Deep Convolutional Neural Network–based Software Improves Radiologist Detection of Malignant Lung Nodules on Chest Radiographs
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Background Multicenter studies are required to validate the added benefit of using deep convolutional neural network (DCNN) software for detecting malignant pulmonary nodules on chest radiographs. Purpose To compare the performance of radiologists in detecting malignant pulmonary nodules on chest radiographs when assisted by deep learning–based DCNN software with that of radiologists or DCNN software alone in a multicenter setting. Materials and Methods Investigators at four medical centers retrospectively identified 600 lung cancer–containing chest radiographs and 200 normal chest radiographs. Each radiograph with a lung cancer had at least one malignant nodule confirmed by CT and pathologic examination. Twelve radiologists from the four centers independently analyzed the chest radiographs and marked regions of interest. Commercially available deep learning–based computer-aided detection software separately trained, tested, and validated with 19 330 radiographs was used to find suspicious nodules. The radiologists then reviewed the images with the assistance of DCNN software. The sensitivity and number of false-positive findings per image of DCNN software, radiologists alone, and radiologists with the use of DCNN software were analyzed by using logistic regression and Poisson regression. Results The average sensitivity of radiologists improved (from 65.1% [1375 of 2112; 95% confidence interval {CI}: 62.0%, 68.1%] to 70.3% [1484 of 2112; 95% CI: 67.2%, 73.1%], P < .001) and the number of false-positive findings per radiograph declined (from 0.2 [488 of 2400; 95% CI: 0.18, 0.22] to 0.18 [422 of 2400; 95% CI: 0.16, 0.2], P < .001) when the radiologists re-reviewed radiographs with the DCNN software. For the 12 radiologists in this study, 104 of 2400 radiographs were positively changed (from false-negative to true-positive or from false-positive to true-negative) using the DCNN, while 56 of 2400 radiographs were changed negatively. Conclusion Radiologists had better performance with deep convolutional network software for the detection of malignant pulmonary nodules on chest radiographs than without. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Jacobson 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
“13 (refs. 63–75) studies validated algorithms on external data”
From Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis (2021) · cites this paper as [72]
In the citing paper
“Twenty-one54,63–67,70,72,76–88 studies compared algorithm performance against healthcare professionals.”
From Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis (2021) · cites this paper as [72]
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 [72]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening
The National Lung Screening Trial Research Team (2011) · New England Journal of Medicine · doi:10.1056/nejmoa1102873 · Cited by 11,064
Lakhani, P., & Sundaram, B. (2017) · Radiology · doi:10.1148/radiol.2017162326 · Cited by 1,775
Park, S. H., & Han, K. (2018) · Radiology · doi:10.1148/radiol.2017171920 · Cited by 894
Self-citationNam, 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
Austin, J. H., Romney, B. M., & Goldsmith, L. S. (1992) · Radiology · doi:10.1148/radiology.182.1.1727272 · Cited by 266
Shah, P. K., Austin, J. H. M., White, C. S., Patel, P., Haramati, L. B., Pearson, G. D. N., Shiau, M. C., & Berkmen, Y. M. (2003) · Radiology · doi:10.1148/radiol.2261011924 · Cited by 198
Missed lung cancer: when, where, and why?
Ciello, A. D., Franchi, P., Contegiacomo, A., Cicchetti, G., Bonomo, L., & Larici, A. R. (2017) · Diagnostic and Interventional Radiology · doi:10.5152/dir.2016.16187 · Cited by 187
Mechanism of satisfaction of search: eye position recordings in the reading of chest radiographs.
Samuel, S., Kundel, H. L., Nodine, C. F., & Toto, L. C. (1995) · Radiology · doi:10.1148/radiology.194.3.7862998 · Cited by 168
Kakeda, S., Moriya, J., Sato, H., Aoki, T., Watanabe, H., Nakata, H., Oda, N., Katsuragawa, S., Yamamoto, K., & Doi, K. (2004) · American Journal of Roentgenology · doi:10.2214/ajr.182.2.1820505 · Cited by 141
Research works printed but not linked: 1
- Hwang S, 2016, Proceedings of SPIE: medical imaging 2016—computer-aided diagnosis. Vol 9785, 97852W
Cited by
Items 101–200 of 248
AI detection of mild COVID-19 pneumonia from chest CT scans
Yao, J.-C., Wang, T., Hou, G.-H., Ou, D., Li, W., Zhu, Q.-D., Chen, W.-C., Yang, C., Wang, L., Wang, L.-P., et al. (2021) · European Radiology · doi:10.1007/s00330-021-07797-x · Cited by 20
Choi, S. Y., Park, S., Kim, M., Park, J., Choi, Y. R., & Jin, K. N. (2021) · Medicine · doi:10.1097/md.0000000000025663 · Cited by 27
Self-citationLee, J. H., Hwang, E. J., Kim, H., & Park, C. M. (2022) · Translational Lung Cancer Research · doi:10.21037/tlcr-21-1012 · Cited by 25
Self-citationWang, H., & Xia, Y. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104488 · Cited by 20
Maiter, A., Hocking, K., Matthews, S., Taylor, J. C., Sharkey, M. J., Metherall, P., Alabed, S., Dwivedi, K., Shahin, Y., Anderson, E., et al. (2023) · BMJ Open · doi:10.1136/bmjopen-2023-077348 · Cited by 24
“CSJ is the guarantor.”
