A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Background Mammographic density improves the accuracy of breast cancer risk models. However, the use of breast density is limited by subjective assessment, variation across radiologists, and restricted data. A mammography-based deep learning (DL) model may provide more accurate risk prediction. Purpose To develop a mammography-based DL breast cancer risk model that is more accurate than established clinical breast cancer risk models. Materials and Methods This retrospective study included 88 994 consecutive screening mammograms in 39 571 women between January 1, 2009, and December 31, 2012. For each patient, all examinations were assigned to either training, validation, or test sets, resulting in 71 689, 8554, and 8751 examinations, respectively. Cancer outcomes were obtained through linkage to a regional tumor registry. By using risk factor information from patient questionnaires and electronic medical records review, three models were developed to assess breast cancer risk within 5 years: a risk-factor-based logistic regression model (RF-LR) that used traditional risk factors, a DL model (image-only DL) that used mammograms alone, and a hybrid DL model that used both traditional risk factors and mammograms. Comparisons were made to an established breast cancer risk model that included breast density (Tyrer-Cuzick model, version 8 [TC]). Model performance was compared by using areas under the receiver operating characteristic curve (AUCs) with DeLong test (P < .05). Results The test set included 3937 women, aged 56.20 years ± 10.04. Hybrid DL and image-only DL showed AUCs of 0.70 (95% confidence interval [CI]: 0.66, 0.75) and 0.68 (95% CI: 0.64, 0.73), respectively. RF-LR and TC showed AUCs of 0.67 (95% CI: 0.62, 0.72) and 0.62 (95% CI: 0.57, 0.66), respectively. Hybrid DL showed a significantly higher AUC (0.70) than TC (0.62; P < .001) and RF-LR (0.67; P = .01). Conclusion Deep learning models that use full-field mammograms yield substantially improved risk discrimination compared with the Tyrer-Cuzick (version 8) model. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Sitek and Wolfe 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
“Because AI-enabled diagnostic technology has made significant advances in radiology23,24, we recruited physicians with different levels of task expertise to perform a radiological task.”
From Do as AI say: susceptibility in deployment of clinical decision-aids (2021) · cites this paper as [23]
In the citing paper
“Radiological data has been combined with other data types for predictive AI systems in various clinical disciplines like oncology21–24 or neurology25,26.”
From Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging (2024) · cites this paper as [21]
In the citing paper
“Spasov et al.36, Yala et al.37, and Yoo et al.38 implemented CNNs to learn image features and fused these feature representations with clinical features before feeding them into a feed-forward neural network.”
From Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines (2020) · cites this paper as [37]
In the citing paper
“Kawahara et al., Yala et al. and Yoo et al. reported an improvement in performance using fusion compared to image-only models (Table 1).”
From Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines (2020) · cites this paper as [37]
In the citing paper
“Spasov et al. and Yala. et al. both used simple concatenation to fuse the learned imaging and clinical features.”
From Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines (2020) · cites this paper as [37]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
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 1×
“For the image-only DL model, we implemented a deep convolutional neural network (ResNet18 [13]) with PyTorch (version 0.31; pytorch.org ).”
MethodInfluentialDeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087
Gail, M. H., Brinton, L. A., Byar, D. P., Corle, D. K., Green, S. B., Schairer, C., & Mulvihill, J. J. (1989) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/81.24.1879 · Cited by 3,334 · cited 1×
“Also, some patients were missing risk factor information, though this limitation is common in both clinical practice and previous studies (1,3–5).”
BackgroundLearning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
A breast cancer prediction model incorporating familial and personal risk factors
Tyrer, J., Duffy, S. W., & Cuzick, J. (2004) · Statistics in Medicine · doi:10.1002/sim.1668 · Cited by 1,345
Boyd, N. F., Byng, J. W., Jong, R. A., Fishell, E. K., Little, L. E., Miller, A. B., Lockwood, G. A., Tritchler, D. L., & Yaffe, M. J. (1995) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/87.9.670 · Cited by 1,105
Effect of Hormone Replacement Therapy on Breast Cancer Risk: Estrogen Versus Estrogen Plus Progestin
Ross, R. K. (2000) · Journal of the National Cancer Institute · doi:10.1093/jnci/92.4.328 · Cited by 877
Cited by
Items 201–300 of 804
Algorithm, Human, or the Centaur: How to Enhance Clinical Care?Preprint
Dean, A., Orfanoudaki, A., Saghafian, S., Song, K., Chakkera, H. A., & Cook, C. B. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4302002 · Cited by 38
“An increasing number of studies show that they can improve physician performance in complex tasks, such as tumor detection and diagnosis of cancer at an earlier stage compared to world-class specialists (Golden 2017, Yala et al. 2019).”
