Transforming Breast Imaging: A Narrative Review of Systematic Evidence on Artificial Intelligence in Mammographic Practice
Abstract
1. Introduction
1.1. Breast Cancer Epidemiology and Clinical Features
1.2. Evolution of Mammographic Imaging
1.3. Artificial Intelligence Integration in Mammography
1.4. Current Challenges and Opportunities in AI-Driven Breast Cancer Screening
1.5. Framing the Research: Key Questions and Aims of the Narrative Review
- Aim
- Trend analysis: Map recent trends in the scientific literature on AI in mammography, highlighting growth areas, publication volume, and thematic shifts using bibliometric insights.
- Themes and categorization: Identify and organize the main themes emerging from existing systematic reviews, focusing on AI applications that enhance breast cancer detection and diagnostic processes in mammography.
- Opportunities and challenges: Analyze the opportunities and challenges reported in the literature, including benefits related to diagnostic performance and clinical workflow, alongside barriers encountered in real-world adoption and integration.
2. Materials and Methods
(“artificial intelligence” OR “machine learning” OR “deep learning” OR “convolutional neural networks,” “transformers,” or “radiomics”) |
AND (“mammography” OR “breast cancer screening”) |
- N1: Clarity of the study’s rationale.
- N2: The appropriateness of the design.
- N3: The transparency of the described methods.
- N4: Clarity in presenting results.
- N5: Coherence between results and conclusions.
- N6: The disclosure of conflicts of interest.
- A “Yes” rating for N6 (conflict of interest disclosure).
- A score of 3 or higher on each of the five graded parameters (N1–N5).
- The types of AI algorithms applied (e.g., CNNs, ensemble learning),
- The clinical tasks and workflow integration,
- The datasets and validation strategies used,
- The reported strengths, weaknesses, and evidence gaps.
3. Results
3.1. Trend Analysis
- Search Key 1 focuses on mammography and AI (our core interest).
- Keys 2, 3, and 4 expand the scope to radiology, oncology, and breast cancer, respectively, still retaining AI as a central theme.
- For Key 2 (“artificial intelligence” AND “radiology”), a vast total of 32,854 publications since 1960 were found, with an overwhelming 87.9% (28,864) published in the last 10 years and 74.0% (24,317) in the last 5 years. The most recent 5 years alone represent about 84.3% of the publications produced in the preceding 5-year period (from 10 to 5 years ago), demonstrating a pronounced clustering of research activity.
- For Key 3 (“artificial intelligence” AND “oncology”), there have been 43,252 publications since 1961, with 81.7% (35,337) from the last decade and 65.7% (28,423) from the last 5 years. The most recent 5 years account for approximately 80.5% of the output of the prior 5-year interval, reflecting a similarly strong acceleration.
- For Key 4 (“artificial intelligence” AND “breast cancer”), a more focused yet significant dataset of 7292 publications since 1986 was identified, with 83.3% (6077) from the last 10 years and 66.8% (4872) from the last 5 years. The most recent 5 years make up about 80.2% of the preceding 5-year output, highlighting a consistent pattern of concentrated growth in AI research specific to breast cancer.
3.2. The Integration of AI in Mammography: The Focus on Emerging Themes and Technological Innovations
3.3. Opportunities and Challenges for Applying Artificial Intelligence in Mammography
4. Discussion
4.1. Current Trends and Evidence Synthesis on AI Applications in Mammography
4.2. Advances in Breast Cancer Research and Mammographic Technologies: The Role of AI
4.3. Towards Routine Integration: Coordinated Efforts for AI in Mammography
4.4. From Promise to Practice: Advancing AI in Mammography Through Trials, Innovation, and Translation
4.5. Limitations
5. A Final Thought: Beyond the Hype—Unlocking the True Clinical Potential of AI in Mammography Through Multidimensional Evidence
6. Conclusions
Supplementary Materials
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Available online: https://gco.iarc.who.int/media/globocan/factsheets/cancers/20-breast-fact-sheet.pdf (accessed on 12 July 2025).
- Available online: https://www.who.int/news-room/fact-sheets/detail/breast-cancer (accessed on 12 July 2025).
- Arnold, M.; Morgan, E.; Rumgay, H.; Mafra, A.; Singh, D.; Laversanne, M.; Vignat, J.; Gralow, J.R.; Cardoso, F.; Siesling, S.; et al. Current and future burden of breast cancer: Global statistics for 2020 and 2040. Breast 2022, 66, 15–23. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Yersal, O.; Barutca, S. Biological subtypes of breast cancer: Prognostic and therapeutic implications. World J. Clin. Oncol. 2014, 5, 412–424. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Ginsburg, O.; Yip, C.H.; Brooks, A.; Cabanes, A.; Caleffi, M.; Dunstan Yataco, J.A.; Gyawali, B.; McCormack, V.; McLaughlin de Anderson, M.; Mehrotra, R.; et al. Breast cancer early detection: A phased approach to implementation. Cancer 2020, 126 (Suppl. 10), 2379–2393. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Nicosia, L.; Gnocchi, G.; Gorini, I.; Venturini, M.; Fontana, F.; Pesapane, F.; Abiuso, I.; Bozzini, A.C.; Pizzamiglio, M.; Latronico, A.; et al. History of Mammography: Analysis of Breast Imaging Diagnostic Achievements over the Last Century. Healthcare 2023, 11, 1596. [Google Scholar] [CrossRef] [PubMed]
- Gold, R.H. The evolution of mammography. Radiol. Clin. N. Am. 1992, 30, 1–19. [Google Scholar] [CrossRef] [PubMed]
- Available online: https://cdas.cancer.gov/hipb/ (accessed on 12 July 2025).
