Current Applications and Future Impact of Machine Learning in Radiology
Open accessThe DOI matches its Crossref record; 90 of the 90 references it cites were found in a registry or an index.
Abstract
Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed.
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
“Computer vision in radiology is so pronounced that it has quickly burgeoned into its own field of research, growing a corpus of work [53][54][55] that extends into all modalities, with a focus on Xrays, CT, and MRI.”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [53]
In the citing paper
“At present, there is insufficient evidence to support clinical translation, but these techniques have the potential to improve diagnostic accuracy and more informed decision making in the future.”
From Adrenal incidentaloma (2020) · cites this paper as [382]
In the citing paper
“Machine learning methods have been applied to classifying images acquired with various imaging modalities, using a variety of features, for various diseases, and with tools such as CAD and radiomics(25,29,30).”
From Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine (2019) · cites this paper as [30]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · cited 1×
“Diagnostic imaging may be one of the first medical disciplines subject to the application of machine learning algorithms, but other fields such as pathology, cardiology, dermatology, and gastroenterology also have potential use cases (87,88).”
Machine learning: Trends, perspectives, and prospects
Jordan, M. I., & Mitchell, T. M. (2015) · Science · doi:10.1126/science.aaa8415 · Cited by 9,955 · cited 1×
“Machine learning algorithms can be deployed with relative simplicity given low cost of software tools and if armed with an appropriate foundation of knowledge (3).”
Radiomics: Images Are More than Pictures, They Are Data
Gillies, R. J., Kinahan, P. E., & Hricak, H. (2016) · Radiology · doi:10.1148/radiol.2015151169 · Cited by 8,421 · cited 1×
“Radiomics is a process designed to extract a large number of quantitative features from radiology images (91).”
Deep learning in medical image analysis
Shen, D., Wu, G., & Suk, H.-I. (2017) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071516-044442 · Cited by 4,968 · cited 1×
“Given the configural information among neighboring pixels or voxels on images (structured input), CNNs have gained great interest in medical image analysis, particularly for feature extraction from images (10).”
Deo, R. C. (2015) · Circulation · doi:10.1161/circulationaha.115.001593 · Cited by 3,466
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016) · Scientific Reports · doi:10.1038/srep26094 · Cited by 1,710
Machine learning for medical imaging
Erickson, B. J., Korfiatis, P., Akkus, Z., & Kline, T. L. (2017) · RadioGraphics · doi:10.1148/rg.2017160130 · Cited by 1,672
Deep Learning in Medical Imaging: General Overview
Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G. B., Seo, J. B., & Kim, N. (2017) · Korean Journal of Radiology · doi:10.3348/kjr.2017.18.4.570 · Cited by 1,276 · cited 2×
“Also, the validation process must be highly robust, otherwise the algorithm could be subject to overfitting to a particular subclassification of data (80).”
Research works printed but not linked: 7
- Mohri M, Rostamizadeh A, Talwalkar A. Foundations of machine learning. Cambridge, Mass: MIT Press, 2012.
- Zeng JY, 2015, Int J Clin Exp Med, 8, 16077
- Wu G, 2013, Med Image Comput Comput Assist Interv, 16, 649
- Cho J, 2017, SIIM 2017 Scientific Session. Massachusetts General Hospital, Harvard Medical School
- Oliveira L, 2015, Stud Health Technol Inform, 216, 1028
- Russell S, 2016, Artificial intelligence: a modern approach, global edition
- Nie D, 2016, Med Image Comput Comput Assist Interv, 9901, 212
Cited by
Items 201–300 of 830
Classification of SARS-CoV-2 and non-SARS-CoV-2 using machine learning algorithms
Singh, O. P., Vallejo, M., El-Badawy, I. M., Ali, A., Madhanagopal, J., & Faudzi, A. A. M. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104650 · Cited by 42
Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans
Cho, H.-H., Lee, H. Y., Kim, E., Lee, G., Kim, J., Kwon, J., & Park, H. (2021) · Communications Biology · doi:10.1038/s42003-021-02814-7 · Cited by 44
Xie, C., Pang, C. L., Chan, B., Wong, E. Y.-Y., Dou, Q., & Vardhanabhuti, V. (2021) · Cancers · doi:10.3390/cancers13102469 · Cited by 42
AI in Breast Cancer Imaging: A Survey of Different Applications
Mendes, J., Domingues, J., Aidos, H., Garcia, N. C., & Matela, N. (2022) · Journal of Imaging · doi:10.3390/jimaging8090228 · Cited by 40
Facial Image-Based Autism Detection: A Comparative Study of Deep Neural Network Classifiers
Farhat, T., Akram, S., AlSagri, H. S., Ali, Z., Ahmad, A., & Jaffar, A. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.045022 · Cited by 44
Wang, Y., Yan, F., Lu, X., Zheng, G., Zhang, X., Wang, C., Zhou, K., Zhang, Y., Li, H., Zhao, Q., et al. (2019) · EBioMedicine · doi:10.1016/j.ebiom.2019.05.040 · Cited by 41
Machine Learning and Coronary Artery Calcium Scoring
Lee, H., Martin, S. S., Burt, J. R., Sahbaee, P., Rapaka, S., Gray, H. N., Leonard, T. J., Schwemmer, C., & Schoepf, U. J. (2020) · Current Cardiology Reports · doi:10.1007/s11886-020-01337-7 · Cited by 41
Artificial intelligence and radiomics in nuclear medicine: potentials and challenges
Aktolun, C. (2019) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-019-04593-0 · Cited by 41
Emerging multimodality imaging techniques for the pulmonary circulation
Rajagopal, S., Bogaard, H. J., Elbaz, M. S. M., Freed, B. H., Rémy‐Jardin, M., van Beek, E. J. R., Gopalan, D., & Kiely, D. G. (2024) · European Respiratory Journal · doi:10.1183/13993003.01128-2024 · Cited by 43
“Machine learning and deep learning can also integrate imaging data with clinical reports for more comprehensive evaluation [174], which may aid in the future in PH screening and diagnosis.”