BackgroundMascarenhas, M., Martins, M., Ribeiro, T., Afonso, J. P. L., Cardoso, P., Mendes, F., Cardoso, H., Almeida, R., Ferreira, J. P. S., Fonseca, J., et al. (2024) · Diagnostics · doi:10.3390/diagnostics14182100 · Cited by 31
“Thus, initiatives will be necessary to ensure the SaMD development complies with ethical standards, such as those aimed at preventing bias in data and algorithms [48,49].”
BackgroundRibelles, N., Jerez, J. M., Rodríguez-Brazzarola, P., Jiménez, B., Díaz-Redondo, T., Mesa, H., Márquez, A., Sánchez‐Muñoz, A., Pajares, B., Carabantes, F., et al. (2020) · European Journal of Cancer · doi:10.1016/j.ejca.2020.11.030 · Cited by 28
Research on Rice Yield Prediction Model Based on Deep Learning
Han, X., Liu, F., He, X., & Ling, F. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/1922561 · Cited by 26
“In addition, the networks with good effect in the field of target detection have also been applied to the field of instance segmentation, and achieved good segmentation results, such as regional convolution network (R–CNN) [26], FAST R–CNN [27], Faster R–CNN [28], Maskr-CNN [29], and so on.”
MethodGaba, A., Kaufman, Z., Cheung, J., Shvakel, M., Hall, K. W., Brun, Y., & Xiong, C. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3327192 · Cited by 35
Pesapane, F., Battaglia, O., Pellegrino, G., Mangione, E., Petitto, S., Manna, E. D. F., Cazzaniga, L., Nicosia, L., Lazzeroni, M., Corso, G., et al. (2023) · Future Oncology · doi:10.2217/fon-2023-0365 · Cited by 30
Vivas, Á. J., Boumediene, S., & Tobón, G. J. (2024) · Autoimmunity Reviews · doi:10.1016/j.autrev.2024.103611 · Cited by 29
Radiomics, deep learning and early diagnosis in oncology
Wei, P. (2021) · Emerging Topics in Life Sciences · doi:10.1042/etls20210218 · Cited by 32
Hendrix, N., Lowry, K. P., Elmore, J. G., Lotter, W., Sorensen, G., Hsu, W., Liao, G. J., Parsian, S., Kolb, S., Naeim, A., et al. (2022) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2022.06.019 · Cited by 25
Barros, V., Tlusty, T., Barkan, E., Hexter, E., Gruen, D., Guindy, M., & Rosen‐Zvi, M. (2022) · Radiology · doi:10.1148/radiol.220027 · Cited by 28
Machine learning in oncology: a review
Nardini, C. (2020) · ecancermedicalscience · doi:10.3332/ecancer.2020.1065 · Cited by 26
“For example, a ML system may learn how to recognise particular structures in mammograms that are associated with higher breast cancer risk [19] or perform Gleason scoring of prostate cancers [12] or classify skin cancers based on the visual appearance of lesions [7].”
BackgroundThe impact of AI on modern oncology from early detection to personalized cancer treatment
Li, J., Zhang, L., Yu, Z., Bao, Z., Li, D., & Wang, L. (2026) · npj Precision Oncology · doi:10.1038/s41698-026-01276-6 · Cited by 24
“Studies have shownthat Table 1 | Inclusion and exclusion criteria the DL model integrating mammographic features with established risk factors outperformed conventional breast cancer risk models in identifying individuals at the highest risk of malignancy 111,112 .”
Mahmood, U. A., Shrestha, R., Bates, . D. B., Mannelli, L., Corrias, G., Erdi, Y. E., & Kanan, C. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.671015 · Cited by 30
“Artificially intelligent (AI) computer-aided diagnostic (CAD) systems have the potential to help radiologists on a multitude of tasks, ranging from tumor classification to improved image reconstruction (Jin et al., 2021; El Naqa et al., 2020; Yala et al., 2019; Antonelli et al., 2019).”
BackgroundMichel, A. M., Ro, V., McGuinness, J. E., Mutasa, S., Terry, M. B., Tehranifar, P., May, B. L., Ha, R. S., & Crew, K. D. (2023) · Breast Cancer Research and Treatment · doi:10.1007/s10549-023-06966-4 · Cited by 26
“Yala et al . found that an image-based DL model outperformed the Tyrer-Cuzick breast cancer risk model, but also showed that a hybrid model of DL and clinical risk factors predicted breast cancer better than either method alone (AUC = 0.70, 95% CI = 0.66–0.75 for the hybrid model) [25].”
