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
Open accessAbstract
BACKGROUND: Emerging evidence suggests that artificial intelligence (AI) can increase cancer detection in mammography screening while reducing screen-reading workload, but further understanding of the clinical impact is needed. METHODS: In this randomised, controlled, parallel-group, non-inferiority, single-blinded, screening-accuracy study, done within the Swedish national screening programme, women recruited at four screening sites in southwest Sweden (Malmö, Lund, Landskrona, and Trelleborg) who were eligible for mammography screening were randomly allocated (1:1) to AI-supported screening or standard double reading. The AI system (Transpara version 1.7.0 ScreenPoint Medical, Nijmegen, Netherlands) was used to triage screening examinations to single or double reading and as detection support highlighting suspicious findings. This is a protocol-defined analysis of the secondary outcome measures of recall, cancer detection, false-positive rates, positive predictive value of recall, type and stage of cancer detected, and screen-reading workload. This trial is registered at ClinicalTrials.gov, NCT04838756 and is closed to accrual. FINDINGS: Between April 12, 2021, and Dec 7, 2022, 105 934 women were randomly assigned to the intervention or control group. 19 women were excluded from the analysis. The median age was 53·7 years (IQR 46·5-63·2). AI-supported screening among 53 043 participants resulted in 338 detected cancers and 1110 recalls. Standard screening among 52 872 participants resulted in 262 detected cancers and 1027 recalls. Cancer-detection rates were 6·4 per 1000 (95% CI 5·7-7·1) screened participants in the intervention group and 5·0 per 1000 (4·4-5·6) in the control group, a ratio of 1·29 (95% CI 1·09-1·51; p=0·0021). AI-supported screening resulted in an increased detection of invasive cancers (270 vs 217, a proportion ratio of 1·24 [95% CI 1·04-1·48]), wich were mainly small lymph-node negative cancers (58 more T1, 46 more lymph-node negative, and 21 more non-luminal A). AI-supported screening also resulted in an increased detection of in situ cancers (68 vs 45, a proportion ratio of 1·51 [1·03-2·19]), with about half of the increased detection being high-grade in situ cancer (12 more nuclear grade III, and no increase in nuclear grade I). The recall and false-positive rate were not significantly higher in the intervention group (a ratio of 1·08 [95% CI 0·99-1·17; p=0·084] and 1·01 [0·91-1·11; p=0·92], respectively). The positive predictive value of recall was significantly higher in the intervention group compared with the control group, with a ratio of 1·19 (95% CI 1·04-1·37; p=0·012). There were 61 248 screen readings in the intervention group and 109 692 in the control group, resulting in a 44·2% reduction in the screen-reading workload. INTERPRETATION: The findings suggest that AI contributes to the early detection of clinically relevant breast cancer and reduces screen-reading workload without increasing false positives. FUNDING: Swedish Cancer Society, Confederation of Regional Cancer Centres, and Swedish governmental funding for clinical research.
Integrity signals
Registry
Cites
Statistics
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 MASAI trial, AI-supported screening reduced radiologist workload by 44.2%.
“the AI-supported screening was non-inferior and reduced radiologist workload by 44.2% (AI arm, 61,248 reads; control, 109,692) without increasing false-positive rates, and with evidence of earlier cancer detection [30,31].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [31]
In the MASAI trial, AI-supported screening was non-inferior to standard double reading.
“the AI-supported screening was non-inferior and reduced radiologist workload by 44.2% (AI arm, 61,248 reads; control, 109,692) without increasing false-positive rates, and with evidence of earlier cancer detection [30,31].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [31]
In the MASAI trial, there was evidence of earlier cancer detection with AI-supported screening.
“the AI-supported screening was non-inferior and reduced radiologist workload by 44.2% (AI arm, 61,248 reads; control, 109,692) without increasing false-positive rates, and with evidence of earlier cancer detection [30,31].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [31]
In the MASAI trial, AI-supported screening did not increase false-positive rates.
