A Deep Learning Model to Triage Screening Mammograms: A Simulation Study
The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Background Recent deep learning (DL) approaches have shown promise in improving sensitivity but have not addressed limitations in radiologist specificity or efficiency. Purpose To develop a DL model to triage a portion of mammograms as cancer free, improving performance and workflow efficiency. Materials and Methods In this retrospective study, 223 109 consecutive screening mammograms performed in 66 661 women from January 2009 to December 2016 were collected with cancer outcomes obtained through linkage to a regional tumor registry. This cohort was split by patient into 212 272, 25 999, and 26 540 mammograms from 56 831, 7021, and 7176 patients for training, validation, and testing, respectively. A DL model was developed to triage mammograms as cancer free and evaluated on the test set. A DL-triage workflow was simulated in which radiologists skipped mammograms triaged as cancer free (interpreting them as negative for cancer) and read mammograms not triaged as cancer free by using the original interpreting radiologists’ assessments. Sensitivities, specificities, and percentage of mammograms read were calculated, with and without the DL-triage–simulated workflow. Statistics were computed across 5000 bootstrap samples to assess confidence intervals (CIs). Specificities were compared by using a two-tailed t test (P < .05) and sensitivities were compared by using a one-sided t test with a noninferiority margin of 5% (P < .05). Results The test set included 7176 women (mean age, 57.8 years ± 10.9 [standard deviation]). When reading all mammograms, radiologists obtained a sensitivity and specificity of 90.6% (173 of 191; 95% CI: 86.6%, 94.7%) and 93.5% (24 625 of 26 349; 95% CI: 93.3%, 93.9%). In the DL-simulated workflow, the radiologists obtained a sensitivity and specificity of 90.1% (172 of 191; 95% CI: 86.0%, 94.3%) and 94.2% (24 814 of 26 349; 95% CI: 94.0%, 94.6%) while reading 80.7% (21 420 of 26 540) of the mammograms. The simulated workflow improved specificity (P = .002) and obtained a noninferior sensitivity with a margin of 5% (P < .001). Conclusion This deep learning model has the potential to reduce radiologist workload and significantly improve specificity without harming sensitivity. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Kontos and Conant 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 [106]
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 · cited 2×
“In brief, we implemented our model as a deep convolutional neural network (ResNet18 [22]) with PyTorch (version 0.31; https://pytorch.org ).”
MethodInfluentialREDUCTION IN MORTALITY FROM BREAST CANCER AFTER MASS SCREENING WITH MAMMOGRAPHY
Tabár, L., Gad, A., Holmberg, L. H., Ljungquist, U., Fagerberg, C. J. G., Baldetorp, L., Gröntoft, O., Lundström, B., Månson, J. C., Eklund, G., et al. (1985) · The Lancet · doi:10.1016/s0140-6736(85)92204-4 · Cited by 1,781
The benefits and harms of breast cancer screening: an independent review
(2012) · The Lancet · doi:10.1016/s0140-6736(12)61611-0 · Cited by 1,492
Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection
Lehman, C. D., Wellman, R. D., Buist, D. S. M., Kerlikowske, K., Tosteson, A. N. A., & Miglioretti, D. L. (2015) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2015.5231 · Cited by 678
Self-citationLehman, C. D., Arao, R. F., Sprague, B. L., Lee, J. M., Buist, D. S. M., Kerlikowske, K., Henderson, L. M., Onega, T., Tosteson, A. N. A., Rauscher, G. H., et al. (2017) · Radiology · doi:10.1148/radiol.2016161174 · Cited by 665
Self-citationInfluence of Computer-Aided Detection on Performance of Screening Mammography
Fenton, J. J., Taplin, S. H., Carney, P. A., Abraham, L., Sickles, E. A., D'Orsi, C., Berns, E. A., Cutter, G., Hendrick, R. E., Barlow, W. E., et al. (2007) · New England Journal of Medicine · doi:10.1056/nejmoa066099 · Cited by 619
Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System
Rodríguez-Ruiz, A., Krupinski, E., Mordang, J.-J., Schilling, K., Heywang-Köbrunner, S. H., Sechopoulos, I., & Mann, R. M. (2019) · Radiology · doi:10.1148/radiol.2018181371 · Cited by 602 · cited 3×
“Although traditional approaches have not demonstrated improved radiologist performance in sensitivity or specificity in clinical practice (14–16), a more recent deep learning approach to CAD has shown promise in improving sensitivity in a reader study (17).”