- Joe, B.N.; Sickles, E.A. The evolution of breast imaging: Past to present. Radiology 2014, 273 (Suppl. 2), S23–S44. [Google Scholar] [CrossRef] [PubMed]
- Available online: https://www.radiologyinfo.org/en/info/tomosynthesis (accessed on 12 July 2025).
- Doi, K. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Comput. Med. Imaging Graph. 2007, 31, 198–211. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Freer, T.W.; Ulissey, M.J. Screening mammography with computer-aided detection: Prospective study of 12,860 patients in a community breast center. Radiology 2001, 220, 781–786. [Google Scholar] [CrossRef] [PubMed]
- McKinney, S.M.; Sieniek, M.; Godbole, V.; Godwin, J.; Antropova, N.; Ashrafian, H.; Back, T.; Chesus, M.; Corrado, G.S.; Darzi, A.; et al. International evaluation of an AI system for breast cancer screening. Nature 2020, 577, 89–94. [Google Scholar] [CrossRef]
- Lehman, C.D.; Wellman, R.D.; Buist, D.S.; Kerlikowske, K.; Tosteson, A.N.; Miglioretti, D.L.; Breast Cancer Surveillance Consortium. Diagnostic Accuracy of Digital Screening Mammography with and Without Computer-Aided Detection. JAMA Intern. Med. 2015, 175, 1828–1837. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Printz, C. Cancer organizations, institutions mobilize together during the COVID-19 pandemic: When confronted with myriad patient and provider challenges, the international cancer community launched multiple collaborations. Cancer 2021, 127, 825–826. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Dang, L.A.; Chazard, E.; Poncelet, E.; Serb, T.; Rusu, A.; Pauwels, X.; Parsy, C.; Poclet, T.; Cauliez, H.; Engelaere, C.; et al. Impact of artificial intelligence in breast cancer screening with mammography. Breast Cancer 2022, 29, 967–977. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Richman, I.; Tessier-Sherman, B.; Galusha, D.; Oladele, C.R.; Wang, K. Breast cancer screening during the COVID-19 pandemic: Moving from disparities to health equity. J. Natl. Cancer Inst. 2023, 115, 139–145. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Kufel, J.; Bargieł-Łączek, K.; Kocot, S.; Koźlik, M.; Bartnikowska, W.; Janik, M.; Czogalik, Ł.; Dudek, P.; Magiera, M.; Lis, A.; et al. What Is Machine Learning, Artificial Neural Networks and Deep Learning?—Examples of Practical Applications in Medicine. Diagnostics 2023, 13, 2582. [Google Scholar] [CrossRef] [PubMed]
- Shifa, N.; Saleh, M.; Akbari, Y.; Al Maadeed, S. A review of explainable AI techniques and their evaluation in mammography for breast cancer screening. Clin. Imaging 2025, 123, 110492. [Google Scholar] [CrossRef] [PubMed]
- Cerdas, M.G.; Farhat, J.; Elshafie, S.I.; Mariyam, F.; James, L.; Qureshi, A.K.; Potru, M.; Paliwei, P.; Joshi, M.R.; Abraham, G.; et al. Exploring the Evolution of Breast Cancer Imaging: A Review of Conventional and Emerging Modalities. Cureus 2025, 17, e82762. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Abu Abeelh, E.; Abuabeileh, Z. Screening Mammography and Artificial Intelligence: A Comprehensive Systematic Review. Cureus 2025, 17, e79353. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Yoon, J.H.; Strand, F.; Baltzer, P.A.T.; Conant, E.F.; Gilbert, F.J.; Lehman, C.D.; Morris, E.A.; Mullen, L.A.; Nishikawa, R.M.; Sharma, N.; et al. Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis. Radiology 2023, 307, e222639. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Zeng, A.; Houssami, N.; Noguchi, N.; Nickel, B.; Marinovich, M.L. Frequency and characteristics of errors by artificial intelligence (AI) in reading screening mammography: A systematic review. Breast Cancer Res. Treat. 2024, 207, 1–13. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Freeman, K.; Geppert, J.; Stinton, C.; Todkill, D.; Johnson, S.; Clarke, A.; Taylor-Phillips, S. Use of artificial intelligence for image analysis in breast cancer screening programmes: Systematic review of test accuracy. BMJ 2021, 374, n1872. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Laws, E.; Palmer, J.; Alderman, J.; Sharma, O.; Ngai, V.; Salisbury, T.; Hussain, G.; Ahmed, S.; Sachdeva, G.; Vadera, S.; et al. Diversity, inclusivity and traceability of mammography datasets used in development of Artificial Intelligence technologies: A systematic review. Clin. Imaging 2025, 118, 110369. [Google Scholar] [CrossRef] [PubMed]