MethodInfluentialUse of artificial intelligence in breast surgery: a narrative review
Seth, I., Lim, B., Joseph, K., Gracias, D., Xie, Y., Ross, R. J., & Rozen, W. M. (2024) · Gland Surgery · doi:10.21037/gs-23-414 · Cited by 22
“Moreover, AI-based models have been proven efficacious in predicting the risk of developing breast cancer in the future by utilizing data collected from DM images (53,54).”
Young, M. R., Abrams, N., Ghosh, S., Rinaudo, J. A., Márquez, G., & Srivastava, S. (2020) · Pancreas · doi:10.1097/mpa.0000000000001603 · Cited by 25
MGBN: Convolutional neural networks for automated benign and malignant breast masses classification
Lou, M., Wang, R., Qi, Y., Zhao, W., Xu, C., Meng, J., Deng, X., & Ma, Y. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10929-6 · Cited by 26
Longitudinal Mammogram Risk Prediction
Karaman, B. K., Dodelzon, K., Akar, G. B., & Sabuncu, M. R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72086-4_41 · Cited by 30
Vo, H. Q., Wong, K., Wong, K. K., Ezeana, C. F., Yu, X., Yang, W., Chang, J. C., Nguyen, H. V., & Wong, S. T. C. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3507638 · Cited by 27
“…[21], [22], [23], [24], [25], while the other aims to differentiate between benign and malignant abnormalities using biopsy data [26], [27], [28], [29], [30], [31], [32], [33], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52].”
Enhancing clinical trial outcome prediction with artificial intelligence: a systematic review
Qian, L., Lu, X., Haris, P. I., Zhu, J., Li, S., & Yang, Y. (2025) · Drug Discovery Today · doi:10.1016/j.drudis.2025.104332 · Cited by 29
Stern, A. D., Goldfarb, A., Minssen, T., & Price, W. N. (2022) · NEJM Catalyst · doi:10.1056/cat.21.0242 · Cited by 40
Edmonds, C. E., O’Brien, S. R., & Conant, E. F. (2022) · Seminars in Ultrasound CT and MRI · doi:10.1053/j.sult.2022.11.001 · Cited by 23
Al-Yaseen, W. L., Jehad, A., Abed, Q. A., & Idrees, A. K. (2021) · International journal of intelligent engineering and systems · doi:10.22266/ijies2021.0430.17 · Cited by 23
“In the last years, various sophisticated methods based on machine learning techniques have been used to help the early diagnosis of breast cancer such as support vector machines (SVM) [3-5], multilayer perceptrons (MLPs) [6, 7] and logistic regression (LR) [8-10].”
MethodA divide and conquer approach to maximise deep learning mammography classification accuracies
Jaamour, A., Myles, C., Patel, A., Chen, S.-J., McMillan, L., & Harris‐Birtill, D. (2023) · PLoS ONE · doi:10.1371/journal.pone.0280841 · Cited by 27
A convolutional deep learning model for improving mammographic breast-microcalcification diagnosis
Kang, D., Gweon, H. M., Eun, N. L., Youk, J. H., Kim, J., & Son, E. J. (2021) · Scientific Reports · doi:10.1038/s41598-021-03516-0 · Cited by 24
Artificial intelligence in breast imaging: potentials and challenges
Li, J.-W., Sheng, D., Chen, J., You, C., Liu, S., Xu, H., & Chang, C. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acfade · Cited by 23
Healthcare’s new Frontier: AI-driven early cancer detection for improved well-being
Deepa, R., Arunkumar, S., Jayaraj, V., & Sivasamy, A. (2023) · AIP Advances · doi:10.1063/5.0177640 · Cited by 25
Artzi, M., Redmard, E., Tzemach, O., Zeltser, J., Gropper, O., Roth, J., Shofty, B., Kozyrev, D. A., Constantini, S., & Ben‐Sira, L. (2021) · IEEE Access · doi:10.1109/access.2021.3085771 · Cited by 24
Dianatinasab, M., Salimifard, K., Mohammadi, R., Saadatmand, S., Fararouei, M., Hosseini, K. S., Jiavid-Sharifi, B., Chaussalet, T., & Dehdar, S. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2023.1276232 · Cited by 23
Dubois, C., Eigen, D., Delmas, E., Einfalt, M., Lemaçon, C., Berteloot, L., Bossuyt, P. M., Drummond, D., Scherdel, P., Simon, F., et al. (2024) · BMJ · doi:10.1136/bmj-2023-076703 · Cited by 23
Chen, X., Li, Y., Hu, M., Salari, E., Chen, X., Qiu, R. L. J., Zheng, B., & Yang, X. (2026) · Medical Physics · doi:10.1002/mp.70261 · Cited by 25
“…schemes than the traditional machine learning technologies using hand-crafted features or automatically computed radiomics features with generally higher performance, 7–9 most existing CAD schemes using deep learning models are still single image based schemes trained solely on one-view mammogram.”