BackgroundMethodField, C. A., & Welsh, A. H. (2007) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2007.00593.x · Cited by 426 · cited 1×
“To account for patients appearing in our test set multiple times, we used the cluster bootstrap procedure (23).”
MethodMammographic Breast Density Assessment Using Deep Learning: Clinical Implementation
Lehman, C. D., Yala, A., Schuster, T., Dontchos, B., Bahl, M., Swanson, K., & Barzilay, R. (2019) · Radiology · doi:10.1148/radiol.2018180694 · Cited by 294 · cited 1×
“Mammograms from 60 886 of the 80 818 women in our patient population were previously reported (20,21).”
Self-citationRodriguez-Ruiz, A., Lång, K., Gubern-Merida, A., Teuwen, J., Broeders, M., Gennaro, G., Clauser, P., Helbich, T. H., Chevalier, M., Mertelmeier, T., et al. (2019) · European Radiology · doi:10.1007/s00330-019-06186-9 · Cited by 210 · cited 2×
“Recall rates from screening mammography have increased steadily concurrently explored in a recent reader study by Rodriguez-Ruiz et al (24), which used a commercial system and showed a simulated workload reduction of 17% with a drop of 1% in sensitivity and a noninferior radiologist AUC of 0.05 on an enriched data set.”
MethodInfluential
Research works printed but not linked: 3
- Shapiro S, 1982, J Natl Cancer Inst, 69, 349
- Miller AB, 1981, Clin Invest Med, 4, 227
- Yala A, 2019, Radiology, 182716
Cited by
Items 101–200 of 218
Pesapane, F., Nicosia, L., D’Amelio, L., Quercioli, G., Pannarale, M. R., Priolo, F., Marinucci, I., Farina, M. G., Penco, S., Dominelli, V., et al. (2025) · Cancers · doi:10.3390/cancers17172901 · Cited by 16
“But in the context of screening personalization, AI detection can be harnessed for triage automation—deciding which exams or patients warrant more urgent attention or additional work-up [43,47,48].”
Yi, P. H., Arun, A., Hafezi‐Nejad, N., Choy, G., Sair, H. I., Hui, F. K., & Fritz, J. (2021) · Skeletal Radiology · doi:10.1007/s00256-021-03880-y · Cited by 15
Ho, T.-Q. H., Bissell, M. C. S., Lee, C. I., Lee, J. M., Sprague, B. L., Tosteson, A. N. A., Wernli, K. J., Henderson, L. M., Kerlikowske, K. M., & Miglioretti, D. L. (2022) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2022.09.030 · Cited by 13
Camurdan, O., Tanyel, T., Cerekci, E. A., Alis, D. C., Meltem, E., Denizoğlu, N., Şeker, M. E., Öksüz, İ., & Karaarslan, E. (2025) · Insights into Imaging · doi:10.1186/s13244-025-01922-w · Cited by 12
“[13 – 15].”
Firuzpour, F., Heydari, M., Aram, C., & Alishvandi, A. (2025) · Bioimpacts · doi:10.34172/bi.30984 · Cited by 27
Machine learning based Breast Cancer screening: trends, challenges, and opportunities
Zizaan, A., & Idri, A. (2023) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2023.2172615 · Cited by 13
Supervised Contrastive Pre-training for Mammographic Triage Screening Models
Cao, Z., Yang, Z., Tang, Y., Zhang, Y., Han, M., Xiao, J. Z., Ma, J., & Chang, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87234-2_13 · Cited by 17
“Table 2 shows the performance comparison of the triage screening task with different approaches, where Yala [30], Wu [28] and McKinney [21] are all previous SOTA models, alongside our proposed single-view and dual-view models with different SCP+SF training strategies.”
BackgroundMethodInfluentialCan AI Help Make Screening Mammography “Lean”?
Kontos, D., & Conant, E. F. (2019) · Radiology · doi:10.1148/radiol.2019191542 · Cited by 12
“Most deep learning applications in breast cancer screening have focused on classifying suspicious findings (6).”
BackgroundBernstein, M. H., Chung, M., Yala, A., & Baird, G. L. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001231 · Cited by 13
Self-citationMulticenter, Multivendor Validation of an FDA-approved Algorithm for Mammography Triage
Retson, T., Watanabe, A. T., Vu, H., & Chim, C. Y. (2022) · Journal of Breast Imaging · doi:10.1093/jbi/wbac046 · Cited by 11
Sabit, H., Yadav, A. K., Salimy, S., Sakr, A., Abdel-Ghany, S. E., Wadan, A. S., Alqosaibi, A. I., Rashwan, R., Algosaibi, S., Alnamshan, M. M., et al. (2026) · Cancer Letters · doi:10.1016/j.canlet.2026.218468 · Cited by 12
Burger, B., Bernathova, M., Seeböck, P., Singer, C. F., Helbich, T. H., & Langs, G. (2023) · European Radiology Experimental · doi:10.1186/s41747-023-00343-y · Cited by 12
“Furthermore, DL may reduce workload by being trained to triage negative screens [26, 27], which would allow radiologists to con - centrate only on suspicious scans.”