- Branco, P.E.S.C.; Franco, A.H.S.; de Oliveira, A.P.; Carneiro, I.M.C.; de Carvalho, L.M.C.; de Souza, J.I.N.; Leandro, D.R.; Cândido, E.B. Artificial intelligence in mammography: A systematic review of the external validation. Rev. Bras. Ginecol. Obstet. 2024, 46, e-rbgo71. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Schopf, C.M.; Ramwala, O.A.; Lowry, K.P.; Hofvind, S.; Marinovich, M.L.; Houssami, N.; Elmore, J.G.; Dontchos, B.N.; Lee, J.M.; Lee, C.I. Artificial Intelligence-Driven Mammography-Based Future Breast Cancer Risk Prediction: A Systematic Review. J. Am. Coll. Radiol. 2024, 21, 319–328. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Avanzo, M.; Porzio, M.; Lorenzon, L.; Milan, L.; Sghedoni, R.; Russo, G.; Massafra, R.; Fanizzi, A.; Barucci, A.; Ardu, V.; et al. Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy. Phys. Med. 2021, 83, 221–241. [Google Scholar] [CrossRef] [PubMed]
- Rentiya, Z.S.; Mandal, S.; Inban, P.; Vempalli, H.; Dabbara, R.; Ali, S.; Kaur, K.; Adegbite, A.; Intsiful, T.A.; Jayan, M.; et al. Revolutionizing Breast Cancer Detection With Artificial Intelligence (AI) in Radiology and Radiation Oncology: A Systematic Review. Cureus 2024, 16, e57619. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Batchu, S.; Liu, F.; Amireh, A.; Waller, J.; Umair, M. A Review of Applications of Machine Learning in Mammography and Future Challenges. Oncology 2021, 99, 483–490. [Google Scholar] [CrossRef] [PubMed]
- Xavier, D.; Miyawaki, I.; Campello Jorge, C.A.; Freitas Silva, G.B.; Lloyd, M.; Moraes, F.; Patel, B.; Batalini, F. Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software. J. Med. Screen. 2024, 31, 157–165. [Google Scholar] [CrossRef] [PubMed]
- Hickman, S.E.; Woitek, R.; Le, E.P.V.; Im, Y.R.; Mouritsen Luxhøj, C.; Aviles-Rivero, A.I.; Baxter, G.C.; MacKay, J.W.; Gilbert, F.J. Machine Learning for Workflow Applications in Screening Mammography: Systematic Review and Meta-Analysis. Radiology 2022, 302, 88–104. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Liu, J.; Lei, J.; Ou, Y.; Zhao, Y.; Tuo, X.; Zhang, B.; Shen, M. Mammography diagnosis of breast cancer screening through machine learning: A systematic review and meta-analysis. Clin. Exp. Med. 2023, 23, 2341–2356. [Google Scholar] [CrossRef] [PubMed]
- Anderson, A.W.; Marinovich, M.L.; Houssami, N.; Lowry, K.P.; Elmore, J.G.; Buist, D.S.M.; Hofvind, S.; Lee, C.I. Independent External Validation of Artificial Intelligence Algorithms for Automated Interpretation of Screening Mammography: A Systematic Review. J. Am. Coll. Radiol. 2022, 19 Pt A, 259–273. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Bhalla, D.; Rangarajan, K.; Chandra, T.; Banerjee, S.; Arora, C. Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature. Indian. J. Radiol. Imaging 2023, 34, 469–487. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Goh, S.; Goh, R.S.J.; Chong, B.; Ng, Q.X.; Koh, G.C.H.; Ngiam, K.Y.; Hartman, M. Challenges in Implementing Artificial Intelligence in Breast Cancer Screening Programs: Systematic Review and Framework for Safe Adoption. J. Med. Internet Res. 2025, 27, e62941. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Gurmessa, D.K.; Jimma, W. Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: A systematic review. BMJ Health Care Inform. 2024, 31, e100954. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Hussain, S.; Ali, M.; Naseem, U.; Nezhadmoghadam, F.; Jatoi, M.A.; Gulliver, T.A.; Tamez-Peña, J.G. Breast cancer risk prediction using machine learning: A systematic review. Front. Oncol. 2024, 14, 1343627. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Oh, K.E.; Vasandani, N.; Anwar, A. Radiomics to Differentiate Malignant and Benign Breast Lesions: A Systematic Review and Diagnostic Test Accuracy Meta-Analysis. Cureus 2023, 15, e49015. