Early Breast Cancer screening

Breast-cancer screening is entering a new phase. Mammography stays the cornerstone, while AI and MRI in dense breasts accelerate the move toward personalized screening.

The current foundation of screening

Breast-cancer screening remains one of the most effective tools in population health. In 2024, the US Preventive Services Task Force (USPSTF) reaffirmed biennial mammography for average-risk women aged 40 to 74, lowering the starting age from 50 to 40 in response to epidemiologic trends and rising incidence among younger women. The update aims to anticipate detection, reduce mortality and promote equity, particularly in populations historically under-screened, such as black women. The mortality benefit derives from repeated rounds of screening, which reduce late-stage diagnoses and enable curative treatment. Biennial intervals are designed to balance sensitivity, cumulative radiation exposure, recall rates and resource sustainability.

Despite its strengths, the USPSTF highlights persistent evidence gaps, including the optimal strategy for women over 75 and the lack of consensus on supplemental screening for dense breasts. Overdiagnosis, the detection of indolent tumors that would never have become clinically significant, remains the main trade-off of population screening, creating a permanent tension between mortality reduction and overtreatment. Sensitivity is also significantly affected by breast density, which not only obscures lesions on mammography but also constitutes an independent risk factor for cancer development. Tumors that arise between screening rounds (so-called interval cancers) often display more aggressive features and are diagnosed at a more advanced stage. This reflects how breast density, tumor biology and screening interval interact to influence outcomes, underscoring the need for strategies that are both more sensitive and more individualized than mammography alone.

Evolving technologies in early detection

The challenge of dense breasts has driven major innovation. The DENSE Trial (NEJM 2019) demonstrated that supplemental MRI in women with extremely dense breasts significantly reduced interval cancers, with benefits confirmed in the second screening round (Radiology 2021). Building on this evidence, the EUSOBI 2022 recommendations propose offering MRI every two to four years in extremely dense breasts, marking one of the clearest examples of a risk-adapted pathway already applicable in clinical practice. Some programs have begun exploring abbreviated MRI protocols to increase feasibility and accessibility, laying the groundwork for tiered screening pathways and bridging the gap between evidence and feasibility.

Technological disruption is advancing even faster in image interpretation. The MASAI randomized trial (Lancet Oncol 2023) demonstrated that AI-supported screen reading is non-inferior to standard double reading, with fewer false positives and reduced workload. These findings were strengthened by real-world data from a nationwide implementation (Nat Med 2025), where AI-assisted workflows delivered safe and consistent performance at population scale. AI is not merely a tool for efficiency - it has the potential to standardize quality across centers, reduce inter-reader variability and triage examinations by risk, acting as a “second pair of eyes” always available. For radiologists, this evolution refocuses expertise toward complex case interpretation, MRI reading and multidisciplinary decision-making.

Together, MRI-based strategies and AI-assisted workflows create a screening ecosystem that is more sensitive, more consistent and potentially more sustainable. Yet these advancements reinforce a unifying principle: uniform, age-based screening intervals are no longer adequate to reflect heterogeneous risk.

The road ahead: toward precision screening

The convergence of epidemiology, imaging and data science points toward a near future of risk-adapted screening, in which screening intensity and modality are determined by individual characteristics rather than age alone. Breast density will remain a key variable, but future models will likely integrate polygenic risk scores, reproductive and hormonal history, clinical predictors and AI-derived risk estimates to stratify women into different categories of baseline risk. In such paradigms, mammography could remain central for the majority, while supplemental MRI or ultrasound would be selectively deployed in women at higher predicted risk.

Beyond imaging, liquid biopsy and circulating tumor DNA assays are being explored as tools for early detection and longitudinal monitoring. Although current sensitivity is insufficient for population screening, such assays may eventually complement imaging by detecting biological signals before radiologic visibility. The long-term direction is clear: biology and risk modeling will progressively influence screening, just as they already shape treatment algorithms in early and metastatic disease.