BackgroundArtificial intelligence‐driven change redefining radiology through interdisciplinary innovation
Huang, R., Meng, X., Zhang, X., Luo, Z., Cao, L., Feng, Q., Ma, G., Dong, D., & Wang, Y. (2025) · Interdisciplinary medicine · doi:10.1002/inmd.20240063 · Cited by 13
Images Are Data: A Breast Imaging Perspective on a Contemporary Paradigm
Dietzel, M., Clauser, P., Kapetas, P., Schulz‐Wendtland, R., & Baltzer, P. (2021) · RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren · doi:10.1055/a-1346-0095 · Cited by 9
“In this scenario, AI might potentially reduce the radiologist’s workload and gain extra time for the read of more cases and/or the assessment of challenging cases [5, 62, 63].”
BackgroundBhalla, D., Rangarajan, K., Chandra, T., Banerjee, S., & Arora, C. (2023) · Indian journal of radiology and imaging - new series/Indian journal of radiology and imaging/Indian Journal of Radiology & Imaging · doi:10.1055/s-0043-1775737 · Cited by 11
Bai, J., Jin, A., Adams, M., Yang, C., & Nabavi, S. (2024) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2024.102341 · Cited by 9
The Latest Trends in Attention Mechanisms and Their Application in Medical Imaging
Shin, H., Lee, J., Eo, T., Jun, Y., Kim, S., & Hwang, D. (2020) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2020.0150 · Cited by 10
“특히 의 료 영상 재구성(reconstruction), 합성(synthesis), 자동 분석(analysis) 및 판독(diagnosis) 등의 영상의학(medical imaging) 분야에서 괄목할 만한 연구들이 나오고 있다(5-12).”
Artificial Intelligence in Breast Imaging
Wang, X., Moriakov, N., Gao, Y., Zhang, T., Han, L., & Mann, R. M. (2022) · Medical radiology · doi:10.1007/978-3-030-94918-1_20 · Cited by 9
Seyyedi, S., Wong, M. J., Ikeda, D. M., & Langlotz, C. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.08563 · Cited by 9
“A recent study showed that a deep learning model trained on a subset of 66,661 screening mammograms has the potential to reduce radiologist workload and significantly improve specificity without harming sensitivity [13].”
BackgroundSossavi, E., Roy, C., & Molière, S. (2026) · European Journal of Radiology Open · doi:10.1016/j.ejro.2026.100727 · Cited by 10
“Triage workflows (gate-keeper [15,27], decision-referral [20,21] and MASAI-type risk allocation [19]) preserved cancer detection — RR 1.02 (0.98 – 1.07) — while reducing recalls by 11 % — RR 0.89 (0.82 – 0.96).”
InfluentialBassi, E., Russo, A., Oliboni, E. S., Zamboni, F., Santis, C. D., Mansueto, G., Montemezzi, S., & Foti, G. (2023) · La radiologia medica · doi:10.1007/s11547-023-01751-1 · Cited by 8
Supervised contrastive pre-training models for mammography screening
Cao, Z., Deng, Z., Yang, Z., Ma, J., & Ma, L. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01075-z · Cited by 11
“In the literature [3, 21, 39], mammographic screening models have been developed and tested only with large-scale private datasets conforming to the realistic patient distribution.”
Deng, Y., Huang, Y., Jing, B., Wu, H., Qiu, W., Chen, H., Li, B., Guo, X., Xie, C., Sun, Y. H., et al. (2023) · European Journal of Radiology · doi:10.1016/j.ejrad.2023.111084 · Cited by 8
Triage of 2D Mammographic Images Using Multi-view Multi-task Convolutional Neural Networks
Kyono, T., Gilbert, F. J., & van der Schaar, M. (2021) · ACM Transactions on Computing for Healthcare · doi:10.1145/3453166 · Cited by 8
“Recent works have applied deep learning to triage the negative mammograms from the radiologist [39, 75] and as a second reader [46, 55, 61].”