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Hussain, S.; Lafarga-Osuna, Y.; Ali, M.; Naseem, U.; Ahmed, M.; Tamez-Peña, J.G. Deep learning, radiomics and radiogenomics applications in the digital breast tomosynthesis: A systematic review. BMC Bioinform. 2023, 24, 401. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Madani, M.; Behzadi, M.M.; Nabavi, S. The Role of Deep Learning in Advancing Breast Cancer Detection Using Different Imaging Modalities: A Systematic Review. Cancers 2022, 14, 5334. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Gardezi, S.J.S.; Elazab, A.; Lei, B.; Wang, T. Breast Cancer Detection and Diagnosis Using Mammographic Data: Systematic Review. J. Med. Internet Res. 2019, 21, e14464. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Yassin, N.I.R.; Omran, S.; El Houby, E.M.F.; Allam, H. Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review. Comput. Methods Programs Biomed. 2018, 156, 25–45. [Google Scholar] [CrossRef] [PubMed]
- Singh, D.; Singh, A.K. Role of image thermography in early breast cancer detection- Past, present and future. Comput. Methods Programs Biomed. 2020, 183, 105074. [Google Scholar] [CrossRef] [PubMed]
- Sorin, V.; Sklair-Levy, M.; Glicksberg, B.S.; Konen, E.; Nadkarni, G.N.; Klang, E. Deep Learning for Contrast Enhanced Mammography—A Systematic Review. Acad. Radiol. 2025, 32, 2497–2508. [Google Scholar] [CrossRef] [PubMed]
- Ciurescu, S.; Ciupici-Cladovan, M.; Buciu, V.B.; Ilaș, D.G.; Cîtu, C.; Sas, I. Systematic Review and Meta-Analysis of AI-Assisted Mammography and the Systemic Immune-Inflammation Index in Breast Cancer: Diagnostic and Prognostic Perspectives. Medicina 2025, 61, 1170. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Rostami, S.; Stutterheim, H.W.; Maxouri, O.; Willemse, J.R.J.; Rodríguez Sánchez, D.I.; Schats, W.; van Golen, L.W.; Vollebergh, M.A.; Cheung, Z.; Vogel, W.V.; et al. Imaging of Cancer of Unknown Primary: A systematic literature review of the past, present, and future. Br. J. Radiol. 2025, 98, 1209–1226. [Google Scholar] [CrossRef] [PubMed]
- Bennett, A.; Shaver, N.; Vyas, N.; Almoli, F.; Pap, R.; Douglas, A.; Kibret, T.; Skidmore, B.; Yaffe, M.; Wilkinson, A.; et al. Screening for breast cancer: A systematic review update to inform the Canadian Task Force on Preventive Health Care guideline. Syst. Rev. 2024, 13, 304. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Available online: https://www.novaoneadvisor.com/report/breast-cancer-therapeutics-market (accessed on 12 July 2025).
- Available online: https://www.marketsandata.com/industry-reports/mammography-market (accessed on 12 July 2025).
- Available online: https://www.marketsandmarkets.com/Market-Reports/diagnostic-imaging-market-411.html (accessed on 12 July 2025).
- Available online: https://www.marketsandmarkets.com/Market-Reports/ai-in-medical-imaging-market-21977207.html (accessed on 12 July 2025).
- Available online: https://www.towardshealthcare.com/insights/ai-in-breast-imaging-market-size (accessed on 12 July 2025).
- Available online: https://www.fda.gov/media/184856/download (accessed on 12 July 2025).
- Available online: https://www.fda.gov/regulatory-information/search-fda-guidance-documents/marketing-submission-recommendations-predetermined-change-control-plan-artificial-intelligence (accessed on 12 July 2025).
- Available online: https://www.acr.org/Clinical-Resources/Publications-and-Research/ACR-Bulletin/Bolstering-Breast-Cancer-Detection (accessed on 12 July 2025).
- Available online: https://digital-strategy.ec.europa.eu/en/policies/regulatory-framework-ai (accessed on 12 July 2025).
- Available online: https://www.eusobi.org/content-eusobi/uploads/EUSOBI-Mammography-beyond-2025_Preliminary-Programme.pdf (accessed on 12 July 2025).
- Available online: https://densitashealth.com/news/densitas-acr-learning-network-strategic-collaboration-to-improve-mammography-positioning/ (accessed on 12 July 2025).
- Available online: https://www.lunit.io/en/company/news/lunit-and-leeds-teaching-hospitals-nhs-trust-to-launch-worlds-first-prospective-ai-study-in-symptomatic-breast-clinic-setting (accessed on 12 July 2025).
