal Course Quality Evaluation Model Using Hybrid Neural Networks and Meta-Learning Optimization
Lu, L., & Xu, M. (2025) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625503694
Exploring Deep Learning Architectures in Clinical PracticePreprint
Kim, M., Park, J., Lee, S., Choi, H., Kang, S., Han, Y., Shin, D., & Jung, G. (2025) · doi:10.36227/techrxiv.175606171.14396791/v1
(2025) · International Workshop on Computer Science and Engineering (WCSE) · doi:10.18178/wcse.2025.06.032
Rajesh, C., Chintakindi, B. M., Rampavan, M., & Arukonda, S. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-2038-0.ch013
Deep Learning-Driven Medical Image Captioning with eXplainable AI
Kushwah, V. R. S., & Shrivastava, A. K. (2025) · Advances in computer science research · doi:10.2991/978-94-6463-858-5_8
Using Relative Risk Rankings to Understand Information Differences in Multimodal Prediction ModelsPreprint
Kim, C., Yoon, W., Lee, H., Lee, J.-O., Afshar, M., Kang, J., & Miller, T. A. (2025) · medRxiv · doi:10.1101/2025.10.30.25339162
Andersson, P., Johnsson, J., Björnsson, O., Cronberg, T., Hassager, C., Zetterberg, H., Stammet, P., Undén, J., Kjaergaard, J., Friberg, H., et al. (2021) · Figshare · doi:10.6084/m9.figshare.14121644
Andersson, P., Johnsson, J., Björnsson, O., Cronberg, T., Hassager, C., Zetterberg, H., Stammet, P., Undén, J., Kjaergaard, J., Friberg, H., et al. (2021) · Figshare · doi:10.6084/m9.figshare.14121641
Hofmeister, J., Garin, N., Montet, X., Scheffler, M., Platon, A., Poletti, P.-A., Stirnemann, J., Debray, M., Claessens, Y.-É., Duval, X., et al. (2024) · Figshare · doi:10.6084/m9.figshare.26675777
Andersson, P., Johnsson, J., Björnsson, O., Cronberg, T., Hassager, C., Zetterberg, H., Stammet, P., Undén, J., Kjaergaard, J., Friberg, H., et al. (2021) · Figshare · doi:10.6084/m9.figshare.14121659
Metadata
- Authors
- Majkowska, A., Mittal, S., Steiner, D. F., Reicher, J. J., McKinney, S. M., Duggan, G. E., Eswaran, K., Cameron Chen, P.-H., Liu, Y., Kalidindi, S. R., Ding, A., Corrado, G. S., Tse, D., & Shetty, S.
- Affiliations
- Stanford Health Care (US)
- From Google Health, 1600 Amphitheatre Pkwy, Mountain View, CA 94043 (A.M., S.M., D.F.S., S.M.M., G.E.D., K.E., P.H.C.C., Y.L., G.S.C., D.T., S.S.); Stanford Healthcare and Palo Alto Veterans Affairs, Palo Alto, Calif (J.J.R.); Apollo Radiology International, Hyderabad, India (S.R.K.); and California Advanced Imaging, Novato, Calif (A.D.).
- ORCID
- Venue
- Radiology
- Published
- 2020-02
- Volume
- 294
- Issue
- 2
- Pages
- 421-431
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2991676991
- Cited by
- 277
- References
- 30
- Citations by year
- 2026: 21 · 2025: 37 · 2024: 36 · 2023: 48 · 2022: 48 · 2021: 52 · 2020: 34
- FWCI
- 22.28
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- chest X-ray interpretation, deep learning, pneumothorax detection, lung nodule detection, lung opacity, rib fracture detection, inverse probability weighting, spectrum bias, generalizability, ChestX-ray14, positive predictive value, sensitivity and specificity
- MeSH terms
- Radiologists, Deep Learning, Adolescent, Adult, Aged, Aged, 80 and over, Child, Child, Preschool, Female, Humans, Infant, Male, Middle Aged, Pneumothorax, Radiographic Image Interpretation, Computer-Assisted, Reference Standards, Respiratory Tract Diseases, Retrospective Studies, Sensitivity and Specificity, Thoracic Injuries, Radiography, Thoracic, Reproducibility of Results, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.