Peters, A. A., Decasper, A., Munz, J., Klaus, J. B., Loebelenz, L. I., Hoffner, M. K. M., Hourscht, C., Heverhagen, J. T., Christe, A., & Ebner, L. (2021) · Journal of Thoracic Disease · doi:10.21037/jtd-20-3522 · Cited by 23
“had average nodule sizes of 41±26 mm in center 1 and 34±18 mm in center 2 (20,22).”
BackgroundRib fracture detection in computed tomography images using deep convolutional neural networks
Kaiume, M., Suzuki, S., Yasaka, K., Sugawara, H., Shen, Y., Katada, Y., Ishikawa, T., Fukui, R., & Abe, O. (2021) · Medicine · doi:10.1097/md.0000000000026024 · Cited by 20
A systematic approach to deep learning-based nodule detection in chest radiographs
Behrendt, F., Bengs, M., Bhattacharya, D., Krüger, J., Opfer, R., & Schlaefer, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-37270-2 · Cited by 26
“Therefore, radiologists would need to carefully review the results of CAD systems, as also noted in clinical validation studies of commercial systems 32,34,74 .”
BackgroundChassagnon, G., Billet, N., Rutten, C., Toussaint, T., de Linval, Q. C., Collin, M., Lemouchi, L., Homps, M., Hedjoudje, M., Ventre, J., et al. (2023) · European Radiology · doi:10.1007/s00330-023-10043-1 · Cited by 19
“…available CADe system as a second reader for lung nodule detection on CXRs, Sim et al showed that the mean sensitivity of radiologists improved significantly from 65.1 to 70.3% ( p 0.001), and the number of false positives per radiograph decreased significantly from 0.20 to 0.18 ( p 0.001) [6].”
BackgroundInfluentialLiu, B., Ye, X., Fan, W., Zhi, X., Ma, H., Wang, J., Wang, P., Wang, Z. M., Wang, H., Wang, X., et al. (2024) · Journal of Cancer Research and Therapeutics · doi:10.4103/jcrt.jcrt_563_24 · Cited by 21
Fanni, S. C., Marcucci, A., Volpi, F., Valentino, S., Neri, E., & Romei, C. (2023) · Diagnostics · doi:10.3390/diagnostics13122020 · Cited by 25
SHARMA, R. N., Kumar, N., & Sharma, V. (2025) · Wiley eBooks · doi:10.1002/9781394278695.ch4 · Cited by 20
Koo, Y. H., Shin, K. E., Park, J. S., Lee, J. W., Byun, S., & Lee, H. (2020) · Journal of Medical Imaging and Radiation Oncology · doi:10.1111/1754-9485.13105 · Cited by 17
“9,14 Extra validation studies have found that DCNNs detect pulmonary nodules well when examining data acquired at different times in various institutions, 6,17 but the ef fi cacy of commercially available software in various clinical settings has not yet been widely reported.”
BackgroundUnsupervised Detection of Lung Nodules in Chest Radiography Using Generative Adversarial Networks
Bhatt, N., Prados, D. R., Hodzic, N., Karanassios, C., & Tizhoosh, H. R. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630340 · Cited by 19
Chen, F., Zhou, Y., Qi, X., Zhang, R., Gao, X., Xia, W., & Zhang, L. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2020.523543 · Cited by 16
“Similar findings have been reported in recent deeplearning-assisted diagnosis studies (29, 30).”
ResultA narrative review of the clinical approach to subsolid pulmonary nodules
Kim, B., & Um, S. (2023) · Annals of Translational Medicine · doi:10.21037/atm-22-5246 · Cited by 21
“Many deep learning algorithms showed high sensitivity (around 70–91%), and all physicians showed improvement in lung nodule detection performance with the assistance of these algorithms (87,88).”
BackgroundMachine Learning in Diagnosis and Prognosis of Lung Cancer by PET-CT
Yuan, L., An, L. K., Zhu, Y., Duan, C., Kong, W., Jiang, P., & Yu, Q. (2024) · Cancer Management and Research · doi:10.2147/cmar.s451871 · Cited by 16
“Therefore, the ML method has been used by many scholars 55 for the early recognition of carcinoma of the lungs.”