- Hernström, V.; Josefsson, V.; Sartor, H.; Schmidt, D.; Larsson, A.M.; Hofvind, S.; Andersson, I.; Rosso, A.; Hagberg, O.; Lång, K. Screening performance and characteristics of breast cancer detected in the Mammography Screening with Artificial Intelligence trial (MASAI): A randomised, controlled, parallel-group, non-inferiority, single-blinded, screening accuracy study. Lancet Digit. Health 2025, 7, e175–e183. [Google Scholar] [CrossRef] [PubMed]
- Friedewald, S.M.; Sieniek, M.; Jansen, S.; Mahvar, F.; Kohlberger, T.; Schacht, D.; Bhole, S.; Gupta, D.; Prabhakara, S.; McKinney, S.M.; et al. Triaging mammography with artificial intelligence: An implementation study. Breast Cancer Res. Treat. 2025, 211, 1–10. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Eisemann, N.; Bunk, S.; Mukama, T.; Baltus, H.; Elsner, S.A.; Gomille, T.; Hecht, G.; Heywang-Köbrunner, S.; Rathmann, R.; Siegmann-Luz, K.; et al. Nationwide real-world implementation of AI for cancer detection in population-based mammography screening. Nat. Med. 2025, 31, 917–924. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Rangarajan, K.; Manivannan, V.V.; Singh, H.; Gupta, A.; Maheshwari, H.; Gogoi, R.; Gogoi, D.; Das, R.J.; Hari, S.; Vyas, S.; et al. Simulation training in mammography with AI-generated images: A multireader study. Eur. Radiol. 2025, 35, 562–571. [Google Scholar] [CrossRef] [PubMed]
- Salim, M.; Liu, Y.; Sorkhei, M.; Ntoula, D.; Foukakis, T.; Fredriksson, I.; Wang, Y.; Eklund, M.; Azizpour, H.; Smith, K.; et al. AI-based selection of individuals for supplemental MRI in population-based breast cancer screening: The randomized ScreenTrustMRI trial. Nat. Med. 2024, 30, 2623–2630. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- McGuinness, J.E.; Anderson, G.L.; Mutasa, S.; Hershman, D.L.; Terry, M.B.; Tehranifar, P.; Lew, D.L.; Yee, M.; Brown, E.A.; Kairouz, S.S.; et al. Effects of vitamin D supplementation on a deep learning-based mammographic evaluation in SWOG S0812. JNCI Cancer Spectr. 2024, 8, pkae042. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Chen, Y.; Jiang, H.; Li, J.; Zhang, J.; Wu, P.; Dai, Z. A Mammography-Based Radiomic Nomogram for Predicting Malignancy in Breast Suspicious Microcalcifications. Acad. Radiol. 2024, 31, 492–502. [Google Scholar] [CrossRef] [PubMed]
- Dembrower, K.; Crippa, A.; Colón, E.; Eklund, M.; Strand, F. ScreenTrustCAD Trial Consortium. Artificial intelligence for breast cancer detection in screening mammography in Sweden: A prospective, population-based, paired-reader, non-inferiority study. Lancet Digit. Health 2023, 5, e703–e711, Erratum in Lancet Digit. Health 2023, 5, e646. https://doi.org/10.1016/S2589-7500(23)00181-4. [Google Scholar] [CrossRef] [PubMed]
- Lång, K.; Josefsson, V.; Larsson, A.M.; Larsson, S.; Högberg, C.; Sartor, H.; Hofvind, S.; Andersson, I.; Rosso, A. Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): A clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study. Lancet Oncol. 2023, 24, 936–944. [Google Scholar] [CrossRef] [PubMed]
- Zhou, C.; Xie, H.; Zhu, F.; Yan, W.; Yu, R.; Wang, Y. Improving the malignancy prediction of breast cancer based on the integration of radiomics features from dual-view mammography and clinical parameters. Clin. Exp. Med. 2023, 23, 2357–2368. [Google Scholar] [CrossRef] [PubMed]
- Sechopoulos, I.; Abbey, C.K.; van der Waal, D.; Geertse, T.; Tetteroo, E.; Pijnappel, R.M.; Broeders, M.J.M. Evaluation of reader performance during interpretation of breast cancer screening: The Recall and detection Of breast Cancer in Screening (ROCS) trial study design. Eur. Radiol. 2022, 32, 7463–7469. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Ma, M.; Liu, R.; Wen, C.; Xu, W.; Xu, Z.; Wang, S.; Wu, J.; Pan, D.; Zheng, B.; Qin, G.; et al. Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms. Eur. Radiol. 2022, 32, 1652–1662. [Google Scholar] [CrossRef] [PubMed]
- Liu, H.; Chen, Y.; Zhang, Y.; Wang, L.; Luo, R.; Wu, H.; Wu, C.; Zhang, H.; Tan, W.; Yin, H.; et al. A deep learning model integrating mammography and clinical factors facilitates the malignancy prediction of BI-RADS 4 microcalcifications in breast cancer screening. Eur. Radiol. 2021, 31, 5902–5912. [Google Scholar] [CrossRef] [PubMed]
- Wei, H.; Fan, H. MM-CLIP: Multi-granularity Mammography CLIP for Breast Cancer Diagnosis. In Proceedings of the 2025 9th International Conference on Digital Signal Processing (ICDSP ’25), Chengdu, China, 21–23 February 2025; pp. 92–99. [Google Scholar] [CrossRef]
- Doma, M.K.; Padmanandam, K.; Tambvekar, S.; Kumar, K.K.; Abdualgalil, B.; Thakur, R.N. Artificial Intelligence-Based Breast Cancer Detection Using WPSO. Int. J. Oper. Res. Inf. Syst. 2022, 13, 1–16. [Google Scholar] [CrossRef]
- Aydemir, B.K.K.; Telatar, Z.; Güney, S.; Dengiz, B. Detecting and Classifying Breast Masses via YOLO-Based Deep Learning. Neural Comput. Appl. 2025, 37, 11555–11582. [Google Scholar] [CrossRef]
- Islam, M.S.; Yasmin, S.; Chowdhury, T.A.; Sayem, A.; Mim, K. AI-Assisted Breast Cancer Diagnosis: Deep Learning on RSNA Mammogram Images for Improved Classification. In Proceedings of the 2023 26th International Conference on Computer and Information Technology (ICCIT), Cox’s Bazar, Bangladesh, 13–15 December 2023. [Google Scholar] [CrossRef]
- Yang, Z.; Cao, Z.; Zhang, Y.; Chang, P.; Wu, S.; Huang, L. MABEL: An AI-Powered Mammographic Breast Lesion Diagnostic System. In Proceedings of the 2020 IEEE International Conference on E-Health Networking, Application & Services (HEALTHCOM), Shenzhen, China, 1–2 March 2021. [Google Scholar] [CrossRef]
- Rath, S.; Giri, K.; Dash, S.R.; Barra, P.; Abdullah, A.A. Application of Artificial Intelligence using Mammograms to Identify Breast Cancer. In Proceedings of the 2024 6th International Conference on Computational Intelligence and Networks (CINE), Bhubaneswar, India, 19–21 December 2024. [Google Scholar] [CrossRef]
- Available online: https://arxiv.org/abs/2506.08677 (accessed on 12 July 2025).