Humans and machines: Moving towards a more symbiotic approach to learning clinical reasoning
Pinnock, R., McDonald, J., Ritchie, D., & Durning, S. J. (2019) · Medical Teacher · doi:10.1080/0142159x.2019.1679361 · Cited by 23
Salih, M., Austin, C., Mantravadi, K., Seow, E., Jitanantawittaya, S., Reddy, S., Vollenhoven, B. J., Rezatofighi, H., & Horta, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-02076-x · Cited by 25
“…it could be argued that the integration of images to clinical data does not improve predictive performance as observed in different disciplines 49,59,60,62 , this could of benefit in the IVF industry as current AI applications are currently only considering images or timelapse videos without…”
The application of artificial intelligence to chest medical image analysis
Liu, F., Tang, J., Ma, J., Wang, C., Ha, Q., Yu, Y., & Zhou, Z. (2021) · Intelligent Medicine · doi:10.1016/j.imed.2021.06.004 · Cited by 22
Feature-level ensemble approach for COVID-19 detection using chest X-ray images
Ho, T. K. K., & Gwak, J. (2022) · PLoS ONE · doi:10.1371/journal.pone.0268430 · Cited by 22
“In particular, DL techniques have successfully been used to diagnose various diseases including the detection of brain tumors from MRI images [10, 11], multiple types of brain disorders from electroencephalograms (EEGs) [12, 13], the levels of mental workloads using functional near-infrared spectroscopy (fNIRS) [14, 1…”
MethodChen, Y., Wang, L., Luo, R., Wang, S., Wang, H., Gao, F., & Wang, D. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.943415 · Cited by 22
“The pipeline of the system consisting of CNN and Faster R-CNN. were lower than those for mass, while the positive predictive value (PPV), sensitivity, and accuracy for non-mass enhancement were slightly higher than those for mass (Figures 7, 8).”
MethodRigaud, B., Weaver, O. O., Dennison, J. B., Awais, M., Anderson, B. M., Chiang, T.-Y. D., Yang, W. T., Leung, J. W. T., Hanash, S., & Brock, K. K. (2022) · Cancers · doi:10.3390/cancers14205003 · Cited by 20
Uncertainty estimation for deep learning-based pectoral muscle segmentation via Monte Carlo dropout
Klaneček, Ž., Wagner, T., Wang, Y., Cockmartin, L., Marshall, N., Schott, B., Deatsch, A. E., Studen, A., Hertl, K., Jarm, K., et al. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acd221 · Cited by 25
“…(CAD) could be beneficial in breast cancer screening programs, especially for tasks such as breast density estimation (Gastounioti et al 2020), breast cancer risk prediction (Yala et al 2019, 2021) and quality assurance ofmammograms (Waade et al 2021, Picard et al 2022,Wadden andHapgood 2022).”
BackgroundMethodHashimoto, N., Hanada, H., Miyoshi, H., Nagaishi, M., Sato, K., Hontani, H., Ohshima, K., & Takeuchi, I. (2023) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2023.100359 · Cited by 28
“For example, Yala et al. 18 improvedrisk prediction bycombining mammography imagesand conventional risk factors.”
BackgroundPertuz, S. D., Sassi, A., Holli-Helenius, K., Kämäräinen, J., Rinta-Kiikka, I. C., Lääperi, A.-L., & Arponen, O. (2019) · European Journal of Radiology · doi:10.1016/j.ejrad.2019.108710 · Cited by 20
Salas, J., Vidal, F. D. B., & Martinez-Trinidad, F. (2019) · IEEE Latin America Transactions · doi:10.1109/tla.2019.9011537 · Cited by 21
Thilagaraj, M., Arunkumar, N., & Govindan, P. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/6785707 · Cited by 20
“Reference [21] presented a deep learning technique. process is developed to improve breast cancer risk prediction. breast cancer database is taken from a larger tertiary academic medical centre. mammograms are filtered to analyze the function. dataset is validated to analyze the data.”
BackgroundRetractedSynthesizing lesions using contextual GANs improves breast cancer classification on mammogramsPreprint
Wu, E., Wu, K., & Lotter, W. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.00086 · Cited by 30
“Common to many machine learning applications in healthcare, developing algorithms for breast cancer detection in mammography [10, 13, 14, 7, 17, 8, 9, 11] is heavily prone to overfitting given the difficulty in collecting large amounts of positive examples.”