Methodde Camargo, T. F. O., Ribeiro, G., da Silva, M. C. B., da Silva, L. O., Torres, P. P. T. E. S., Silva, D. D., de Santos, M. O. N., Salibe-Filho, W., Rosa, M. E. E., Novaes, M. D. A., et al. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1512910 · Cited by 16
Nam, J. G., Kim, H. J., Lee, E. H., Hong, W., Park, J., Hwang, E. J., Park, C. M., & Goo, J. M. (2021) · European Radiology · doi:10.1007/s00330-021-08162-8 · Cited by 15
Self-citationMahboub, B. H., Tadepalli, M., Raj, T., Santhanakrishnan, R., Hachim, M. Y., Bastaki, U. M. H. A., Hamoudi, R., Haider, E. A., & Alabousi, A. (2022) · Advances in Biomedical and Health Sciences · doi:10.4103/abhs.abhs_17_22 · Cited by 17
Takamatsu, A., Ueno, M., Yoshida, K., Kobayashi, T., Kobayashi, S., & Gabata, T. (2023) · Japanese Journal of Radiology · doi:10.1007/s11604-023-01503-1 · Cited by 18
“Compared with manual reading, CAD-assisted interpretation improves the detect-ability of nodules without increasing the false-positive rate on chest radiographs [9, 10].”
MethodResultInfluentialZhu, H., Tao, G., Jiang, Y., Sun, L., Chen, J., Guo, J., Wang, N., Wei, H., Liu, X., Chen, Y., et al. (2024) · European Journal of Radiology · doi:10.1016/j.ejrad.2024.111586 · Cited by 15
A deep learning approach for anterior cruciate ligament rupture localization on knee MR images
Qu, C., Yang, H., Wang, C., Wang, C., Ying, M., Chen, Z., Yang, K., Zhang, J., Li, K., Dimitriou, D., et al. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2022.1024527 · Cited by 14
Kim, H., Lee, K. H., Han, K., Lee, J. W., Kim, J. Y., Im, D. J., Hong, Y. J., Choi, B. W., & Hur, J. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2022.53820 · Cited by 18
Self-citationThe Use of Artificial Intelligence for the Classification of Craniofacial Deformities
Kuehle, R., Ringwald, F. G., Bouffleur, F., Hagen, N., Schaufelberger, M., Nahm, W., Hoffmann, J., Freudlsperger, C., Engel, M., & Eisenmann, U. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12227082 · Cited by 16
“Recognizing the efficacy of convolutional neural networks (CNNs) and deep learning (DL) in medical image analysis, particularly in radiology [27,28], we aim to leverage these technologies for classifying pathological growth patterns in craniosynostosis.”
Cai, P., Yang, T. H., Xie, Q., Liu, P., & Li, P. (2024) · Journal of Clinical Ultrasound · doi:10.1002/jcu.23703 · Cited by 15
“8 To address these challenges, we have integrated artificial intelligence (AI) technology with UF image data to develop a model that meets clinical requirements, utilizing deep learning algorithms to overcome medical obstacles.”
Huh, J. E., Lee, J. H., Hwang, E. J., & Park, C. M. (2023) · Korean Journal of Radiology · doi:10.3348/kjr.2022.0548 · Cited by 15
Posner, K. M., Bakus, C., Basralian, G., Chester, G., Zeiman, M., O’Malley, G. R., & Klein, G. R. (2024) · Cureus · doi:10.7759/cureus.55945 · Cited by 18
“Despite other AI models having successfully been utilized to interpret images in the fields of radiology, pathology, and gastroenterology this study did not exhibit the same success with ChatGPT [27,28].”
ResultDeng, Z., Song, D., & 上山, 瑠. (2025) · Decision Support Systems · doi:10.1016/j.dss.2025.114512 · Cited by 12
Wang, Q., Xu, S., Zhang, G., Zhang, X., Gu, J., Yang, S., Zeng, M., & Zhang, Z. (2022) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.13759 · Cited by 14
“10 Computed tomography (CT) is a widely used diagnostic imaging modality in oncology, and CT images are one type of the most commonly adopted data sources in current texture analysis studies.”