BackgroundShahrvini, T., Wood, E. J., Joines, M. M., Nguyen, H. B., Hoyt, A. C., Chalfant, J. S., Capiro, N. M., Fischer, C. P., Sayre, J. W., Hsu, W. W. Y., et al. (2025) · American Journal of Roentgenology · doi:10.2214/ajr.25.33412 · Cited by 7
The digital revolution in pathology: Towards a smarter approach to research and treatment
Tucci, F. A., Laurinavičius, A., Kather, J. N., & Eloy, C. (2024) · Tumori Journal · doi:10.1177/03008916241231035 · Cited by 8
“35 CNN showed also incredible success in the classification of skin cancer by training on a vast dataset of dermoscopic images.”
Artificial Intelligence to Support Independent Assessment of Screening Mammograms—The Time Has Come
Lehman, C. D. (2020) · JAMA Oncology · doi:10.1001/jamaoncol.2020.3186 · Cited by 7
Self-citationYouk, J. H., & Kim, E. (2022) · Korean Journal of Radiology · doi:10.3348/kjr.2021.0912 · Cited by 8
“A few other studies have reported the triage of screening mammograms using in-house deep-learning models or commercially available AI systems dedicated to cancer detection [13-16].”
BackgroundOgu, J. C., Ozcan, B. B., Doğan, B. E., Xi, Y., & Knippa, E. E. (2025) · Breast Cancer Research and Treatment · doi:10.1007/s10549-025-07870-9 · Cited by 7
Bhalla, D., Ramachandran, A., Rangarajan, K., Dhanakshirur, R. R., Banerjee, S., & Arora, C. (2022) · Current Problems in Diagnostic Radiology · doi:10.1067/j.cpradiol.2022.04.003 · Cited by 7
Meta-Repository of Screening Mammography Classifiers
Chłędowski, J., Stadnick, B., Witowski, J. S., Rajiv, V., Shamout, F. E., Cho, K., & Geras, K. J. (2025) · Studies in health technology and informatics · doi:10.3233/shti251263 · Cited by 6
Validation of a deep learning mammography model in a population with low screening ratesPreprint
Wu, K., Wu, E., Wu, Y., Tan, H., Sorensen, G., Wang, M., & Lotter, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00364 · Cited by 6
“For instance, a triage-style clinical implementation could significantly reduce overall workload for clinicians, while maintaining high diagnostic accuracy [4].”
BackgroundMarino, M. A., Avendaño, D., Sofia, C., Zapata, P., Portaluri, A., Orlando, A. A. M., Avalos-Montes, P. J., Blandino, A., Ascenti, G., & Cardona-Huerta, S. (2022) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405619666221128102209 · Cited by 8
van Winkel, S. L., Sechopoulos, I., Rodríguez‐Ruiz, A., Veldkamp, W. J. H., Gennaro, G., Chevalier, M. L., Helbich, T. H., Zhang, T., Wallis, M., & Mann, R. M. (2025) · Diagnostics · doi:10.3390/diagnostics15121566 · Cited by 6
VMRA-MaR: An Asymmetry-Aware Temporal Framework for Longitudinal Breast Cancer Risk Prediction
Sun, Z., Thrun, S., & Kampffmeyer, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05182-0_64 · Cited by 5
Confidence in radiology AI: From black-box scores to trusted decisions
Karunanayake, N. (2025) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2025.100046 · Cited by 5
Zhang, P., Ye, Z., Wei, R., Niu, H., Li, H., Wang, M., Xue, P., & Riggs, S. L. (2025) · Applied Ergonomics · doi:10.1016/j.apergo.2025.104663 · Cited by 6
Applications of Artificial Intelligence in Mammography from a Development and Validation Perspective
Kim, K. H., & Lee, S. H. (2021) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2020.0205 · Cited by 7
“미국 의 검진 코호트 자료에서도 다른 알고리즘을 이용하여 자동으로 음성 판정을 내리는 시뮬레이션 연구가 시행되었는데, 전체 검사의 20%를 줄이더라도 민감도 측면에서는 열등하지 않다(non-inferior)는 것을 보여주었다(56).”
Singh, S., & Healy, N. A. (2024) · Insights into Imaging · doi:10.1186/s13244-024-01869-4 · Cited by 5
“One paper with 108 citations published in Radiology used an AI software to triage screening mammograms [30].”
Mammography in 2022, from Computer-Aided Detection to Artificial Intelligence Applications
Pesapane, F., Trentin, C., Montesano, M., Ferrari, F., Nicosia, L., Rotili, A., Penco, S., Farina, M., Marinucci, I., Abbate, F., et al. (2022) · Clinical and Experimental Obstetrics & Gynecology · doi:10.31083/j.ceog4911237 · Cited by 7
“In a simulation study, a deep learning model performed triage of screening mammograms, demonstrating an improvement in radiologist efficiency and specificity, without decreasing of sensitivity [25].”