For clinicians, three practical messages emerge. First, biennial mammography from age 40 remains the standard for average-risk women, backed by robust evidence. Second, dense breasts warrant individualized consideration, and MRI should be discussed when supported by guidelines and available resources. Third, AI-supported screening is ready for structured integration, with solid evidence supporting its safety and efficiency. Early detection will not be replaced, it will be refined. Screening will become more targeted, more data-driven and more aligned with individual risk, with the ongoing responsibility to balance mortality reduction against the risk of overdiagnosis in average-risk populations.

Sources and further reading
  1. US Preventive Services Task Force; Nicholson WK, Silverstein M, Wong JB, Barry MJ, Chelmow D, Coker TR, Davis EM, Jaén CR, Krousel-Wood M, Lee S, Li L, Mangione CM, Rao G, Ruiz JM, Stevermer JJ, Tsevat J, Underwood SM, Wiehe S. Screening for Breast Cancer: US Preventive Services Task Force Recommendation Statement. JAMA. 2024 Jun 11;331(22):1918-1930. doi: 10.1001/jama.2024.5534. Erratum in: JAMA. 2024 Sep 30. doi: 10.1001/jama.2024.19851. PMID: 38687503.
  2. Eisemann N, Bunk S, Mukama T, Baltus H, Elsner SA, Gomille T, Hecht G, Heywang-Köbrunner S, Rathmann R, Siegmann-Luz K, Töllner T, Vomweg TW, Leibig C, Katalinic A. Nationwide real-world implementation of AI for cancer detection in population-based mammography screening. Nat Med. 2025 Mar;31(3):917-924. doi: 10.1038/s41591-024-03408-6. Epub 2025 Jan 7. PMID: 39775040; PMCID: PMC11922743.
  3. Lång K, Josefsson V, Larsson AM, 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 Aug;24(8):936-944. doi: 10.1016/S1470-2045(23)00298-X. PMID: 37541274.
  4. Bakker MF, de Lange SV, Pijnappel RM, Mann RM, Peeters PHM, Monninkhof EM, Emaus MJ, Loo CE, Bisschops RHC, Lobbes MBI, de Jong MDF, Duvivier KM, Veltman J, Karssemeijer N, de Koning HJ, van Diest PJ, Mali WPTM, van den Bosch MAAJ, Veldhuis WB, van Gils CH; DENSE Trial Study Group. Supplemental MRI Screening for Women with Extremely Dense Breast Tissue. N Engl J Med. 2019 Nov 28;381(22):2091-2102. doi: 10.1056/NEJMoa1903986. PMID: 31774954.
  5. Veenhuizen SGA, de Lange SV, Bakker MF, Pijnappel RM, Mann RM, Monninkhof EM, Emaus MJ, de Koekkoek-Doll PK, Bisschops RHC, Lobbes MBI, de Jong MDF, Duvivier KM, Veltman J, Karssemeijer N, de Koning HJ, van Diest PJ, Mali WPTM, van den Bosch MAAJ, van Gils CH, Veldhuis WB; DENSE Trial Study Group. Supplemental Breast MRI for Women with Extremely Dense Breasts: Results of the Second Screening Round of the DENSE Trial. Radiology. 2021 May;299(2):278-286. doi: 10.1148/radiol.2021203633. Epub 2021 Mar 16. PMID: 33724062.
  6. Mann RM, Athanasiou A, Baltzer PAT, Camps-Herrero J, Clauser P, Fallenberg EM, Forrai G, Fuchsjäger MH, Helbich TH, Killburn-Toppin F, Lesaru M, Panizza P, Pediconi F, Pijnappel RM, Pinker K, Sardanelli F, Sella T, Thomassin-Naggara I, Zackrisson S, Gilbert FJ, Kuhl CK; European Society of Breast Imaging (EUSOBI). Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI). Eur Radiol. 2022 Jun;32(6):4036-4045. doi: 10.1007/s00330-022-08617-6. Epub 2022 Mar 8. PMID: 35258677; PMCID: PMC9122856.
  7. Tomlinson-Hansen SE, Budh DP, Sapra A. Breast Cancer Screening in the Average-Risk Patient. 2024 Oct 3. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2025 Jan–. PMID: 32310510.