MethodSelf-citationMachine Learning for Hepatocellular Carcinoma Segmentation at MRI:RadiologyIn Training
Raman, A. G., Jones, C. K., & Weiss, C. R. (2022) · Radiology · doi:10.1148/radiol.212386 · Cited by 13
Artificial intelligence-assisted point-of-care devices for lung cancer
Ng, X. J. K., Khairuddin, A. S. M., Liu, H. L., Loh, T. C., Tan, J. L., Khor, S. M., & Leo, B. F. (2025) · Clinica Chimica Acta · doi:10.1016/j.cca.2025.120191 · Cited by 13
Krishnakumar, K., Gurrapu, O., Reshma, P., Krishnammal, P. M., Khan, H. Q., & Amane, N. (2025) · International Conference on Computing for Sustainability and Intelligent Future (COMP-SIF) · doi:10.1109/comp-sif65618.2025.10969915 · Cited by 11
“Preventing the aggravation of severe illnesses and the need for their early diagnosis using artificial intelligence technologies are an important accomplishment[15].”
Ibrahim, S. F., Osman, A., Awadallah, S. M., & Abdelrahman, A. S. (2023) · The Egyptian Journal of Radiology and Nuclear Medicine · doi:10.1186/s43055-023-01093-y · Cited by 12
“…for lesion detection which showed improvement in radiolo-gists’ sensitivity from 78.13% to 88.75% for nodule/mass and the study of Sim et al. [10] who revealed an increase in the sensitivity of radiologists from 65.1 to 70.3% with a decline in the number of false-positive findings (from 0.2…”
BackgroundInfluentialXue, P., Si, M., Qin, D., Wei, B., Seery, S., Ye, Z., Chen, M., Wang, S., Song, C., Zhang, B., et al. (2023) · Journal of Medical Internet Research · doi:10.2196/43832 · Cited by 15
Kvak, D., Chromcová, A., Hrubý, R., Janů, E., Biros, M., Pajdaković, M., Kvaková, K., Al–antari, M. A., Polaskova, P., & Strukov, S. (2023) · Diagnostics · doi:10.3390/diagnostics13061043 · Cited by 13
“[25] evaluated the effectiveness of commercial DLAD (Samsung Electronics Auto Lung Nodule Detection) in improving the detection of pulmonary lesions on CXRs by radiologists.”
BackgroundMethodFrom Pixels to Pathology: Employing Computer Vision to Decode Chest Diseases in Medical Images
Arslan, M., Haider, A., Khurshid, M., Bakar, S. S. U. A., Jani, R., Masood, F., Tahir, T., Mitchell, K., Panchagnula, S. V., & Mandair, S. (2023) · Cureus · doi:10.7759/cureus.45587 · Cited by 12
“Notably, multi-center research has revealed that radiologists aided by DL-based convolutional neural network (CNN) systems demonstrated an improvement of over 5% in sensitivity (SEN) when identifying malignant lung nodules, compared to radiologists not using such systems [29].”
BackgroundHamanaka, R., & Oda, M. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14020164 · Cited by 11
“…improved from 65.1% to 70.3% and the number of false-positive findings per radiograph declined from 0.2 to 0.18 when the radiologists re-reviewed radiographs using the deep CNN software Samsung Auto Lung Nodule Detection (ALHD, version 1.00; Samsung Electronics, Suwon, South Korea) [7].”
BackgroundMethodInfluentialLi, Y., Wang, T., Fu, Y., & Shi, Y. (2020) · The Clinical Respiratory Journal · doi:10.1111/crj.13258 · Cited by 10
Park, Y. W., Eom, S., Kim, S., Lim, S., Park, J. E., Kim, H. S., You, S. C., Ahn, S. S., & Lee, S. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108288 · Cited by 12
Self-citationVladzymyrskyy, A. V., Kudryavtsev, N. D., Kozhikhina, D. D., Михайлович, Ш. И., Morozov, S. P., Ledikhova, N. V., Klyashtornyy, V. G., Goncharova, I. V., Novikov, A. V., & Vnukova, O. M. (2022) · Russian Journal of Preventive Medicine · doi:10.17116/profmed2022250717 · Cited by 10
Recognizing Edge-Based Diseases of Vocal Cords by Using Convolutional Neural Networks
Tsung, C.-K., & Tso, Y.-A. (2022) · IEEE Access · doi:10.1109/access.2022.3221457 · Cited by 10
“For example, nodules [25], [26], [27] and polyps [28], [29], [30] are common VC diseases that affect an individual’s voice.”
BackgroundNuutinen, M., & Leskelä, R. (2023) · Health and Technology · doi:10.1007/s12553-023-00763-1 · Cited by 12
“In that study and also in the studies [1–3, 26, 29, 31, 34, 45, 52], GT method was both majority vote and high expertise.”