BackgroundNguyen, X. V., Öztek, M. A., Nelakurti, D. D., Brunnquell, C. L., Mossa‐Basha, M., Haynor, D. R., & Prevedello, L. M. S. (2020) · Topics in Magnetic Resonance Imaging · doi:10.1097/rmr.0000000000000249 · Cited by 40
Diagnostic captioning: a survey
Pavlopoulos, J., Kougia, V., Androutsopoulos, I., & Papamichail, D. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01684-7 · Cited by 45
“In that sense, we should aim to position AI as tools to be used by physicians for a better medical outcome [19, 35, 71].”
MethodThe Effects of Perinodular Features on Solid Lung Nodule Classification
Calheiros, J. L. L., Amorim, L., de Lima, L. L., Filho, A. F. D. L., Ferreira, J. R., & Oliveira, M. C. (2021) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-021-00453-2 · Cited by 43
“Nowadays, a widely used approach for CADx and radiomics is based on the segmentation and extraction of quantitative attributes from diagnosed nodule images; these attributes are used for clinical decision support by training machine learning algorithms to classify unknown nodule samples [11, 17, 27].”
Methodvan Boven, M. R., Henke, C. E., Leemhuis, A. G., Hoogendoorn, M., van Kaam, A. H., Königs, M., & Oosterlaan, J. (2022) · PEDIATRICS · doi:10.1542/peds.2021-056052 · Cited by 40
Wu, T., Duan, Y., Zhang, T., Tian, W., Liu, H., & Deng, Y. (2022) · Frontiers in Bioscience-Landmark · doi:10.31083/j.fbl2709254 · Cited by 42
“AI models are typically built using a limited dataset that is assumed to be representative of all past and future data across different institutions [128].”
BackgroundZeng, W., Li, W., Huang, K., Lin, Z., Dai, H., He, Z., Liu, R., Zeng, Z., Qin, G., Chen, W., et al. (2022) · Frontiers in Neurology · doi:10.3389/fneur.2022.982783 · Cited by 38
Medical students’ perceptions of the impact of artificial intelligence in radiology
Galán, G. C., & Sendra‐Portero, F. (2022) · Radiología (English Edition) · doi:10.1016/j.rxeng.2021.03.008 · Cited by 39
A Series-Based Deep Learning Approach to Lung Nodule Image Classification
Balcı, M. A., Batrancea, L. M., Akgüller, Ö., & Nichita, A. (2023) · Cancers · doi:10.3390/cancers15030843 · Cited by 40
“Moreover, machine learning algorithms use this collection of properties as a training set for classifying unseen nodule samples [16,17].”
BackgroundKoçak, B., Kaya, O. K., Erdim, Ç., Kuş, E. A., & Kılıçkesmez, Ö. (2020) · American Journal of Roentgenology · doi:10.2214/ajr.20.22847 · Cited by 36
Artificial intelligence - based ultrasound elastography for disease evaluation - a narrative review
Zhang, X., Wei, Q., Wu, G.-G., Tang, Q., Pan, X.-F., Chen, G.-Q., Zhang, D., Dietrich, C. F., & Cui, X. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1197447 · Cited by 38
“After a model is developed, there is often an urgent need for an independent external test dataset to evaluate the performance and generalizability of the developed model (23).”