Rahimnezhad, A., Rezaeijo, S. M., Bayat, M. P., & Heydarheydari, S. (2025) · The Egyptian Journal of Radiology and Nuclear Medicine · doi:10.1186/s43055-025-01659-y · Cited by 4
“Evidence shows that AI, particularly deep learning models, can support breast cancer screening and diagnosis [9, 11], with performance in some studies comparable to or even exceeding that of experienced radiologists [12, 13].”
Adelsmayr, G., Janisch, M., Pohl, M., Fuchsjäger, M., & Schoellnast, H. (2024) · Digital Health · doi:10.1177/20552076241298472 · Cited by 4
Valentim, C. A., Mariuci, G., & David, S. A. (2025) · International Journal of Dynamics and Control · doi:10.1007/s40435-025-01642-5 · Cited by 4
Kim, H. J., Kim, H. H., Eom, H. J., Choi, W. J., Chae, E. Y., Shin, H. J., & Cha, J. H. (2025) · European Radiology · doi:10.1007/s00330-025-11849-x · Cited by 5
“The “ minimal-risk ” group included the lowest 20% of AI scores [13, 16, 19], which corresponded to a patient-level suspicion score of 0 for AI-1 and exam-level suspicion categories of 4 or lower for AI-2.”
InfluentialArtificial intelligence and interpretations in breast cancer imaging
Li, H., & Giger, M. L. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-821259-2.00015-6 · Cited by 5
Watanabe, A. T., Vu, H., Chim, C. Y., Litt, A. W., Retson, T., & Mayo, R. C. (2024) · Journal of Breast Imaging · doi:10.1093/jbi/wbae056 · Cited by 4
Bridging the Trust Gap in Artificial Intelligence for Health care: Lessons from Clinical Oncology
Cooney-Waterhouse, T., Ou, W., Mukherji, S., Frytak, J. R., Saha, P., & Waterhouse, D. M. (2025) · AI in Precision Oncology · doi:10.1089/aipo.2025.0001 · Cited by 4
Deciphering musculoskeletal artificial intelligence for clinical applications: how do I get started?
Mutasa, S., & Yi, P. H. (2021) · Skeletal Radiology · doi:10.1007/s00256-021-03850-4 · Cited by 4
Deep learning for detection of iso-dense, obscure masses in mammographically dense breasts
Rangarajan, K., Aggarwal, P., Gupta, D. K., Dhanakshirur, R. R., Baby, A., Pal, C., Gupta, A. K., Hari, S., Banerjee, S., & Arora, C. (2023) · European Radiology · doi:10.1007/s00330-023-09717-7 · Cited by 6
“Several recent studies have shown how deep learning networks have the potential to reduce clinical workloads by means of automated triage [18, 19].”
BackgroundArtificial Intelligence in Oncology: Present Potential, Prospective Prospects, And Ethical Reviews
Mahmood, A. A. R., Murgod, R., Badapanda, S. S., & Abraham, J. (2024) · International Journal of Trends in OncoScience · doi:10.22376/ijtos.2024.2.1.37-45 · Cited by 4
Problems and shortcuts in deep learning for screening mammographyPreprint
Tsue, T. T., Mombourquette, B., Taha, A., Matthews, T. P., Vu, Y. N. T., & Su, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.16417 · Cited by 4
Bong, J. H., Kim, T. H., & Jeong, S. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-880 · Cited by 3
“In a study by Yala et al. (34), a DL model was developed to triage mammograms as cancer free.”