BackgroundMethodInfluentialKoyyada, S. P., & Singh, T. P. (2024) · SN Computer Science · doi:10.1007/s42979-023-02573-8 · Cited by 16
“DB, on the other hand, consists of 50 non-TB CXRs and 50 TB CXRs, and the test set is 25 non-TB and 25 TB CXRs. [134] Two radiologists collected Chest X-rays at each center (BWC, with 19 years of experience in chest radiology, MJC, 18 years of experience, and six chest radiologists with more than…”
Alilou, M., Prasanna, P., Bera, K., Gupta, A. B., Rajiah, P. S., Yang, M., Jacono, F. J., Velcheti, V., Gilkeson, R., Linden, P. A., et al. (2021) · Cancers · doi:10.3390/cancers13112781 · Cited by 8
“Multiple papers [24–26] have already explored the potential of deep networks for detecting and segmenting the pulmonary nodules on CT scans [27], and there is a growing interest in the use of these models for diagnosis and classification of lung nodules on CT scans [22,23,28].”
BackgroundGhosh, T., Tanwar, S., Chumber, S., & Vani, K. (2021) · The Egyptian Journal of Radiology and Nuclear Medicine · doi:10.1186/s43055-021-00499-w · Cited by 8
“While there has been considerable interest in the application of convolutional neural networks and other forms of machine learning for classification of chest radio-graphs into various pathologies, the underlying technology utilized in all these studies remain exclusionary [5, 24 – 26].”
BackgroundWallner, C., Alam, M., Drysch, M., Wagner, J. M., Sogorski, A., Dadras, M., von Glinski, M., Reinkemeier, F., Becerikli, M., Heute, C., et al. (2021) · Cancers · doi:10.3390/cancers13194961 · Cited by 8
“These applications display better detection rates than a radiological-medical assessment alone [16].”
BackgroundÇoşkun, N., Yalçınkaya, M., & Demir, E. (2024) · Journal of Pediatric Surgery · doi:10.1016/j.jpedsurg.2024.162014 · Cited by 7
The impact of AI feedback on the accuracy of diagnosis, decision switching and trust in radiography
Rainey, C., Bond, R., McConnell, J., Gill, A., Hughes, C., Kumar, D., & McFadden, S. L. (2025) · PLoS ONE · doi:10.1371/journal.pone.0322051 · Cited by 10
“Since then, other findings have been published evidencing the impressive performance of CNNs for pathology detection in comparison to, and in conjunction with, human experts [11,15–17].”
Duncan, S. F., Kidd, A. C., Perdomo-Lampignano, J. A., Cannon, P., Hall, M., Stobo, D., Maclay, J. D., Blyth, K. G., & Lowe, D. J. (2025) · European Journal of Radiology · doi:10.1016/j.ejrad.2025.112409 · Cited by 7
A Narrative Review of the Use of Artificial Intelligence in Breast, Lung, and Prostate Cancer
Patel, K., Huang, S., Rashid, A., Varghese, B. A., & Gholamrezanezhad, A. (2023) · Life · doi:10.3390/life13102011 · Cited by 8
Hwang, S. H., Shin, H. J., Kim, E., Lee, E. H., & Lee, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-47194-6 · Cited by 10
“When it was used as an adjunct to doctor judgment, lung-nodule detection improved regardless of reader experience 2,4,9,10,23 .”
BackgroundMethodLi, Y., Liu, H., Lv, Q., & Long, J. (2024) · BMC Pulmonary Medicine · doi:10.1186/s12890-024-02987-x · Cited by 7
Tugwell-Allsup, J., Owen, B. W., Hibbs, R., & England, A. (2025) · Radiography · doi:10.1016/j.radi.2025.01.011 · Cited by 8
Efficient Automatic Detection of Uterine Fibroids Based on the Scalable EfficientDet
Yang, T. H., Li, P., & Liu, P. (2022) · IEEE International Conference on Anti-counterfeiting, Security, and Identification (ASID) · doi:10.1109/asid56930.2022.9996062 · Cited by 7
“{Fl = 2 · Recall · Precision! (Recall+ Precision) ( 4) Lamr = FP /(TN + FP) 3) AP is shown in (5).”
Artificial Intelligence in Medical Imaging by Machine Learning and Deep Learning
Rahate, K., Sengar, M. S., & Patel, S. (2024) · Advances in medical technologies and clinical practice book series · doi:10.4018/979-8-3693-2238-3.ch006 · Cited by 7
Using Deep Learning Model for Adapting and Managing COVID-19 Pandemic Crisis
Alodat, M. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.03.070 · Cited by 7
“The Last layer of the model has Soft-Max classifier and four neurons, where one neuron for negative cases (normal), and three neurons for positive cases (pneumonia viral, pneumonia bacterial and Covid-19) [18].”
MethodClinical aspects of using artificial intelligence for the interpretation of chest X-rays
Morozov, S. P., Kokina, D. Y., Pavlov, N. A., Kirpichev, Y., Gombolevskiy, V. А., & Андрейченко, А. Е. (2021) · Tuberculosis and lung diseases · doi:10.21292/2075-1230-2021-99-4-58-64 · Cited by 8
“, сравнивающем эффективность искусственного интеллекта и врачей-рентгенологов в диагностике узлов легких, применение сверточной нейросети при повторном просмотре позволило улучшить чувствительность определения узлов врачами на 5,2%, помогло отклонить ложноположительные результаты [40].”