BackgroundMethodTumor classification of gastrointestinal liver metastases using CT-based radiomics and deep learning
Tharmaseelan, H., Vellala, A. K., Hertel, A., Tollens, F., Rotkopf, L. T., Rink, J. S., Woźnicki, P., Ayx, I., Bartling, S. H., Nörenberg, D., et al. (2023) · Cancer Imaging · doi:10.1186/s40644-023-00612-4 · Cited by 36
“However, the potential methodology ranges from radiomics features [14], often combined with ML-classifiers [15], and applications of convolutional neural networks (CNN) [16].”
BackgroundClassification of Parkinson’s disease by deep learning on midbrain MRI
Welton, T., Hartono, S., Lee, W., Teh, P. Y., Hou, W., Chen, R. C., Chen, C., Lim, E. W., Prakash, K. M., Tan, L., et al. (2024) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2024.1425095 · Cited by 40
“Ideally, such tools should be incorporated into an automatic pipeline to not require additional steps, and should present the results directly on a clinical workstation, which requires regulatory approval (Choy et al., 2018).”
BackgroundSuper‐resolution head and neck MRA using deep machine learning
Koktzoglou, I., Huang, R. H., Ankenbrandt, W. J., Walker, M. T., & Edelman, R. R. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.28738 · Cited by 37
Biercher, A., Meller, S., Wendt, J., Caspari, N., Schmidt-Mosig, J., Decker, S. D., & Volk, H. A. (2021) · Frontiers in Veterinary Science · doi:10.3389/fvets.2021.721167 · Cited by 38
Zhou, Y., Li, X., Ng, L., Zhao, Q. C., Guo, W., Hu, J., Zhong, J., Su, W., Liu, C., & Su, S. (2023) · Frontiers in Immunology · doi:10.3389/fimmu.2023.1103509 · Cited by 45
“In comparison with the traditional statistical model, the comprehensive analysis of ML ensures the robustness of the model and improves the prediction accuracy through iterative algorithm (46, 47).”
MethodPreparing to work with artificial intelligence: assessing WHS when using AI in the workplace
Cebulla, A., Szpak, Z. L., & Knight, G. (2023) · International Journal of Workplace Health Management · doi:10.1108/ijwhm-09-2022-0141 · Cited by 41
Weikert, T., Francone, M., Abbara, S., Baessler, B., Choi, B. W., Gutberlet, M., Hecht, E. M., Loewe, C., Mousseaux, E., Natale, L., et al. (2021) · European Radiology · doi:10.1007/s00330-020-07417-0 · Cited by 34
Machine learning prediction of diabetic foot ulcers in the inpatient population
Stefanopoulos, S., Ayoub, S., Qiu, Q., Ren, G., Osman, M., Nazzal, M. M. S., & Ahmed, A. E. (2021) · Vascular · doi:10.1177/17085381211040984 · Cited by 34
From CT to artificial intelligence for complex assessment of plaque-associated risk
Opincariu, D., Benedek, T., Chițu, M., Raț, N., & Benedek, I. (2020) · International journal of cardiac imaging · doi:10.1007/s10554-020-01926-1 · Cited by 34
Zheng, R., Wang, L., Wang, C., Yu, X., Chen, W., Li, Y., Li, W., Yan, F., Wang, H., & Li, R. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/abf2f8 · Cited by 33
Machine Learning Demonstrates High Accuracy for Disease Diagnosis and Prognosis in Plastic Surgery
Mantelakis, A., Assael, Y., Sorooshian, P., & Khajuria, A. (2021) · Plastic & Reconstructive Surgery Global Open · doi:10.1097/gox.0000000000003638 · Cited by 33
Kedra, J., Davergne, T., Braithwaite, B., Servy, H., & Gossec, L. (2021) · Expert Review of Clinical Immunology · doi:10.1080/1744666x.2022.2017773 · Cited by 34
“In cardiology and radiology for instance, ML projects are numerous [117,118].”
BackgroundNg, C. K. C. (2023) · Children · doi:10.3390/children10030525 · Cited by 42
“In this way, the potential benefits of the CAD could be realized in a wider context [5,10,12,13].”
BackgroundQuantitative PET-based biomarkers in lymphoma: getting ready for primetime
Alderuccio, J. P., Kuker, R. A., Yang, F., & Moskowitz, C. H. (2023) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-023-00799-2 · Cited by 37
Applications and challenges of neural networks in otolaryngology (Review)
Taciuc, I.-A., Dumitru, M., Vrînceanu, D., Gherghe, M., Manole, F., Marinescu, A., Serboiu, C. S., Neagoş, A., & Costache, A. (2024) · Biomedical Reports · doi:10.3892/br.2024.1781 · Cited by 34
“The development of ML and deep learning algorithms, combined with the processing power tools that are currently available, is a field that is garnering interest in the medical setting (38,39).”