- Available online: https://arxiv.org/abs/2506.03177 (accessed on 12 July 2025).
- Available online: https://arxiv.org/abs/2503.13309 (accessed on 12 July 2025).
- Available online: https://www.arxiv.org/abs/2505.03018 (accessed on 12 July 2025).
Common Theme | Summary | Key References |
---|---|---|
Reader cancer detection comparison | Most systematic reviews explore AI systems that show comparable sensitivity and specificity to radiologists in mammography and suggest they are an advanced technique for cancer detection. | [21,22,24,29,31,32,34,35,36,40,41,42,43,44,45,46,48] |
Radiologist workload reduction | AI can triage low-risk mammograms, thereby reducing the number of images requiring human interpretation without compromising sensitivity. | [21,30,31] |
Error types | AI errors are typically quantified in terms of false positives and negatives, which vary based on positivity thresholds, algorithm version, and study quality. | [23] |
Ethical implication | Many studies explore the ethical implication, challenges and frameworks on the use of AI software in clinical practice. | [29,36,37] |
Methodological limitations | Many studies are retrospective, with concerns about bias, limited generalizability, and the inconsistent reporting of accuracy metrics, highlighting the necessity of performing more rigorous prospective studies. | [24,29,32,33,34,45,47] |
Combined AI and radiologist performance | The integration of AI with radiologist interpretation frequently results in improved diagnostic accuracy compared to using radiologists alone. | [26,34,35] |
Prospective and future applications | AI technology shows promise for future risk-based screening, early detection, and personalized screening strategies based on imaging features. | [27,29,37,38,44] |
Performance on advanced imaging technique | AI has been applied to modalities such as DBT and CEM, showing promising yet preliminary results. | [22,38,40,45] |
Ref. | Brief Description | AI Applications and Technical Details |
---|---|---|
[21] | Systematic review on AI in screening mammography focusing on diagnostic accuracy, reductions in false positives, and radiologist support. Analyzes 13 studies on AI performance in breast cancer detection. | AI algorithms assist in mammography readings, sometimes outperforming double radiologist readings. Techniques improve specificity, reduce unnecessary recalls, and lower workload. Challenges include false positives and variation in performance across demographics. |
[22] | Meta-analysis assessing standalone AI performance in digital mammography and digital breast tomosynthesis (DBT) screening. Includes 16 studies with over 1 million exams. | Standalone AI evaluated via reader and cohort studies. AI shows higher AUC than radiologists in digital mammography and DBT. AI demonstrates higher sensitivity but lower specificity compared to radiologists. Uses QUADAS-2 for study quality assessment. |
[23] | Systematic review focusing on error types and frequencies in AI mammography readings, analyzing false-positive and false-negative rates across 7 retrospective studies. | Errors analyzed include false positives and false negatives varying by AI threshold and algorithm version. Meta-analysis of pooled error rates conducted. Sparse reporting of other AI error types such as location or technical errors. |
[24] | Systematic review of AI test accuracy in breast cancer screening programs including 12 studies (131,822 women). Examines AI alone or combined with radiologists. | Most AI systems less accurate than single radiologists and far less than double readings. Some small studies show promise in lab settings. AI used for triage screens out low-risk women but can miss some cancers. No prospective clinical studies found. QUADAS-2 tool used for quality assessment. |
[25] | Review of mammography datasets used in AI development, focusing on dataset diversity, inclusivity, traceability, and accessibility. | Identifies 254 datasets with most privately held; poor demographic reporting (race/ethnicity, sex/gender). Highlights global representation gaps and documentation transparency issues, impacting AI model generalizability and fairness. |
[26] | Systematic review of external validation studies for AI algorithms in mammography breast cancer screening (30 studies, 2014–2024). | AI algorithms demonstrate comparable AUC and sensitivity to radiologists alone. Combining AI with radiologists improves accuracy statistically. Studies include diverse populations and validation datasets. Emphasizes need for external validation. |
[27] | Systematic review on integration of AI in breast cancer screening workflows, focusing on clinical implementation challenges and real-world performance. | Discusses AI deployment in clinical settings, highlighting variability in algorithm performance, integration with radiologists, regulatory considerations, and workflow optimization. Emphasizes importance of prospective studies and continuous monitoring of AI tools. |