BackgroundAl-Dekah, A. M., & Sweileh, W. M. (2025) · BMJ Open · doi:10.1136/bmjopen-2025-101169 · Cited by 21
Gao, W., Manning, J. C., Devaraj, K., Richards-Kortum, R. R., McFall, S. M., Murphy, R. L., Semeere, A., & Erickson, D. (2025) · JCO Global Oncology · doi:10.1200/go-25-00142 · Cited by 24
New Horizons: Artificial Intelligence for Digital Breast Tomosynthesis
Goldberg, J. E., Reig, B., Lewin, A. A., Gao, Y., Heacock, L. C., Heller, S. L., & Moy, L. P. (2022) · Radiographics · doi:10.1148/rg.220060 · Cited by 23
An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring
Bhaskhar, N., Rubin, D. L., & Lee‐Messer, C. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3272876 · Cited by 20
Liu, Y., Sorkhei, M., Dembrower, K., Azizpour, H., Strand, F., & Smith, K. (2024) · Radiology · doi:10.1148/radiol.232535 · Cited by 22
Ellis, S., Gomes, S., Trumble, M., Halling‐Brown, M., Young, K. C., Chaudhry, N. S., Harris, P. M., & Warren, L. M. (2024) · Radiology Artificial Intelligence · doi:10.1148/ryai.230431 · Cited by 26
Öztekin, P. S., KATAR, O., Omma, T., Erel, S., Tokur, O., Avcı, D., Aydoğan, M., Yıldırım, Ö., Avcı, E., & Acharya, U. R. (2024) · Journal of Ultrasound in Medicine · doi:10.1002/jum.16535 · Cited by 24
Jones, E. F., Hathi, D., Freimanis, R. I., Mukhtar, R. A., Chien, A. J., Esserman, L. J., Veer, L. J. V., Joe, B. N., & Hylton, N. M. (2020) · Cancers · doi:10.3390/cancers12061511 · Cited by 20
“Deep-learning [195] of mammographic images has been increasingly used to aid breast cancer detection [196], prediction of breast cancer risks [197,198], and identification of significant microcalcifications evaluation [199].”
Lehman, C. D., Mercaldo, S. F., Wang, G. X., Dontchos, B. N., Specht, M. C., & Lamb, L. R. (2021) · American Journal of Roentgenology · doi:10.2214/ajr.21.26890 · Cited by 20
Self-citationPicón, A., Bereciartua, A., Egusquiza, I., Romero-Rodriguez, J., Jimenez-Ruiz, C. J., Eggers, T., Klukas, C., & Navarra-Mestre, R. (2022) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2022.09.004 · Cited by 27
Ye, R. Z., Subramanian, A., Diedrich, D. A., Lindroth, H. L., Pickering, B. W., & Herasevich, V. (2022) · Journal of Imaging · doi:10.3390/jimaging8120330 · Cited by 25
Role of calibration in uncertainty-based referral for deep learning
Zhang, R., Gatsonis, C. A., & Steingrimsson, J. A. (2023) · Statistical Methods in Medical Research · doi:10.1177/09622802231158811 · Cited by 21
“…in cardiovascular imaging; Yao et al. 5 summarized recent literature in neuroradiology and highlighted directions for future work; Yala et al. 6,7 studied mammography-based models for improving breast cancer risk prediction and triage efficiency, and Geras et al. 8 outlined current status and…”
BackgroundStrategic Applications of Artificial Intelligence in Healthcare and Medicine
Chan, C. Y. T., & Petrikat, D. (2023) · Journal of Medical and Health Studies · doi:10.32996/jmhs.2023.4.3.8 · Cited by 23
Tan, H., Wu, Q., Wu, Y., Zheng, B., Wang, B., Chen, Y., Du, L., Zhou, J., Fu, F., Guo, H., et al. (2025) · Insights into Imaging · doi:10.1186/s13244-025-01983-x · Cited by 23
“Recent advances in deep learning-based arti fi cial intelligence (AI) methods [13 – 17] have exhibited great potential in breast cancer detection and diagnosis.”
May, A., Gesell‐May, S., Müller, T., & Ertel, W. (2021) · Equine Veterinary Journal · doi:10.1111/evj.13528 · Cited by 17
Chakravarthy, S. R. S., Bharanidharan, N., & Rajaguru, H. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15265-5 · Cited by 19
“Many research works are being proposed based on deep-learning approaches for breast cancer diagnosis [37, 42, 43].”