BackgroundCT Findings in Pulmonary and Abdominal Sarcoidosis. Implications for Diagnosis and Classification
Tana, C., Donatiello, I., Coppola, M. G., Ricci, F., Maccarone, M. T., Ciarambino, T., Cipollone, F., & Giamberardino, M. A. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9093028 · Cited by 33
Conformal Prediction Sets Improve Human Decision MakingPreprint
Cresswell, J. C., Sui, Y., Kumar, B., & Vouitsis, N. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.13744 · Cited by 79
“For instance, radiologists diagnose diseases by classifying X-ray images, and could potentially improve the accuracy and speed of diagnosis by leveraging machine learning classifiers (Choy et al., 2018; Agarwal et al., 2023).”
BackgroundA Review of the Clinical Applications of Artificial Intelligence in Abdominal Imaging
Mervak, B. M., Fried, J. G., & Wasnik, A. P. (2023) · Diagnostics · doi:10.3390/diagnostics13182889 · Cited by 34
“…they have been heralded in widespread applications within radiology departments, with proposed uses including image quality control, augmentation and prioritization of workflows and worklists, segmentation of organs and lesions, detection of incidental findings, and assisting with classification [2].”
Imaging-based internal body temperature measurements: The journal Temperature toolbox
Raiko, J. R. H., Koskensalo, K., & Sainio, T. (2020) · Temperature · doi:10.1080/23328940.2020.1769006 · Cited by 33
“As machine learning algorithms already detect pathologies from CT images [138] in the future they might extract several parameters, such as temperature, from a single dataset or even several multimodal datasets.”
BackgroundÚbeda, P. L., Díaz–Galiano, M. C., Martín‐Noguerol, T., Ureña-López, A., Valdivia, M. T. M., & Luna, A. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113647 · Cited by 32
Bridge, C. P., Gorman, C., Pieper, S., Doyle, S., Lennerz, J. K., Kalpathy–Cramer, J., Clunie, D., Fedorov, A., & Herrmann, M. D. (2022) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-022-00683-y · Cited by 35
“…of years, ML models have evolved technically within the research domain [8] and the vision is that these models will soon be applied widely in clinical practice to support pathologists and radiologists in interpretation of images and ultimately improve diagnostic accuracy and efficiency [6, 9–11].”
Artificial Intelligence and Advanced Melanoma: Treatment Management Implications
Guerrisi, A., Falcone, I., Valenti, F., Rao, M., Gallo, E., Ungania, S., Maccallini, M. T., Fanciulli, M., Frascione, P., Morrone, A., et al. (2022) · Cells · doi:10.3390/cells11243965 · Cited by 37
“A third category of algorithms is characterized by reinforcement learning, when the machine independently apprehends from the environment without being taught explicitly [47].”
BackgroundWill AI Replace Physicians in the Near Future? AI Adoption Barriers in Medicine
Obuchowicz, R., Piórkowski, A., Nurzyǹska, K., Obuchowicz, B., Strzelecki, M., & Bielecka, M. (2026) · Diagnostics · doi:10.3390/diagnostics16030396 · Cited by 33
“This capability underpins their success in radiology [6,7].”
The value of MR textural analysis in prostate cancer
Patel, N., Henry, A. M., & Scarsbrook, A. F. (2018) · Clinical Radiology · doi:10.1016/j.crad.2018.11.007 · Cited by 32
Streun, G. L., Elmiger, M. P., Dobay, A., Ebert, L. C., & Kræmer, T. (2020) · Drug Testing and Analysis · doi:10.1002/dta.2775 · Cited by 31
Machine Learning in Meningioma MRI: Past to Present. A Narrative Review
Neromyliotis, E., Κalamatianos, T., Paschalis, A., Komaitis, S., Fountas, K. N., Kapsalaki, E. Z., Stranjalis, G., & Tsougos, I. (2020) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.27378 · Cited by 34
“…deep-learning approaches, have recently gained considerable traction over “ traditional ” machine-learning approaches utilizing support vector machines (SVMs) and random forests, 13 – 15 in studies addressing segmentation (tumor delineation), diagnosis, progression, and prognostication.”
BackgroundComplex Relationship Between Artificial Intelligence and CT Radiation Dose
Gupta, R. V., Kalra, M. K., Ebrahimian, S., Kaviani, P., Primak, A. N., Bizzo, B. C., & Dreyer, K. J. (2021) · Academic Radiology · doi:10.1016/j.acra.2021.10.024 · Cited by 31
Self-citationShoham, G., Berl, A., Shir‐az, O., Shabo, S., & Shalom, A. (2022) · Experimental Dermatology · doi:10.1111/exd.14550 · Cited by 31
Luo, Y., Sun, X., Kong, X., Tong, X., Xi, F., Yu, M., Miao, Z., & Ma, J. (2023) · European Journal of Radiology · doi:10.1016/j.ejrad.2023.110731 · Cited by 32
Imaging Analytics using Artificial Intelligence in Oncology: A Comprehensive Review
Chakrabarty, N., & Mahajan, A. (2023) · Clinical Oncology · doi:10.1016/j.clon.2023.09.013 · Cited by 35
The Case for User-Centered Artificial Intelligence in Radiology
Filice, R. W., & Ratwani, R. M. (2020) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2020190095 · Cited by 30
“A newer deep learning methods, have shown great promise in radiology research and in translation to practice (1).”