Calcification sign for prediction of benignity in pulmonary nodules: A meta‐analysis
Zhou, C., Liu, X., Gan, X., & Li, X. (2021) · The Clinical Respiratory Journal · doi:10.1111/crj.13410 · Cited by 7
Liu, Y., Wang, F., Wang, P., Zhou, Z., Wang, H., Li, J., Qiu, Y., Wang, H., & Miao, S. (2026) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-025-06413-5 · Cited by 10
“In addition, AI technology extends extensively across detection (Lo et al. 2018; Sim et al. 2020), prediction of benign and malignant conditions (Ding et al. 2023; Zhou et al. 2023), and lesion information detection of lung lesions.”
Nuutinen, M., Hiltunen, A.-M., Korhonen, S., Haavisto, I., Poikonen‐Saksela, P., Mattson, J., Manikis, G. C., Kondylakis, H., Simos, P. G., Mazzocco, K., et al. (2022) · Health and Technology · doi:10.1007/s12553-023-00733-7 · Cited by 7
Research in the application of artificial intelligence to lung cancer diagnosis
Liu, W., Shen, N., Zhang, L., Wang, X., Chen, B., Liu, Z., & Yang, C. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1343485 · Cited by 6
Artificial Intelligence and Early Detection of Breast, Lung, and Colon Cancer: A Narrative Review
Debellotte, O., Dookie, R. L., Rinkoo, F., Kar, A., Gonzalez, J. F. S., Saraf, P., Iqbal, M. A., Ghazaryan, L., Mukunde, A.-C., Khalid, A., et al. (2025) · Cureus · doi:10.7759/cureus.79199 · Cited by 17
“In contrast, Sim et al.'s study demonstrates that the CAD tool significantly enhances radiologists' sensitivity and reduces false-positives; however, the tool's standalone performance was lower in sensitivity [81].”
Wang, G., Nie, F., Wang, Y., Yang, D., Dong, T., Liu, T., & Wang, P. (2022) · Clinical Endocrinology · doi:10.1111/cen.14741 · Cited by 8
Multi-label neural architecture search for chest radiography image classification
Yang, Y., Wei, J., Yu, Z., & Zhang, R. (2024) · Multimedia Systems · doi:10.1007/s00530-023-01215-6 · Cited by 6
“However, the direct application of successful networks [23, 44] to a medical image task may not be optimal.”
Medical Image Perception Research in the Emerging Age of Artificial Intelligence
Jacobson, F. L. (2019) · Radiology · doi:10.1148/radiol.2019192252 · Cited by 7
Kirshenboim, Z. E., Gilat, E. K., Carl, L., Bekker, E., Tau, N., Klug, M., Konen, E., & Marom, E. M. (2023) · European Journal of Radiology · doi:10.1016/j.ejrad.2023.111241 · Cited by 6
Hanaoka, S., Nomura, Y., Yoshikawa, T., Nakao, T., Takenaga, T., Matsuzaki, H., Yamamichi, N., & Abe, O. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03227-7 · Cited by 7
Pneumonia X‐ray detection with anchor‐free detection framework and data augmentation
Yan, N., & Tao, Y. (2023) · International journal of imaging systems and technology (Print) · doi:10.1002/ima.22860 · Cited by 6
“To compare radiologists' performance in detecting malignant pulmonary nodules on chest radiographs when assisted by deep learning-based DCNN software 21 with that of radiologists or DCNN software alone in a multi-center setting.”
BackgroundKim, M. S., & Kang, M. (2025) · Asian Nursing Research · doi:10.1016/j.anr.2025.03.008 · Cited by 6
Self-citationRhee, 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
“Artificial intelligence (AI) tools have demonstrated excellent performance in identifying various abnormalities on CXRs and are currently used in clinical practice to assist physicians in interpreting CXR findings [11-24].”
Zhao, D., Packer, T., Jie, X., Shahid, M., Oke, J. L., & Plüddemann, A. (2025) · BJR|Artificial Intelligence · doi:10.1093/bjrai/ubaf016 · Cited by 8
“15,20,21,22,23,27,30,35,40,45 Due to their retrospective nature, others utilized histopathological and clinical diagnoses made at the time.”