FSE-Net: feature selection and enhancement network for mammogram classification
Liao, C., Wen, X., Qi, S., Liu, Y., & Cao, R. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acf559 · Cited by 4
IMPACTO DA INTELIGÊNCIA ARTIFICIAL NO DIAGNÓSTICO MÉDICO: DESAFIOS E OPORTUNIDADES
Magalhães, M. I. S., Vargas, C. V., Bomfim, V. V. B. D. S., Ferreira, T. G., & Behrens, P. D. A. C. (2024) · Revista Ibero-Americana de Humanidades, Ciências e Educação · doi:10.51891/rease.v10i1.12819 · Cited by 3
The impact of artificial intelligence on double reading of mammograms
Kudryavtsev, N. D., Kozhikhina, D. D., Goncharova, I. V., Михайлович, Ш. И., Sharova, D. E., Arzamasov, K. M., & Vladzymyrskyy, A. V. (2024) · Russian Journal of Preventive Medicine · doi:10.17116/profmed20242705132 · Cited by 3
Pre-biopsy Multi-class Classification of Breast Lesion Pathology in Mammograms
Tlusty, T., Ozery-Flato, M., Barros, V., Barkan, E., Amit, M., Gruen, D., Guindy, M., Arazi, T., Rozin, M., Rosen‐Zvi, M., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87589-3_29 · Cited by 3
Breast Cancer Detection Using Machine Learning
Sinha, A., Kumar, G., Khuman, L. Y., & Swamy, S. (2023) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2023.52223 · Cited by 3
Pesapane, F., Caumo, F., Mantellini, P., Irmici, G., Depretto, C., Penco, S., Rotili, A., Trentin, C., Dominelli, V., Corso, G., et al. (2026) · La radiologia medica · doi:10.1007/s11547-026-02217-w · Cited by 3
“In 2019, Yala et al. reported an early deep-learning model that analyzed prior “normal” mammograms to predict 5-year cancer risk [18].”
Zouzos, A., Milovanovic, A., Dembrower, K., & Strand, F. (2023) · JMIR AI · doi:10.2196/48123 · Cited by 3
“The AI CAD system had been validated by previous studies using a deep learning model to triage screening mammograms [11,19].”
MethodHuang, Y., Deng, Y., Liu, Y., Qiang, M., Qiu, W., Xia, W., Jing, B., Feng, C., Chen, H., Cao, X., et al. (2023) · iScience · doi:10.1016/j.isci.2023.108347 · Cited by 2
“Inspired by promising and recent advancements in human-computer interactions, 16–18, 29, 6 Most routine follow-up MR scans among these patients with complete remission (CR) of NPC show stable histological and structural changes induced by radiation that may not require manual review.”
BackgroundMunawir, A., Srigati, S. A., & Wulandari, P. (2023) · Ganesha Medicine · doi:10.23887/gm.v3i1.55575 · Cited by 2
The Potential Diagnostic Application of Artificial Intelligence in Breast Cancer
Behzadi, M., Azinfar, A., Alshakarchi, H. I., Khazaei, Y., Gataa, I. S., Ferns, G. A., Naderi, H., Avan, A., Fiuji, H., & Rad, M. P. (2025) · Current Pharmaceutical Design · doi:10.2174/0113816128369168250311172823 · Cited by 2
Artificial Intelligence as an Assistant in Breast Cancer Screening
Fuchsjäger, M. H., & Adelsmayr, G. (2021) · Radiology · doi:10.1148/radiol.212675 · Cited by 2
Automated Brain Abnormality Detection using a Self-Supervised Text-Vision FrameworkPreprint
Wood, D. A., Guilhem, E., Kafiabadi, S., Busaidi, A. A., Hammam, A., Mansoor, N. M., Townend, M., Agarwal, S., Wei, Y., Mazumder, A., et al. (2024) · doi:10.22541/au.171571444.45086524/v1 · Cited by 3
Govindarajan, K., & Narayanasamy, D. (2024) · Traitement du signal · doi:10.18280/ts.410302 · Cited by 1
“One popular and proven deep learning algorithm is CNN, which remarkably impacts image processing, segmentation, and recognition [15].”
BackgroundFuture Trends in AI and Smart Healthcare
Kaur, A., Sandhu, R., Kaur, G., & Ghai, D. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3311-3.ch015 · Cited by 1
Vijetha, J. K., Anitha, J., & Thilaka, M. K. (2025) · Journal of cancer research updates · doi:10.30683/1929-2279.2025.14.20 · Cited by 1
“[32] employed deep multi-instance to aggregate patch level features across whole images bridging local and global information.”
Fan, K. L., Thompson, Y. L. E., Chen, W., Abbey, C. K., & Samuelson, F. W. (2025) · Medical Decision Making · doi:10.1177/0272989x251388665 · Cited by 2
“…as a function of the percentage of patients excluded by the AI algorithm, using the AI thresholds in table E2 of the Appendix in Yala et al. 6 The blue line shows the percentage change of EU for different artificial intelligence (AI) thresholds, and the vertical error bars represent the…”
InfluentialMammography triage in the AI era: The original “real-time” triage is already in the room
Esmerer, E. U., & Nazlı, M. A. (2026) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2026.100085 · Cited by 1
Zhu, C., Zhang, R., Song, X., Shang, K., Lu, Y., Wu, W., Ma, J., Tang, Y., Cao, Z., Shen, L., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-76634-w · Cited by 1
“This may help allocate expert attention more effectively to the most time-sensitive cases 32 – 34 .”