Savardi, M., Signoroni, A., Benini, S., Vaccher, F., Alberti, M., Ciolli, P., Di Meo, N., Falcone, T., Ramanzin, M., Romano, B., et al. (2025) · Insights into Imaging · doi:10.1186/s13244-024-01893-4 · Cited by 30
Bani-Ahmad, M., England, A., McLaughlin, L., Hadi, Y. H., & McEntee, M. F. (2025) · Radiography · doi:10.1016/j.radi.2025.102968 · Cited by 30
Stephens, M. E., O’Neal, C. M., Westrup, A. M., Muhammad, F., McKenzie, D. M., Fagg, A. H., & Smith, Z. A. (2021) · Neurosurgical Review · doi:10.1007/s10143-021-01624-z · Cited by 32
A deep learning framework for automated detection and quantitative assessment of liver trauma
Farzaneh, N., Stein, E. B., Soroushmehr, S. M. R., Gryak, J., & Najarian, K. (2022) · BMC Medical Imaging · doi:10.1186/s12880-022-00759-9 · Cited by 36
“Novel big data analytics and computational frameworks, however, are keys to solving such problems in digital health technology [15].”
BackgroundCommon and Uncommon Errors in Emergency Ultrasound
Serafino, M. D., Iacobellis, F., Schillirò, M. L., D’Auria, D., Verde, F., Grimaldi, D., Orabona, G. D., Caruso, M., Sabatino, V., Rinaldo, C., et al. (2022) · Diagnostics · doi:10.3390/diagnostics12030631 · Cited by 30
Sheng, W., Xia, S., Wang, Y., Yan, L., Ke, S., Mellisa, E., Gong, F., Zheng, Y., & Tang, T. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.964605 · Cited by 30
Robotics, artificial intelligence and distributed ledgers in surgery: data is key!
Chand, M., Ramachandran, N., Stoyanov, D. V., & Lovat, L. B. (2018) · Techniques in Coloproctology · doi:10.1007/s10151-018-1847-5 · Cited by 31
Hua, Y., Chen, R., & Qin, H. (2025) · Electronics · doi:10.3390/electronics14040805 · Cited by 32
“The integration of radiomics with advanced artificial intelligence (AI) models, especially deep learning frameworks, has shown significant promise in improving detection, segmentation, and classification tasks in medical imaging [5,6].”
Hameed, B. M. Z., Gayathri, P., Patil, V., Shekhar, P., Raza, S. Z., Karimi, H., Paul, R., Naik, N., Modi, S., Vigneswaran, G., et al. (2021) · Therapeutic Advances in Urology · doi:10.1177/17562872211044880 · Cited by 35
“21 Narrow-scope ML algorithms do not need vast data from testing but might need data from high-quality ground truth training.”
Fu, T., Viswanathan, V. S., Attia, A., Zerbib-Attal, E., Kosaraju, V., Barger, R., Vidal, J., Bittencourt, L. K., & Faraji, N. (2023) · Academic Radiology · doi:10.1016/j.acra.2023.10.042 · Cited by 31
Artificial intelligence in musculoskeletal oncological radiology
Vogrin, M., Trojner, T., & Kelc, R. (2020) · Radiology and Oncology · doi:10.2478/raon-2020-0068 · Cited by 33
Using Machine Learning to Evaluate Attending Feedback on Resident Performance
Neves, S. E., Chen, M. J., Ku, C. M., Karan, S., DiLorenzo, A. N., Schell, R. M., Lee, D. E., Diachun, C. A. B., Jones, S. B., & Mitchell, J. D. (2021) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000005265 · Cited by 28
Percepciones de estudiantes de Medicina sobre el impacto de la inteligencia artificial en radiología
Galán, G. C., & Sendra‐Portero, F. (2021) · Radiología · doi:10.1016/j.rx.2021.03.006 · Cited by 36
Moreau, N., Rousseau, C., Fourcade, C., Santini, G., Brennan, A., Ferrer, L., Lacombe, M., Guillerminet, C., Colombié, M., Jézéquel, P., et al. (2021) · Cancers · doi:10.3390/cancers14010101 · Cited by 29
“Indeed, most deep-learning studies on lesion segmentation aim to detect and segment lesions on a single acquisition for different purposes such as diagnosis, radiotherapy planning or to correlate image findings with other clinical data [43].”