“the AI-supported screening was non-inferior and reduced radiologist workload by 44.2% (AI arm, 61,248 reads; control, 109,692) without increasing false-positive rates, and with evidence of earlier cancer detection [30,31].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [31]
Cites
Harbeck, N., Penault-Llorca, F., Cortes, J., Gnant, M., Houssami, N., Poortmans, P., Ruddy, K., Tsang, J., & Cardoso, F. (2019) · Nature Reviews Disease Primers · doi:10.1038/s41572-019-0111-2 · Cited by 3,024 · see citing works
Early breast cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up
Loibl, S., André, F., Bachelot, T., Barrios, C. H., Bergh, J. C. S., Burstein, H. J., Cardoso, M. J., Carey, L., Dawood, S. S., Mastro, L. D., et al. (2023) · Annals of Oncology · doi:10.1016/j.annonc.2023.11.016 · Cited by 1,078 · see citing works
Perry, N., Broeders, M. J. M., de Wolf, C., Törnberg, S., Holland, R., & von Karsa, L. (2007) · Annals of Oncology · doi:10.1093/annonc/mdm481 · Cited by 1,018 · see citing works
Lång, K., Josefsson, V., Larsson, A.-M., Larsson, S., Högberg, C., Sartor, H., Hofvind, S., Andersson, I., & Rosso, A. (2023) · The Lancet Oncology · doi:10.1016/s1470-2045(23)00298-x · Cited by 598 · see citing works
Self-citationPestalozzi, B. C., Zahrieh, D., Mallon, E., Gusterson, B. A., Price, K. N., Gelber, R. D., Holmberg, S. B., Lindtner, J., Snyder, R. D., Thurlimann, B. J. K., et al. (2008) · Journal of Clinical Oncology · doi:10.1200/jco.2007.14.9336 · Cited by 490 · see citing works
Dembrower, K., Crippa, A., Colón, E., Eklund, M., & Strand, F. (2023) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00153-x · Cited by 371 · see citing works
Ductal carcinoma in situ: to treat or not to treat, that is the question
on behalf of the PRECISION team, van Seijen, M., Lips, E. H., Thompson, A. M., Nik‐Zainal, S., Futreal, P. A., Hwang, E. S., Verschuur, E., Lane, J., Jonkers, J., et al. (2019) · British Journal of Cancer · doi:10.1038/s41416-019-0478-6 · Cited by 321 · see citing works
Breast Cancer Screening and Diagnosis: A Synopsis of the European Breast Guidelines
Schünemann, H. J., Donata, L., Quinn, C., Follmann, M., Alonso‐Coello, P., Rossi, P. G., Lebeau, A., Nyström, L., Broeders, M. J. M., Ioannidou-Mouzaka, L., et al. (2019) · Annals of Internal Medicine · doi:10.7326/m19-2125 · Cited by 286 · see citing works
Self-citationConfidence Intervals for the Ratio of Two Binomial Proportions
Koopman, P. A. R. (1984) · Biometrics · doi:10.2307/2531405 · Cited by 273 · see citing works
Evans, K. K., Birdwell, R. L., & Wolfe, J. M. (2013) · PLoS ONE · doi:10.1371/journal.pone.0064366 · Cited by 238 · see citing works
Houssami, N., & Hunter, K. E. (2017) · npj Breast Cancer · doi:10.1038/s41523-017-0014-x · Cited by 229 · see citing works
Colzani, E., Liljegren, A., Johansson, A. L. V., Adolfsson, J., Hellborg, H., Hall, P. F., & Czene, K. (2011) · Journal of Clinical Oncology · doi:10.1200/jco.2010.32.6462 · Cited by 205 · see citing works
Hennigs, A., Riedel, F., Gondos, Á., Sinn, H., Schirmacher, P., Marmé, F., Jäger, D., Kauczor, H., Stieber, A., Lindel, K., et al. (2016) · BMC Cancer · doi:10.1186/s12885-016-2766-3 · Cited by 200 · see citing works
Lauritzen, A. D., Rodríguez‐Ruiz, A., von Euler‐Chelpin, M., Lynge, E., Vejborg, I., Nielsen, M., Karssemeijer, N., & Lillholm, M. (2022) · Radiology · doi:10.1148/radiol.210948 · Cited by 172 · see citing works
Prospective implementation of AI-assisted screen reading to improve early detection of breast cancer
Ng, A. Y., Oberije, C., Ambrózay, É., Szabó, E., Serfőző, O., Karpati, E., Fox, G., Glocker, B., Morris, E. A., Forrai, G., et al. (2023) · Nature Medicine · doi:10.1038/s41591-023-02625-9 · Cited by 154 · see citing works
Larsen, M., Aglen, C. F., Lee, C. I., Hoff, S. R., Lund-Hanssen, H., Lång, K., Nygård, J. F., Ursin, G., & Hofvind, S. S. H. (2022) · Radiology · doi:10.1148/radiol.212381 · Cited by 120 · see citing works
Self-citationCan artificial intelligence reduce the interval cancer rate in mammography screening?