Application of Genetic Algorithm in Predicting Mental Illness: A Case Study of Schizophrenia
Rabipour, S., & Asadi, Z. (2023) · Springer tracts in nature-inspired computing · doi:10.1007/978-981-99-3428-7_7 · Cited by 1
Application of Artificial Intelligence in Breast Imaging: Current Landscape and Prospects
Kim, H. J., & Kim, H. H. (2023) · Korean Journal of Family Practice · doi:10.21215/kjfp.2023.13.4.196 · Cited by 2
Africano, G., Arponen, O., Rinta-Kiikka, I. C., & Pertuz, S. D. (2023) · Acta Radiologica · doi:10.1177/02841851231218960 · Cited by 1
“These systems have been evaluated in different scenarios, including as stand-alone systems for breast cancer detection (7 – 9) and for reducing radiologist workload (10 – 12) and as a second reader (8,13).”
BackgroundUse of equivalent relative utility to evaluate artificial intelligence-based rule-out devices
Fan, K. L., Thompson, Y. L. E., Chen, W., Abbey, C. K., & Samuelson, F. W. (2024) · SPIE Medical Imaging: Image Perception, Observer Performance, and Technology Assessment · doi:10.1117/12.3008632 · Cited by 1
“As an example, Yala et al. 4 concluded that, at certain AI operating point, the with-device workflow significantly improved specificity (from 93.5% to 94.2”
BackgroundInfluentialRezayi, S., Nilashi, M., Esmaeeli, E., Ramezanghorbani, N., Arji, G., Ahmadi, H., Shahmoradi, L., & Zahmatkeshan, M. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11215-4 · Cited by 1
Tan, H., Wu, Q., Wu, Y., Zheng, B., Wang, B., Chen, Y., Du, L., Zhou, J., Fu, F., Guo, H., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-2489648/v1 · Cited by 1
Fractional mathematical oncology: cancer-related dynamics under an interdisciplinary viewpoint
Valentim, C. A. (2023) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.74.2023.tde-07112023-093919 · Cited by 2
Stop Training Artificial Intelligence Algorithms Now. Start Prospective Trials!
Nishikawa, R. M., & Sumkin, A. (2024) · Journal of Breast Imaging · doi:10.1093/jbi/wbae083 · Cited by 1
Sutton, C., Prowse, J., Elshehaly, M., & Randell, R. (2025) · medRxiv · doi:10.1101/2025.07.24.25332132 · Cited by 2
Found in Translation: Unpacking the Artificial Intelligence Revolution That Has Already Arrived
Woloshyn, O., Preiss, K., Rowe, S. P., Fishman, E. K., & Chu, L. C. H. (2020) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2020.02.018
Secure inference of quantized neural networks
Mehta, H. (2020) · DSpace@MIT (Massachusetts Institute of Technology)
ARTIFICIAL INTELLIGENCE TO INTERPRET MAMMOGRAMS- ARE WE THERE YET?
Sethi, D., Sachdev, N., & Singh, Y. (2020) · INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH · doi:10.36106/ijsr/6834881
Yoo, H., Kim, E. Y., Kim, H. J., Choi, Y. R., Cho, Y. J., & Jin, K. N. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3742292
9. Computerized Diagnostic Aid for Mammography Using Deep Learning
Muramatsu, C. (2021) · Japanese Journal of Radiological Technology · doi:10.6009/jjrt.2021_jsrt_77.5.489
Bilder sind Daten: Eine Perspektive der Brustbildgebung auf ein zeitgenössisches Paradigma
Dietzel, M., Clauser, P., Kapetas, P., Schulz‐Wendtland, R., & Baltzer, P. (2021) · Senologie - Zeitschrift für Mammadiagnostik und -therapie · doi:10.1055/a-1557-1062
“[63] Yala A, Schuster T, Miles R et al.”