BackgroundManaging Randomness to Enable Reproducible Machine Learning
Ahmed, H., & Lofstead, J. (2022) · International Workshop on Practical Reproducible Evaluation of Computer Systems (P-RECS) · doi:10.1145/3526062.3536353 · Cited by 37
“ML has been pivotal to advancements in fields such as health care [4, 5], material sciences [7], economics [1], radiology [8], civil engineering [19], and sales and marketing [23].”
MethodHassan, J., Saeed, S. M., Deka, L., Uddin, M. J., & Das, D. B. (2024) · Pharmaceutics · doi:10.3390/pharmaceutics16020260 · Cited by 35
“This combinatorial approach of ML and MM makes cancer management feasible, cost-effective, and more accurate than before.”
BackgroundMachine Learning Algorithms for Classification of First‐Trimester Fetal Brain Ultrasound Images
Gofer, S., Haik, O., Bardin, R., Gilboa, Y., & Perlman, S. (2022) · Journal of Ultrasound in Medicine · doi:10.1002/jum.15860 · Cited by 27
“Transvaginal ultrasound of the fetal head in an axial view obtained at 13 weeks of gestation in a fetus with a normal NT (A) and an increased (5 mm) NT (B) demonstrating the segments that served for analysis: Skin (1), bone (2), meninges (3), cortex (4), ependyma (5), cerebrospinal fluid (6), choroid plexus (7).”
RETRACTED: A deep learning-based ensemble for autism spectrum disorder diagnosis using facial images
Farhat, T., Akram, S., Rashid, M., Jaffar, A., Bhatti, S. M., & Iqbal, M. A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0321697 · Cited by 30
“Researchers use machine learning and deep learning to detect autism using facial images dataset primarily [6,7].”
RetractedCurrent and emerging artificial intelligence applications for pediatric abdominal imaging
Dillman, J. R., Somasundaram, E., Brady, S. L., & He, L. (2021) · Pediatric Radiology · doi:10.1007/s00247-021-05057-0 · Cited by 28
Lee, K. F. A., Gan, W., & Christopoulos, G. I. (2021) · Sensors · doi:10.3390/s21113843 · Cited by 27
Kriza, C., Amenta, V., Zenié, A., Panidis, D., Chassaigne, H., Urbán, P., Holzwarth, U., Sauer, A. V., Reina, V., & Griesinger, C. B. (2021) · European Journal of Radiology · doi:10.1016/j.ejrad.2021.110028 · Cited by 29
“The field of medical imaging has seen rapid progress in the last years for the application of artificial intelligence (AI) methodologies, especially machine learning (ML) and deep learning (DL) [1].”
Clinical Decision Support for Laboratory Testing
Hughes, A. E. O., & Jackups, R. (2022) · Clinical Chemistry · doi:10.1093/clinchem/hvab201 · Cited by 28
Evolving perspectives on evaluating obesity: from traditional methods to cutting-edge techniques
Wang, H., Qin, Y., Niu, J., Chen, H., Lu, X., Wang, R., & Han, J. (2025) · Annals of Medicine · doi:10.1080/07853890.2025.2472856 · Cited by 31
“Artificial intelligence (AI), including machine learning and deep learning, has recently been proposed as a solution for obtaining automatic and reliable abdominal adipose tissue analysis [155,156].”
Shin, H. J., Lee, S., Kim, S., Son, N., & Kim, E. (2023) · PLoS ONE · doi:10.1371/journal.pone.0282123 · Cited by 27
Mergen, V., Kobe, A. R., Blüthgen, C., Euler, A., Flohr, T. G., Frauenfelder, T., Alkadhi, H., & Eberhard, M. (2020) · European Journal of Radiology Open · doi:10.1016/j.ejro.2020.100272 · Cited by 26
Resch, D., Gullo, R. L., Teuwen, J., Semturs, F., Hummel, J. B., Resch, A., & Pinker, K. (2024) · Radiology Imaging Cancer · doi:10.1148/rycan.230149 · Cited by 25
Kumar, R. R., Sporn, K., Paladugu, P., Khanna, A., Gowda, C., Ngo, A., Waisberg, E., Ong, J., Jagadeesan, R., & Tavakkoli, A. (2025) · Diagnostics · doi:10.3390/diagnostics15131648 · Cited by 32
“These innovations increasingly mirror the demands of clinical decision-making, where precise and comprehensive imaging assessments are critical for prognostic evaluations [190].”