InfluentialArtificial Intelligence in Respiratory Medicine: The Journey So Far – A review
Kalaiyarasan, K., & Sridhar, R. (2023) · Journal of Association of Pulmonologist of Tamil Nadu · doi:10.4103/japt.japt_13_23 · Cited by 6
Nodule Synthesis and Selection for Augmenting Chest X-ray Nodule Detection
Shen, Z., Ouyang, X., Wang, Z., Zhan, Y., Xue, Z., Wang, Q., Cheng, J., & Shen, D. G. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88010-1_45 · Cited by 6
Artificial Intelligence in Medical Imaging Data Analytics using CT Images
Thool, K. B. U., Wankhede, P. A., Yella, V. R., Tamijeselvan, S., Suganthi, D., & Rastogi, R. (2023) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc57686.2023.10192998 · Cited by 4
“Perceptib le characteristics like carcinoma volume, tumor structure such as the existence of arteries, veins, inflammat ion, and calcificat ion, consistency of carcinoma edges, and anatomic interactions to adjacent tissues like the lymph node and linings of the pleura are given highest importance for assessing the tum…”
BackgroundKhan, N., & Das, A. (2024) · IP Journal of diagnostic pathology and oncology/IP journal of diagnostic pathology and oncology/Journal of diagnostic pathology and oncology · doi:10.18231/j.jdpo.2024.042 · Cited by 4
Li, J., Liu, Y., Zhang, L., Xing, Y., Lyu, Z., Huang, Y., Zhang, P., Ye, Z., Wang, M., & Song, F. (2025) · British Journal of Cancer · doi:10.1038/s41416-025-03147-6 · Cited by 4
“Deep learning (DL) algorithms have been developed to enhance the detection rate of malignant nodules, yielding promising results [21 – 24].”
Zhang, W., Zhuang, D., Wei, W., Li, Y., Ma, L., Du, H., Jin, A., He, J., & Li, X. (2025) · Clinical & Translational Oncology · doi:10.1007/s12094-025-03945-7 · Cited by 3
“Furthermore, when radiologists receive CADe results, their average sensitivity significantly increases, underscoring the clinical value of CADe [25].”
Deng, H., Huang, W., Zhou, X., Zhou, T., Fan, L., & Liu, S. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1447132 · Cited by 3
Apport de l’intelligence artificielle dans le post-traitement de l’imagerie thoracique
Greniér, P., Brun, A., & Mellot, F. (2023) · Revue des Maladies Respiratoires · doi:10.1016/j.rmr.2023.12.001 · Cited by 4
Fan, Y., Su, Z., Wei, M., Hao, L., Jiang, Y. L., Li, X., Meng, Z., Wang, Y., Wu, H., Song, J., et al. (2021) · Thoracic Cancer · doi:10.1111/1759-7714.14213 · Cited by 4
Estimation of pathological subtypes in subsolid lung nodules using artificial intelligence
Hu, X., Liu, Y., Kang, T., Yu, H., Zhao, T., Huang, Y., & Kong, Y. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e34863 · Cited by 2
“…adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS) were included in the revised 2021 categorization of thoracic tumors by the WHO as precursor glandular lesions, whereas minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) were categorized as adenocarcinomas [7].”
BackgroundMethodYOLOv11-MFF: A multi-scale frequency-adaptive fusion network for enhanced CXR anomaly detection
Guan, L., Zhang, R., & Zhao, Y. M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0334283 · Cited by 2
“Recent efforts have targeted the detection of specific chest diseases, such as lung cancer [7], nodules [8,9], penumothorax [10], tuberculosis [11], or pneumonia [12].”
Domain Adaptive Lung Nodule Detection in X-Ray Image
Zhao, H., Jiang, L., Ma, L., Sun, D., & Fu, Y. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831519 · Cited by 3
“In recent years, numerous researchers leverage object detection models for lung nodule detection [2]–[7].”
Muto, R., Fukuta, S., Watanabe, T., Shindo, Y., Kanemitsu, Y., Kajikawa, S., Yonezawa, T., Inoue, T., Ichihashi, T., Shiratori, Y., et al. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.1042067 · Cited by 3
Nawabi, J., Eminovic, S., Hartenstein, A., Baumgaertner, G. L., Schnurbusch, N., Rudolph, M. M., Wasilewski, D., Onken, J., Siebert, E., Wiener, E., et al. (2025) · Brain Sciences · doi:10.3390/brainsci15050450 · Cited by 2
“These models can enhance diagnostic accuracy and reduce reliance on invasive procedures by capturing complex spatial features in imaging data [9–13].”
Lee, D. E., Chae, K. J., Jin, G. Y., Park, S. Y., Jeong, J. S., & Ahn, S. Y. (2023) · Acta Radiologica · doi:10.1177/02841851231202323 · Cited by 3
“There have been many studies about chest radiographs using DLAD (4,5,10,12 – 14) and, recently, it was approved by the FDA.”