BackgroundFujita, H. (2021) · Nihon Nyugan Kenshin Gakkaishi (Journal of Japan Association of Breast Cancer Screening) · doi:10.3804/jjabcs.30.121
Lång, K., & Levy, M. S. (2022) · Springer eBooks · doi:10.1007/978-3-030-91170-6_9
Breast Cancer Detection Using Machine Learning
Rathi, D., Rathad, C., Raskar, A., Randhave, O., & Rasal, M. (2022) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2022.47875
Artificial Intelligence in Breast Imaging
Bitencourt, A. G. V., & Pinker, K. (2023) · Springer eBooks · doi:10.1007/978-981-99-0035-0_36 · Cited by 1
Automated Brain Abnormality Detection using a Self-Supervised Text-Vision FrameworkPreprint
Wood, D. A., Guilhem, E., Kafiabadi, S., Busaidi, A. A., Hammam, A., Mansoor, N. M., Townend, M., Agarwal, S., Wei, Y., Mazumder, A., et al. (2024) · doi:10.22541/au.171571444.45086524/v2
A self-supervised framework for abnormality detection from brain MRIPreprint
Wood, D. A., Guilhem, E., Kafiabadi, S., Busaidi, A. A., Dissanayake, K., Hammam, A., Mansoor, N. M., Townend, M., Agarwal, S., Wei, Y., et al. (2024) · doi:10.22541/au.171900128.89392883/v1
Wolf, A. L., Hennrich, J., & Buck, C. (2024) · Springer eBooks · doi:10.1007/978-3-658-43860-9_34 · Cited by 1
da Silva, S. J. S., Shimazu, R. F., & Coelho, R. D. S. V. (2024) · Revista Multidisciplinar do Nordeste Mineiro · doi:10.61164/rmnm.v12i5.3339
Artificial Intelligence in Breast Imaging: Basic Principles for Radiologists
Rana, P., & Rangarajan, K. (2025) · Springer eBooks · doi:10.1007/978-981-97-9847-6_20
Inteligencia artificial en el diagnóstico por imagen de patología mamaria
Benito, M. Á., Elías-Cabot, E., & Romero-Martín, S. (2025) · Revista de Senología y Patología Mamaria · doi:10.1016/j.senol.2025.100684
De waarde van artificiële intelligentie bij mammografische borstkankerscreening
LASEURE, H., Ranschaert, E. R., & Verstraete, K. (2025) · Tijdschrift voor Geneeskunde · doi:10.47671/tvg.81.24.131
Wang, C., Li, C., & Lin, G. (2025) · Journal of Imaging · doi:10.3390/jimaging11070240
“In fact, DL algorithms have been applied in clinical diagnosis of breast cancer, lung cancer, prostate cancer classification, and screening [21,35–39], which proves the high diagnostic efficiency and capability of the DL models to reduce the workload of doctors.”
Şeker, M. E., & Ozkan, O. S. (2025) · European Radiology · doi:10.1007/s00330-025-12095-x
“…” by de fi ning minimal-risk and high-risk groups based on fi xed percentile thresholds (lowest 20% and highest 10% of AI scores, respectively) without con fi rming those thresholds within their speci fi c study cohort, referencing previously published literature for this methodology [1, 6 – 8].”
Mammography — well-known tool still in the mainstream
Łuczyńska, E., Heinze, S., Kozieł, W., Malisz, P., Brandt, Ł., Dobrowolska, M., Kulińska, K., & Rudnicki, W. (2025) · Nowotwory Journal of Oncology · doi:10.5603/njo.107799
Next-gen diagnostics: artificial intelligence-powered imaging in breast cancer care
Preetam, S., Bhattacharjee, S., Mishra, R., Muduli, K., Rustagi, S., Bora, J., Deshwal, R. K., Malik, S., & Gundamaraju, R. (2025) · Journal of Cancer Metastasis and Treatment · doi:10.20517/2394-4722.2025.74 · Cited by 2
Metadata
- Authors
- Yala, A., Schuster, T., Miles, R., Barzilay, R., & Lehman, C.
- Affiliations
- Harvard University (US)
- Venue
- Radiology
- Published
- 2019-10
- Volume
- 293
- Issue
- 1
- Pages
- 38-46
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2964642168
- Cited by
- 210
- References
- 22
- Citations by year
- 2026: 13 · 2025: 33 · 2024: 31 · 2023: 37 · 2022: 31 · 2021: 36 · 2020: 26 · 2019: 3
- FWCI
- 10.95
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Breast Cancer Alliance
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Digital Radiography and Breast Imaging
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- deep learning, mammography screening, triage, breast cancer screening, sensitivity and specificity, breast cancer detection, simulation study, non-inferiority margin, bootstrap confidence intervals, breast cancer mortality reduction, cost-effectiveness, false positive reduction
- MeSH terms
- Deep Learning, Adult, Aged, Aged, 80 and over, Breast, Breast Neoplasms, Computer Simulation, Female, Humans, Image Interpretation, Computer-Assisted, Mammography, Middle Aged, Registries, Retrospective Studies, Triage, Cohort Studies
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.