Artificial Intelligence and Deep Learning of Head and Neck Cancer
Razek, A. A. K. A., Khaled, R., Helmy, E. M., Naglah, A., AbdelKhalek, A., & El-Baz, A. S. (2021) · Magnetic Resonance Imaging Clinics of North America · doi:10.1016/j.mric.2021.06.016 · Cited by 26
Torres‐Lopez, V., Rovenolt, G. E., Olcese, A. J., Garcia, G. E., Chacko, S. M., Robinson, A. B., Gaiser, E., Acosta, J., Herman, A. L., Kuohn, L. R., et al. (2022) · JAMA Network Open · doi:10.1001/jamanetworkopen.2022.27109 · Cited by 25
Artificial intelligence in diagnostic ultrasonography
Dıcle, O. (2023) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2022.211260 · Cited by 31
“5 In this way, it is possible to easily perform complex, time-consuming, and inadequately sensitive operations for human beings through machines.”
BackgroundInfluentialQuantification of Indocyanine Green Fluorescence Imaging in General, Visceral and Transplant Surgery
Pollmann, L., Juratli, M. A., Roushansarai, N., Pascher, A., & Hölzen, J. P. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12103550 · Cited by 25
Aeberhard, J. L., Radan, A., Soltani, R. A., Strahm, K. M., Schneider, S., Carrié, A., Lemay, M., Krauss, J., Delgado-Gonzalo, R., & Surbek, D. (2024) · Methods and Protocols · doi:10.3390/mps7010005 · Cited by 28
“In the field of radiology, studies have shown that AI systems interpret images in the same variability range as experienced specialists [11,12].”
BackgroundComputer‐Aided Detection AI Reduces Interreader Variability in Grading Hip Abnormalities With MRI
Tibrewala, R., Ozhinsky, E., Shah, R., Flament, I., Crossley, K. M., Srinivasan, R., Souza, R. B., Link, T. M., Pedoia, V., & Majumdar, S. (2020) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.27164 · Cited by 25
“Furthermore, these trained networks could be used as an assist tool when training incoming radiologists, assuming all the network predictions are vetted by an experienced radiologist, therefore reducing the workload on the experienced radiologist.(27,28) FIGURE 7: Correlation plot between input and predicted total SHO…”
MethodHomayounieh, F., Babaei, R., Mobin, H. K., Arru, C. D., Sharifian, M., Mohseni, I., Zhang, E. W., Digumarthy, S. R., & Kalra, M. K. (2020) · Journal of Computer Assisted Tomography · doi:10.1097/rct.0000000000001094 · Cited by 24
“However, in the past few years, automatic organ segmentation and incorporation of machine learning for radiomics analyses should greatly ease this burden.(25,26) Industry and academia should investigate how these tasks can be automated and brought into routine clinical practice in a way that is least disruptive and mo…”
BackgroundArtificial Intelligence: Singularity Approaches
TerKonda, S. P., TerKonda, A. A., Sacks, J. M., Kinney, B. M., Gurtner, G. C., Nachbar, J. M., Reddy, S., & Jeffers, L. L. C. (2023) · Plastic & Reconstructive Surgery · doi:10.1097/prs.0000000000010572 · Cited by 25
Next generation phenotyping for diagnosis and phenotype–genotype correlations in Kabuki syndrome
Hennocq, Q., Willems, M., Amiel, J., Arpin, S., Attié‐Bitach, T., Bongibault, T., Bouygues, T., Cormier‐Daire, V., Corre, P., Dieterich, K. D., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-52691-3 · Cited by 26
“The model for ears was trained on 1221 manually annotated photographs, with a first stage of dimensioning (diagonal = 100), a patch shape of [(15, 15), (23, 23)] and 50 iterations and a second stage without resizing, with a patch shape of [(20, 20), (30, 30)] and 20 new iterations.”
MethodThe Role of Artificial Intelligence in the Diagnosis of Melanoma
Kalidindi, S. (2024) · Cureus · doi:10.7759/cureus.69818 · Cited by 33
“ML is considered the core of AI and includes supervised, unsupervised, and reinforcement learning algorithms, each with distinct learning methods [63,64].”
BackgroundContext aware machine learning techniques for brain tumor classification and detection – A review
Amjad, U., Raza, A., Fahad, M., Farid, D., Akhunzada, A., Abubakar, M., & Beenish, H. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e41835 · Cited by 27
Nakai, H., Nishio, M., Yamashita, R., Ono, A., Nakao, K. K., Fujimoto, K., & Togashi, K. (2019) · Academic Radiology · doi:10.1016/j.acra.2019.05.016 · Cited by 24
Wang, T.-W., Shiao, Y.-C., Hong, J.-S., Lee, W.-K., Hsu, M.-S., Cheng, H.-M., Yang, H.-C., Lee, C.-C., Pan, H.-C., You, W. C., et al. (2024) · Mayo Clinic Proceedings: Digital Health · doi:10.1016/j.mcpdig.2024.01.002 · Cited by 23
“8,9 However, the very boon of these data abundance also presents challenges, primarily stemming from data set disparities.”