BackgroundRobustness of Deep Networks for Mammography: Replication Across Public Datasets
Velarde, O. M., Lin, C., Eskreis‐Winkler, S., & Parra, L. C. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-023-00943-5 · Cited by 21
“Lastly, Yala et al. [27] introduced a risk prediction model that leverages a high-level representation at the exam level to predict risk factors (e.g., age and breast density) in situations where these factors are unavailable, and this model exhibited enhanced risk discrimination compared to the…”
BackgroundDeep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study
Liu, C., Sun, M., Arefan, D., Zuley, M. L., Sumkin, J. H., & Wu, S. (2024) · Breast Cancer Research · doi:10.1186/s13058-024-01830-9 · Cited by 17
A Complete Study on Machine Learning Algorithms for Medical Data Analysis
Kaur, I., & Ali, A. A. (2024) · Wiley eBooks · doi:10.1002/9781394175345.ch7 · Cited by 17
Conte, L., Rizzo, E., Civino, E., Tarantino, P., Nunzio, G. D., & Matteis, E. D. (2024) · Applied Sciences · doi:10.3390/app14188474 · Cited by 21
“For example, [40] demonstrated that ML models, due to their inherent non-linearity, achieved equivalent (and superior) performance across different ethnicities compared with the Tyrer–Cuzick model, which showed significant differences in the AUC values for white and African American women.”
Decoupling Inherent Risk and Early Cancer Signs in Image-Based Breast Cancer Risk Models
Liu, Y., Azizpour, H., Strand, F., & Smith, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59725-2_23 · Cited by 22
Artificial intelligence for the real world of breast screening
Wallis, M. (2021) · European Journal of Radiology · doi:10.1016/j.ejrad.2021.109661 · Cited by 19
Artificial Intelligence in the Era of Precision Oncological Imaging
Cellina, M. I., Cè, M., Khenkina, N., Sinichich, P., Cervelli, M., Poggi, V., Boemi, S., Ierardi, A. M., & Carrafiello, G. (2022) · Technology in Cancer Research & Treatment · doi:10.1177/15330338221141793 · Cited by 23
“The hybrid model placed 31% of patients in the top risk category, compared with 18% identified by the IBIS/TC model, and was able to identify the features associated with long-term risk beyond early detection of the disease.(27) Another aspect related to risk stratification includes the assessment of incidentally disc…”
BackgroundArtificial Intelligence in Breast X-Ray Imaging
Vedantham, S., Shazeeb, M. S., Chiang, J. A., & Vijayaraghavan, G. R. (2022) · Seminars in Ultrasound CT and MRI · doi:10.1053/j.sult.2022.12.002 · Cited by 19
Ramsdale, E. E., Snyder, E., Culakova, E., Xu, H., Dziorny, A. C., Yang, S., Zand, M. S., & Anand, A. (2021) · Journal of Geriatric Oncology · doi:10.1016/j.jgo.2021.03.012 · Cited by 16
A Pictorial Exploration of Mammary Paget Disease: Insights and Perspectives
Mariano, L., Nicosia, L., Pupo, D., Olivieri, A. M., Scolari, S., Pesapane, F., Latronico, A., Bozzini, A. C., Fusco, N., Blanco, M. C., et al. (2023) · Cancers · doi:10.3390/cancers15215276 · Cited by 16
“Mirai, a deep-learning-based mammography risk model, integrates DM features and clinical factors to predict BC risk within a 5-year timeframe, showing robust validation across diverse international datasets [69].”
BackgroundSpatiotemporal Mammography-based Deep Learning Model for Improved Breast Cancer Risk Prediction
Melek, A., Fakhry, S., & Basha, T. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340602 · Cited by 17
“Deep learning approaches and Convolutional Neural Networks (CNNs) in particular can exploit the imaging features and subtle cues in the mammograms which are the standard imaging technique in breast cancer screening [14]–[16].”
BackgroundResultLongitudinal interpretability of deep learning based breast cancer risk prediction
Klaneček, Ž., Wang, Y., Wagner, T., Cockmartin, L., Marshall, N., Schott, B., Deatsch, A. E., Studen, A., Jarm, K., Krajc, M., et al. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad9db3 · Cited by 17
“With the emergence of deep learning (DL), state-of-the-art BCR prediction models (Yala et al 2019, 2021, Dembrower et al 2020) no longer rely solely on traditional risk factors, such as age, family history and genetics, but also integrate mammography images acquired during screening.”
AI in 2D Mammography: Improving Breast Cancer Screening Accuracy
Ciurescu, S., Cerbu, S., Dima, C. N., Borozan, F., Pârvănescu, R., Ilaș, D. G., Cîtu, C., Vernic, C., & Sas, I. (2025) · Medicina · doi:10.3390/medicina61050809 · Cited by 16
“While digital mammography has improved image quality and diagnostic precision compared to film-based mammography, the inherent limitations of 2D imaging persist, particularly in women with dense breast tissue, where sensitivity is significantly reduced [6,7].”