[28] | Systematic review of AI applied to medical imaging research in Italy (2015–2020). Main imaging modalities: MRI (44%), CT (12%), radiography/mammography (11%). Focuses on neurological diseases (29%) and cancer diagnosis (25%). AI tasks: classification (57%), segmentation (16%). Methods: 65% machine learning, 35% deep learning. Rapid growth in AI research observed. | AI used primarily for image classification and segmentation across multiple imaging modalities. Machine learning and deep learning models analyzed. Emphasis on building common frameworks, data sharing, and collaborations. |
[29] | Review of AI advancements in breast cancer detection and treatment, highlighting shift from CAD to AI-based methods. Discusses challenges like data quality, regulation, ethics, and validation. Promising potential to improve early diagnosis and patient outcomes. | AI applications in automated interpretation of mammograms and tomosynthesis. Deep learning methods improve accuracy and efficiency in detection. Challenges include algorithm validation and clinical integration. |
[30] | Systematic review of AI in mammography focusing on diagnosis and prediction of breast malignancies. Reports reduction in false positives (up to 69%) and increased sensitivity (84–91%). AI models can independently classify suspicious findings comparable to radiologists. | Machine learning models applied to reduce radiologist workload, improve diagnosis accuracy, and predict breast cancer risk. Calls for larger prospective studies to confirm clinical utility. |
[31] | Meta-analysis on deep learning (DL) software for triaging breast cancer screening mammograms. Shows 68.3% reduction in radiologist workload with 93.1% sensitivity. Highlights complexity of AI implementation but promising healthcare optimization. | DL algorithms used for triage of mammograms to exclude low-risk cases, maintaining high sensitivity. Meta-analysis of commercially available DL software with performance metrics reported. |
[32] | Systematic review and meta-analysis of standalone machine learning (ML) algorithms for screening mammography workflow. ML algorithms achieve or exceed human reader performance with pooled sensitivity of 75.4%, specificity of 90.6%, AUC of 0.89. | Standalone ML models for mammogram detection and triage, evaluated independently from human readers. Evidence based on retrospective studies; external prospective validation needed. |
[33] | Meta-analysis of ML methods (CNN, ANN, SVM) in mammography diagnosis for breast cancer screening. CNN showed highest sensitivity (96.1%), specificity (95.0%) and AUC (0.974). Emphasizes need for prospective studies. | Evaluation of different ML methods for breast cancer diagnosis on mammography images. CNNs demonstrate superior performance compared to ANN and SVM. |
[34] | Systematic review of independent external validation studies of AI algorithms for screening mammography. Some AI algorithms improve accuracy over radiologists alone; combined AI and radiologist interpretation shows further improvement. | External validation of commercial AI tools for mammography cancer detection. Studies include retrospective reader and simulation designs. AI improves diagnostic accuracy, especially when combined with radiologists. |
[35] | Systematic review evaluating reproducibility and explainability of deep learning in mammography for breast cancer detection. Found high risk of bias in most studies; only few of adequate quality. Common architectures include ResNet and RetinaNet. Highest AUC reported was ~0.945. Combined AI and radiologist readings improve performance. Lack of explainability and real-world interaction studies noted. | Analysis of deep learning models’ reproducibility and clinical validity. Emphasis on need for explainable AI and real-world validation. Ensemble models and patch classifiers common. Highest diagnostic performance when AI assists radiologists. |
[36] | Systematic review identifying challenges in AI implementation for breast cancer screening. Key issues: reproducibility, evidentiary standards, tech integration, trust, ethics, legal and societal concerns. Uses CFIR framework to propose governance strategies. | Mainly AI in mammography (19 studies) and ultrasound (1 study). Highlights needs for robust evidence, trust-building, addressing ethical/legal aspects, and structured governance. CFIR helps map challenges to solutions for clinical adoption. |
[37] | Review of explainable AI (XAI) methods applied to breast cancer diagnosis via mammography and ultrasound. Investigates evaluation methods, ethical challenges, and trust in XAI systems. | Analyzes 14 studies on XAI for breast cancer imaging. Finds limited evaluation of user trust and confidence. Dataset quality and related issues highlighted as key research gaps. Calls for systematic evaluation of XAI trustworthiness in clinical settings. |
[38] | Systematic review on machine learning and deep learning for breast cancer risk prediction using imaging, radiomics, genomics, and clinical data. Discusses current approaches and future potential. | Covers 20 studies using DL models for personalized risk prediction integrating multi-modal data. Explores NLP applications on imaging and non-imaging features to improve clinical decision-making. Provides overview for researchers on AI risk assessment techniques. |