Neuroimaging in Psychiatry and Neurodevelopment: why the emperor has no clothes
Anderson, A. N., King, J. B., & Anderson, J. S. (2019) · British Journal of Radiology · doi:10.1259/bjr.20180910 · Cited by 26
Kim, H. J., Kim, H. H., Kim, K., Choi, W. J., Chae, E. Y., Shin, H. J., Cha, J. H., & Shim, W. H. (2022) · Insights into Imaging · doi:10.1186/s13244-022-01183-x · Cited by 24
“With the recent evolution of artificial intelligence (AI) algorithms, there is much interest in its use in radiology, which is largely based on image data that can be easily processed and analyzed by computers [4, 12–15].”
BackgroundWang, X., Fan, Y., Zhang, N., Li, J., Duan, Y., & Yang, B. (2022) · Frontiers in Neurology · doi:10.3389/fneur.2022.910259 · Cited by 25
“It also drives the emergence of deep learning (DL) subfield, which has shown impressive results in medical image processing without prior selection for relevant features (9, 10).”
BackgroundRadiomics in Cardiovascular Disease Imaging: from Pixels to the Heart of the Problem
Spadarella, G., Perillo, T., Ugga, L., & Cuocolo, R. (2022) · Current Cardiovascular Imaging Reports · doi:10.1007/s12410-022-09563-z · Cited by 23
Zhang, C., Wu, C., Zhang, H., Dou, W., Li, W., Sami, M. U., & Xu, K. (2020) · Neuroscience · doi:10.1016/j.neuroscience.2020.07.008 · Cited by 24
Dagli, M. M., Rajesh, A., Asaad, M., & Butler, C. E. (2021) · The American Surgeon · doi:10.1177/00031348211065101 · Cited by 26
“One of the biggest applications ofML inmedicine today is within the field of radiology where supervised ML is being used to analyze and interpret imaging scans.(7) Tasks involving automated classification are a unique strength of ML; this concept is used for interpreting imaging scans and staging different malignancie…”
MethodBahar, R. C., Merkaj, S., Petersen, G. C., Tillmanns, N., Subramanian, H. E., Brim, W. R., Zeevi, T., Staib, L. H., Kazarian, E., Lin, M., et al. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.856231 · Cited by 26
“Prior to broad clinical use, ML models must be trained and validated on large, multi-institutional datasets to ensure generalizability (43).”
MethodThe role of artificial intelligence in clinical imaging and workflows
Wilson, D. U., Bailey, M. Q., & Craig, J. C. (2022) · Veterinary Radiology & Ultrasound · doi:10.1111/vru.13157 · Cited by 32
Chokshi, F. H., Flanders, A. E., Prevedello, L. M. S., & Langlotz, C. P. (2019) · Radiology Artificial Intelligence · doi:10.1148/ryai.2019190021 · Cited by 25
“Stakeholders from academia, corporations, professional societies, and government agencies are attempting to organize and guide the development, validation, and dissemination of AI algorithms in health care (2,3).”
BackgroundGau, K., Schmidt, C. S. M., Urbach, H., Zentner, J., Schulze‐Bonhage, A., Kaller, C. P., & Foit, N. A. (2020) · Neuroradiology · doi:10.1007/s00234-020-02481-1 · Cited by 22
Metadata
- Authors
- Choy, G., Khalilzadeh, O., Michalski, M., Do, S., Samir, A. E., Pianykh, O. S., Geis, J. R., Pandharipande, P. V., Brink, J. A., & Dreyer, K. J.
- Affiliations
- Harvard University (US)
- ORCID
- Venue
- Radiology
- Published
- 2018-08
- Volume
- 288
- Issue
- 2
- Pages
- 318-328
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- PMC
- PMC6542626
- OpenAlex
- W2810349670
- Cited by
- 800
- References
- 89
- Citations by year
- 2026: 37 · 2025: 85 · 2024: 101 · 2023: 118 · 2022: 139 · 2021: 140 · 2020: 110 · 2019: 57 · 2018: 13
- FWCI
- 1.77
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Radiology (publishedVersion)
- Europe PMC (PubMed Central) (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institute of Biomedical Imaging and Bioengineering (K23EB020710)
- Topics
- 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
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- machine learning, artificial intelligence, diagnostic radiology, radiology workflow, clinical decision support systems, medical image analysis, radiology reporting, image post-processing, radiation dose assessment, triage, order scheduling
- MeSH terms
- Machine Learning, Humans, Radiology, Radiology Information Systems
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.