Lång, K., Hofvind, S. S. H., Rodríguez‐Ruiz, A., & Andersson, I. (2021) · European Radiology · doi:10.1007/s00330-021-07686-3 · Cited by 108 · see citing works
Self-citationFayanju, O. M., & Thompson, A. M. (2016) · Breast Diseases A Year Book Quarterly · doi:10.1016/j.breastdis.2016.04.021 · Cited by 70 · see citing works
Cross-national comparison of screening mammography accuracy measures in U.S., Norway, and Spain
Domingo, L., Hofvind, S. S. H., Hubbard, R. A., Román, M., Benkeser, D. C., Sala, M., & Castells, X. (2015) · European Radiology · doi:10.1007/s00330-015-4074-8 · Cited by 59 · see citing works
Self-citationVargas‐Palacios, A., Sharma, N., & Sagoo, G. S. (2023) · Nature Communications · doi:10.1038/s41467-023-41754-0 · Cited by 57 · see citing works
Koch, H. W., Larsen, M., Bartsch, H., et al. (2023) · European Radiology · doi:10.1007/s00330-023-09461-y · Cited by 34 · see citing works
Elías-Cabot, E., Romero-Martín, S., Raya-Povedano, J. L., Brehl, A.-K., & Benito, M. Á. (2023) · European Radiology · doi:10.1007/s00330-023-10426-4 · Cited by 32 · see citing works
The emperor has few clothes: a realistic appraisal of current AI in radiology
Huisman, M., van Ginneken, B., & Harvey, H. (2024) · European Radiology · doi:10.1007/s00330-024-10664-0 · Cited by 20 · see citing works
Estimation of the stage-wise costs of breast cancer in Germany using a modeling approach
Khan, S. A., Hernández-Villafuerte, K., Hernández, D., et al. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2022.946544 · Cited by 16 · see citing works
Koch, H. W., Larsen, M., Bartsch, H., Martiniussen, M. A., Styr, B. M., Fagerheim, S., Haldorsen, I. H. S., & Hofvind, S. S. H. (2024) · European Radiology · doi:10.1007/s00330-024-10662-2 · Cited by 14 · see citing works
Self-citationArtificial intelligence for breast cancer screening: breathtaking results and a word of caution
Segnan, N., & Ponti, A. (2023) · The Lancet Oncology · doi:10.1016/s1470-2045(23)00336-4 · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Artificial intelligence across the cancer care continuum
Riaz, I. B., Khan, M. A., & Osterman, T. J. (2025) · Cancer · doi:10.1002/cncr.70050 · Cited by 40 · see citing works
Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery
Kuno, M., Osumi, H., Udagawa, S., Yoshikawa, K., Ooki, A., Shinozaki, E., Ishikawa, T., Oba, J., Yamaguchi, K., & Sakurada, K. (2025) · Current Oncology · doi:10.3390/curroncol32110588 · Cited by 7 · see citing works
- Authors
- Hernström, V., Josefsson, V., Sartor, H., Schmidt, D., Larsson, A.-M., Hofvind, S., Andersson, I., Rosso, A., Hagberg, O., & Lång, K.
- Affiliations
- Lund University (SE)
- Cancer Registry of Norway (NO)
- Corresponding author
- Lång, Kristina
- ORCID
- Venue
- The Lancet Digital Health
- Publisher
- Elsevier BV
- Published
- 2025-03
- Volume
- 7
- Issue
- 3
- Pages
- e175-e183
- ISSN
- 2589-7500 (ISSN-L)
- OpenAlex
- W4407091026
- Cited by
- 174
- References
- 26
- Citations by year
- 2026: 108 · 2025: 65 · 2020: 1
- FWCI
- 69.39
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- The Lancet Digital Health (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Lund University Publications (Lund University) (submittedVersion, cc-by)
- Funders
- Skånes universitetssjukhus
- Cancerfonden (22 0611FE)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Digital Radiography and Breast Imaging
- Health Sciences › Medicine › Oncology › Global Cancer Incidence and Screening
- Keywords
- breast cancer, artificial intelligence, mammography screening, cancer detection, recall rate, false positive rate, double reading, non-inferiority, invasive breast cancer, AI-assisted triage, breast cancer mortality reduction, positive predictive value
- MeSH terms
- Aged, Artificial Intelligence, Breast Neoplasms, Female, Humans, Mammography, Mass Screening, Middle Aged, Sweden, Single-Blind Method, Early Detection of Cancer
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