MammoDG: Generalisable Deep Learning Advances Cross-Domain Multi-Center Breast Cancer Screening
Yang, Y., Wang, S., Liu, L., Hickman, S. E., Gilbert, F. J., Schönlieb, C., & Avilés-Rivero, A. I. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02979-w · Cited by 18
“…for mammography cancer diagnosis can be broadly divided into three main categories: 1) single view-based models (Zhu et al., 2017b; Wu et al., 2019; Yala et al., 2019); 2) multiple view-based models (Geras et al., 2017; Khan et al., 2019; Zhao et al., 2020; Wei et al., 2022); and 3) patch-based…”
Optimization of Electronic Medical Records for Data Mining Using a Common Data Model
Kwong, M., Gardner, H. L., Dieterle, N., & Rentko, V. T. (2019) · Topics in companion animal medicine · doi:10.1016/j.tcam.2019.100364 · Cited by 17
“When compared with established diagnosis approaches, the incorporation of data mining efforts improved risk assessment modeling in this population of women.(5)”
ResultJiang, J., Lei, S., Zhu, M., Li, R., Yue, J., Chen, J., Li, Z., Gong, J., Lin, D., Wu, X., et al. (2021) · Frontiers in Medicine · doi:10.3389/fmed.2021.664023 · Cited by 18
“…learning, hold great promise in the automatic diagnosis of extensive diseases based on medical images, such as infantile cataracts (1– 4), diabetic retinopathy (5, 6), age-related macular degeneration (7, 8), glaucoma (9), breast cancer (10, 11), skin cancer (12), and autism spectrum disorder (13).”
BackgroundAlshutbi, M., Li, Z., Alrifaey, M., Ahmadipour, M., & Othman, M. M. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07290-6 · Cited by 16
Resting state network mapping in individuals using deep learning
Luckett, P. H., Lee, J. J., Park, K. Y., Raut, R. V., Meeker, K. L., Gordon, E. M., Snyder, A. Z., Ances, B. M., Leuthardt, E. C., & Shimony, J. S. (2023) · Frontiers in Neurology · doi:10.3389/fneur.2022.1055437 · Cited by 19
Li, D., Raymond, L., & Bergman, P. (2025) · The Review of Economic Studies · doi:10.1093/restud/rdaf040 · Cited by 32
(2026) · International Journal of Drug Delivery Technology · doi:10.25258/ijddt.16.65s.21 · Cited by 15
(2026) · International Journal of Drug Delivery Technology · doi:10.25258/ijddt.16.65s.22 · Cited by 15
Deep Learning in Lung and Colon Cancer classifications
Mridha, K., Islam, M. I., Ashfaq, S., Priyok, M. A., & Barua, D. (2022) · International Conference on Advances in Computing, Communication and Materials (ICACCM) · doi:10.1109/icaccm56405.2022.10009311 · Cited by 15
Expert and deep learning model identification of iEEG seizures and seizure onset times
Desai, S. A., Afzal, M. F., Barry, W., Kuo, J. T. W., Benard, S. W., Traner, C. B., Tcheng, T. K., Seale, C. G., & Morrell, M. J. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1156838 · Cited by 16
“Even in the medical field, several studies have leveraged deep neural networks to identify abnormalities in MRIs, mammograms, and retinal images with a high degree of confidence (Ting et al., 2017; Lundervold and Lundervold, 2019; Yala et al., 2019).”
BackgroundArtificial intelligence methods available for cancer research
Murmu, A., & Győrffy, B. (2024) · Frontiers of Medicine · doi:10.1007/s11684-024-1085-3 · Cited by 18
Yeoh, H. H., Liew, A., Phan, R. C. W., Strand, F., Rahmat, K., Nguyen, T. L., & Tan, M. (2025) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ae1ee4 · Cited by 16
“Image-based deep learning models (Aan et al 2019, Yala et al 2019, 2021) have shown very promising results and suggest that deep learning has the ability to recognize more predictive information in mammograms than traditional risk models.”
Hung, P., Lin, J., Chen, C., Hung, K.-Y., Hsieh, T.-Y., Hsu, M., Kuo, H.-C., & Lin, Y.-J. (2020) · Nutrients · doi:10.3390/nu13010021 · Cited by 18
“Biochemical parameters, including βHB and plasma acylcarnitines [19] and amino acid levels were compared in and between groups at the various time points by conducting generalized estimating equation (GEE) after adjusting confounding effect of anticonvulsants.”
MethodVenugopal, V. K., Takhar, R., Gupta, S. K., Saboo, A., & Mahajan, V. (2022) · Journal of Medical Systems · doi:10.1007/s10916-022-01806-2 · Cited by 15
Breast cancer screening in average-risk women: towards personalized screening
Bitencourt, A. G. V., Saccarelli, C. R., Kuhl, C. K., & Morris, E. A. (2019) · British Journal of Radiology · doi:10.1259/bjr.20190660 · Cited by 15
Basic Artificial Intelligence Techniques
Kalpathy–Cramer, J., Patel, J., Bridge, C. P., & Chang, K. (2021) · Radiologic Clinics of North America · doi:10.1016/j.rcl.2021.06.005 · Cited by 17
Promoting health equity through improved regulation of artificial intelligence medical devices
Dortche, K., McCarthy, G., Banbury, S., & Yannatos, I. (2023) · Journal of Science Policy & Governance · doi:10.38126/jspg210302 · Cited by 14
“For example, while a traditional model for breast cancer risk was more accurate for White than African American women, an AI model showed more accurate overall results and equal accuracy across racial groups (Yala et al. 2019). ii.”