[39] | Systematic review and meta-analysis on radiomics to differentiate benign and malignant breast lesions. Assesses diagnostic accuracy across imaging modalities including MRI, mammography, ultrasound, and CT. | Includes 31 studies with 8773 patients. Radiomics showed high sensitivity and specificity across MRI, mammography, and ultrasound, with CT data limited. Supports radiomics as promising adjunct or alternative diagnostic tool, while biopsy remains gold standard. |
[40] | Comprehensive review of deep learning, radiomics, and radiogenomics applications in digital breast tomosynthesis (DBT). Focus on DBT’s potential for enhanced early breast cancer detection. | Thirty studies reviewed on DL, radiomics, and radiogenomics applied to DBT, synthetic mammography, and full-field digital mammography. Emphasizes interdisciplinary approaches and new model development for clinical deployment of AI in DBT imaging. |
[41] | Systematic review of deep learning in breast cancer detection using multiple imaging modalities. Discusses limitations of current manual analysis and benefits of AI-assisted interpretation. | Reviews latest AI and DL models across mammograms, ultrasound, MRI, and histopathology images. Reports on datasets and algorithm development supporting early detection and improved diagnostic accuracy. Highlights AI’s role in reducing false positives and improving efficiency. |
[42] | Systematic review of ML and DL for breast cancer detection using mammographic data. Highlights evolution from traditional ML to deep learning improving CAD systems. | Deep learning methods (CNNs, deep feature learning) enhance diagnostic accuracy in breast cancer CAD; issues include data scarcity and computational cost, mitigated by data augmentation and improved DL architectures. |
[43] | Systematic review of machine learning CAD systems for breast cancer using various imaging modalities. | Analysis of ML classifiers and image modalities for breast cancer detection; discussion on improving CAD systems objectivity and efficiency. |
[44] | Review on infrared breast thermography for early breast cancer detection, covering image acquisition, segmentation, feature extraction, and classification. | Use of artificial neural networks to improve thermographic image classification; numerical simulation to reduce false positives; ML techniques for real-time applications recommended. |
[45] | Systematic review on deep learning applications in contrast-enhanced mammography (CEM). | CNN models dominate; used for lesion classification, detection, segmentation; attention mechanisms improve accuracy; integration with radiomics and radiologist assessments enhances diagnostic performance; mostly retrospective studies, need for prospective validation. |
[46] | Meta-analysis of AI-assisted mammography and prognostic role of Systemic Immune–Inflammation Index (SII) in breast cancer. | AI shows high diagnostic accuracy (AUC up to 0.93), reduces radiologist workload and improves detection in dense breasts. SII is prognostic biomarker linked to survival. Challenges include cut-off variability and need for prospective studies. |
[47] | Systematic review on imaging modalities for cancer of unknown primary (CUP). | Use of CT, MRI, FDG-PET/CT, emerging whole-body MRI, FAPI-PET/CT, AI and radiomics to improve detection and characterization of primary tumors; evolving imaging tech increases diagnostic precision. |
[48] | Systematic review update on breast cancer screening informing Canadian guidelines. Although not focused solely on mammography, this study offers important updated evidence on breast cancer screening, helping to contextualize AI’s role within current screening guidelines. | Machine learning employed to prioritize screening literature; synthesis of RCT and observational data on screening benefits and harms; ML used in research prioritization. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lastrucci, A.; Iosca, N.; Wandael, Y.; Barra, A.; Ricci, R.; Nori Cucchiari, J.; Forini, N.; Lepri, G.; Giansanti, D. Transforming Breast Imaging: A Narrative Review of Systematic Evidence on Artificial Intelligence in Mammographic Practice. Diagnostics 2025, 15, 2197. https://doi.org/10.3390/diagnostics15172197
Lastrucci A, Iosca N, Wandael Y, Barra A, Ricci R, Nori Cucchiari J, Forini N, Lepri G, Giansanti D. Transforming Breast Imaging: A Narrative Review of Systematic Evidence on Artificial Intelligence in Mammographic Practice. Diagnostics. 2025; 15(17):2197. https://doi.org/10.3390/diagnostics15172197
Chicago/Turabian StyleLastrucci, Andrea, Nicola Iosca, Yannick Wandael, Angelo Barra, Renzo Ricci, Jacopo Nori Cucchiari, Nevio Forini, Graziano Lepri, and Daniele Giansanti. 2025. "Transforming Breast Imaging: A Narrative Review of Systematic Evidence on Artificial Intelligence in Mammographic Practice" Diagnostics 15, no. 17: 2197. https://doi.org/10.3390/diagnostics15172197
APA StyleLastrucci, A., Iosca, N., Wandael, Y., Barra, A., Ricci, R., Nori Cucchiari, J., Forini, N., Lepri, G., & Giansanti, D. (2025). Transforming Breast Imaging: A Narrative Review of Systematic Evidence on Artificial Intelligence in Mammographic Practice. Diagnostics, 15(17), 2197. https://doi.org/10.3390/diagnostics15172197