BackgroundSelf-citationHoy, M. K., Desai, V. S., Mutasa, S., Hoy, R. C., Gorniak, R., & Belair, J. A. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-023-00920-y · Cited by 2
Analyzing CT Scan Images Using Deep Transfer Learning for Patients with Covid-19 Disease
Alodat, M. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-3880-0_8 · Cited by 2
Deep Transfer Learning and Intelligent Item Packing in Retail Management
Alodat, M. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-5868-7_4 · Cited by 2
Lim, C. Y., Ki, Y., Chung, M. J., Park, S., Park, S., Woo, J. H., & Kim, J. H. (2023) · Diagnostics · doi:10.3390/diagnostics13122060 · Cited by 2
“The training set was 13,710 normal radiographs and 3500 lung nodule (benign or malignant)-containing radiographs, while a test/validation set was 640 normal radiographs and 1480 lung-nodule radiographs (a total of 5700 lung nodules; size: 7 mm ≤ x ≤ 45 mm) [4].”
MethodSelf-citationCho, 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
“16-19 In this study, the performance of the AI reached a level similar to that of radiologists.”
Self-citationVijjhalwar, R., Song, K., Chappell, D. D. G., Turton, J., Boylan, J., Threlkeld, J., Page, M., Sampson, M., Arlachov, Y., Chisholm, C., et al. (2025) · BJR|Artificial Intelligence · doi:10.1093/bjrai/ubaf017 · Cited by 1
Genomic and Imaging Biomarker Analysis in Lung Cancer: A SHAP-Guided Approach
Sathya, A., Deevna Reddy, R., & Blessy, J. J. (2025) · doi:10.1109/iccds64403.2025.11209732 · Cited by 1
“CNNs now dominate: CheXNet [11] achieved radiologist-level performance on chest X-rays, while 3D CNNs proved effective for CT scans, as in Setio et al.’s [12] multi-view CNN and Ardila et al.’s [13] end-to-end malignancy predictor.”
Kumar, J. S., Balamurugan, S., & Sasikala, S. (2021) · Journal of Medical Imaging and Health Informatics · doi:10.1166/jmihi.2021.3837 · Cited by 1
Su, T., & Kao, J. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-99136-0.00008-8 · Cited by 1
Saha, S., Majumdar, S., & Bhattacharyya, P. (2023) · Springer eBooks · doi:10.1007/978-981-99-3505-5_15 · Cited by 1
Exploring Convolution Neural Networks for Image Classification in Medical Imaging
Priya, V. K., Chattu, P., Sivasankari, K., Pisal, D. T., Sai, B. R., & Suganthi, D. (2024) · International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) · doi:10.1109/iitcee59897.2024.10467794 · Cited by 1
“Medical imaging has long been the cornerstone of modern healthcare, enabling clinicians to peer into the human body's inner workings and disclose critical diagnostic information[1].”
BackgroundGavrilov, P. V., & Smolnikova, U. A. (2021) · Almanac of Clinical Medicine · doi:10.18786/2072-0505-2021-49-035 · Cited by 3
Exploring AI in Healthcare: How the Acceleration of Data Processing can Impact Life Saving Diagnoses
Janes, J., Bansal, A., & Baron, T. (2022) · Electronic workshops in computing · doi:10.14236/ewic/odak22.2 · Cited by 1
Metadata
- Authors
- Sim, Y., Chung, M. J., Kotter, E., Yune, S., Kim, M., Do, S., Han, K., Kim, H., Yang, S., Lee, D.-J., & Choi, B. W.
- Affiliations
- Yonsei University (KR)
- Harvard University (US)
- ORCID
- Venue
- Radiology
- Published
- 2020-01
- Volume
- 294
- Issue
- 1
- Pages
- 199-209
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2984645840
- Cited by
- 248
- References
- 26
- Citations by year
- 2026: 10 · 2025: 32 · 2024: 39 · 2023: 55 · 2022: 39 · 2021: 60 · 2020: 12
- FWCI
- 12.78
- Type
- journal article
- Language
- en
- Open access
- Licence
- cc-by-nc-nd
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- YUHSpace (Yonsei University Medical Library) (submittedVersion, cc-by-nc-nd)
- Funders
- Samsung Electronics
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Lung Cancer Diagnosis and Treatment
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- deep convolutional neural networks, computer-aided detection, lung cancer, chest radiograph, radiologist performance, false positives, nodule detection, diagnostic accuracy, multicenter validation
- MeSH terms
- Adult, Aged, Solitary Pulmonary Nodule, Female, Humans, Lung, Lung Neoplasms, Male, Middle Aged, Radiographic Image Interpretation, Computer-Assisted, Retrospective Studies, Sensitivity and Specificity, Radiography, Thoracic, Reproducibility of Results, Neural Networks, Computer, Multiple Pulmonary Nodules, 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.