Result(2026) · International Journal of Drug Delivery Technology · doi:10.25258/ijddt.16.65s.20 · Cited by 14
Lamb, L. R., Mercaldo, S. F., Ghaderi, K. F., Carney, A. S., & Lehman, C. D. (2023) · Radiology · doi:10.1148/radiol.223077 · Cited by 15
Self-citationLi, H., Zhao, Y., Duan, J., Gu, J., Liu, Z., Zhang, H., Zhang, Y., & Li, Z. (2024) · Displays · doi:10.1016/j.displa.2024.102698 · Cited by 16
Wang, S., Jiang, Y., Che, L., Wang, R. H., & Li, S. C. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae515 · Cited by 16
Yin, L., Zhang, Y., Qin, R., Xiang, L.-L., Zhang, Q., Wu, T. F., Shaibu, Z., Fang, Y., Xiao, X., & Shan, X.-H. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1385352 · Cited by 14
“AI-based models have demonstrated remarkable accuracy in cancer prediction and therapeutic ef fi cacy based on genetics and hormonal parameters (34, 35).”
MethodJannatdoust, P., Valizadeh, P., Saeedi, N., Valizadeh, G., Salari, H. M., Rad, H. S., & Gity, M. (2025) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.29687 · Cited by 17
“128,129 Another area of research involves using generative AI models to automatically generate standardized radiology reports, 130 reducing variability and increasing ef fi ciency in clinical work fl ows.”
Miyawaki, I. A., Banerjee, I., Batalini, F., Jorge, C. A. C., Celi, L. A., Cobanaj, M., Dee, E. C., Gichoya, J. W., Kaffey, Z. Y., Lloyd, M. R., et al. (2025) · European Journal of Cancer · doi:10.1016/j.ejca.2025.115394 · Cited by 14
Raju, V., Reddy, R., Javan, A. C., Hajihossainlou, B., Weissleder, R., Guiseppi‐Elie, A., Kurabayashi, K., Jones, S. A., & Faghih, R. T. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108592 · Cited by 14
“IL-10 has been found to be a marker for increased T cells (immune cells) and consequently, a predictor of severity of illness in those infected Neumann et al. (2020”
Transformer-based personalized attention mechanism for medical images with clinical records
Takagi, Y., Hashimoto, N., Masuda, H., Miyoshi, H., Ohshima, K., Hontani, H., & Takeuchi, I. (2023) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2022.100185 · Cited by 16
Deep Learning Analysis of Mammography for Breast Cancer Risk Prediction in Asian Women
Kim, H., Lim, J., Kim, H., Lim, Y., Seo, B. K., & Bae, M. S. (2023) · Diagnostics · doi:10.3390/diagnostics13132247 · Cited by 20
“[22] developed a deep learning model that used mammograms in addition to traditional risk factors (a hybrid deep learning model) to assess breast cancer risk.”
BackgroundBreast Cancer Risk Prediction Using Deep Learning
Bae, M. S., & Kim, H. (2021) · Radiology · doi:10.1148/radiol.2021211446 · Cited by 14
Metadata
- Authors
- Yala, A., Lehman, C., Schuster, T., Portnoi, T., & Barzilay, R.
- Affiliations
- Harvard University (US)
- Venue
- Radiology
- Published
- 2019-07
- Volume
- 292
- Issue
- 1
- Pages
- 60-66
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2944016032
- Cited by
- 758
- References
- 21
- Citations by year
- 2026: 89 · 2025: 123 · 2024: 117 · 2023: 118 · 2022: 119 · 2021: 86 · 2020: 75 · 2019: 30
- FWCI
- 56.99
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Breast Cancer Alliance
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Digital Radiography and Breast Imaging
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- breast cancer risk prediction, breast cancer risk models, Tyrer-Cuzick model, breast density, hybrid deep learning model, breast cancer screening, risk discrimination, breast cancer risk stratification
- MeSH terms
- Deep Learning, Adult, Aged, Aged, 80 and over, Breast, Breast Neoplasms, Female, Humans, Mammography, Middle Aged, Radiographic Image Interpretation, Computer-Assisted, Retrospective Studies, Reproducibility of Results, Risk Assessment
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.