Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

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

Open access

Abstract

Background Retrospective studies have shown promising results using artificial intelligence (AI) to improve mammography screening accuracy and reduce screen-reading workload; however, to our knowledge, a randomised trial has not yet been conducted. We aimed to assess the clinical safety of an AI-supported screen-reading protocol compared with standard screen reading by radiologists following mammography.Methods In this randomised, controlled, population-based trial, women aged 40-80 years eligible for mammography screening (including general screening with 1·5-2-year intervals and annual screening for those with moderate hereditary risk of breast cancer or a history of breast cancer) at four screening sites in Sweden were informed about the study as part of the screening invitation. Those who did not opt out were randomly allocated (1:1) to AI-supported screening (intervention group) or standard double reading without AI (control group). Screening examinations were automatically randomised by the Picture Archive and Communications System with a pseudo-random number generator after image acquisition. The participants and the radiographers acquiring the screening examinations, but not the radiologists reading the screening examinations, were masked to study group allocation. The AI system (Transpara version 1.7.0) provided an examination-based malignancy risk score on a 10-level scale that was used to triage screening examinations to single reading (score 1-9) or double reading (score 10), with AI risk scores (for all examinations) and computer-aided detection marks (for examinations with risk score 8-10) available to the radiologists doing the screen reading. Here we report the prespecified clinical safety analysis, to be done after 80 000 women were enrolled, to assess the secondary outcome measures of early screening performance (cancer detection rate, recall rate, false positive rate, positive predictive value [PPV] of recall, and type of cancer detected [invasive or in situ]) and screen-reading workload. Analyses were done in the modified intention-to-treat population (ie, all women randomly assigned to a group with one complete screening examination, excluding women recalled due to enlarged lymph nodes diagnosed with lymphoma). The lowest acceptable limit for safety in the intervention group was a cancer detection rate of more than 3 per 1000 participants screened. The trial is registered with ClinicalTrials.gov, NCT04838756, and is closed to accrual; follow-up is ongoing to assess the primary endpoint of the trial, interval cancer rate.Findings Between April 12, 2021, and July 28, 2022, 80 033 women were randomly assigned to AI-supported screening (n=40 003) or double reading without AI (n=40 030). 13 women were excluded from the analysis. The median age was 54·0 years (IQR 46·7-63·9). Race and ethnicity data were not collected. AI-supported screening among 39 996 participants resulted in 244 screen-detected cancers, 861 recalls, and a total of 46 345 screen readings. Standard screening among 40 024 participants resulted in 203 screen-detected cancers, 817 recalls, and a total of 83 231 screen readings. Cancer detection rates were 6·1 (95% CI 5·4-6·9) per 1000 screened participants in the intervention group, above the lowest acceptable limit for safety, and 5·1 (4·4-5·8) per 1000 in the control group-a ratio of 1·2 (95% CI 1·0-1·5; p=0·052). Recall rates were 2·2% (95% CI 2·0-2·3) in the intervention group and 2·0% (1·9-2·2) in the control group. The false positive rate was 1·5% (95% CI 1·4-1·7) in both groups. The PPV of recall was 28·3% (95% CI 25·3-31·5) in the intervention group and 24·8% (21·9-28·0) in the control group. In the intervention group, 184 (75%) of 244 cancers detected were invasive and 60 (25%) were in situ; in the control group, 165 (81%) of 203 cancers were invasive and 38 (19%) were in situ. The screen-reading workload was reduced by 44·3% using AI.Interpretation AI-supported mammography screening resulted in a similar cancer detection rate compared with standard double reading, with a substantially lower screen-reading workload, indicating that the use of AI in mammography screening is safe. The trial was thus not halted and the primary endpoint of interval cancer rate will be assessed in 100 000 enrolled participants after 2-years of follow up.Funding Swedish Cancer Society, Confederation of Regional Cancer Centres, and the Swedish governmental funding for clinical research (ALF).

Overview

CoChat Summary

TL;DR

In the MASAI trial, AI-supported screen reading resulted in a similar cancer detection rate to standard double reading (6·1 vs 5·1 per 1000 screened; ratio 1·2, 95% CI 1·0–1·5) and reduced screen-reading workload by 44·3%. The prespecified safety analysis supported continuing the trial to assess the primary endpoint of interval cancer rate.

Key findings

  • Cancer detection rate was 6·1 per 1000 screened participants (95% CI 5·4–6·9) in the AI-supported group versus 5·1 per 1000 (4·4–5·8) in the control group, a ratio of 1·2 (95% CI 1·0–1·5; p=0·052), above the prespecified lowest acceptable safety limit of more than 3 per 1000.
  • Recall rate was 2·2% (95% CI 2·0–2·3) with AI versus 2·0% (1·9–2·2) in controls; false positive rate was 1·5% (95% CI 1·4–1·7) in both groups; PPV of recall was 28·3% (25·3–31·5) versus 24·8% (21·9–28·0).
  • AI-supported screening detected 244 cancers (184 [75%] invasive, 60 [25%] in situ) among 39,996 participants; standard screening detected 203 cancers (165 [81%] invasive, 38 [19%] in situ) among 40,024 participants.
  • Screen-reading workload was reduced by 44·3% with AI: 46,345 readings versus 83,231 readings.

Methods

  • Randomised, controlled, population-based, non-inferiority, single-blinded screening accuracy study at four Swedish screening sites; women aged 40–80 years eligible for mammography screening were randomly allocated 1:1 to AI-supported screening (n=40,003) or standard double reading without AI (n=40,030); 13 women were excluded, leaving a modified intention-to-treat population.
  • The AI system (Transpara version 1.7.0) provided an examination-based malignancy risk score on a 10-level scale, triaging examinations with score 1–9 to single reading and score 10 to double reading; AI risk scores and computer-aided detection marks (for scores 8–10) were available to radiologists.
  • This prespecified clinical safety analysis, performed after 80,000 women were enrolled, assessed early screening performance (cancer detection rate, recall rate, false positive rate, PPV of recall, and type of cancer detected) and screen-reading workload.

Limitations

  • Stated in the paper: race and ethnicity data were not collected; follow-up is ongoing to assess the primary endpoint of interval cancer rate, so this report covers early screening performance rather than final trial outcomes.
  • Evident from the text: the findings come from a single trial in Sweden using one AI system and version, so longer-term outcomes and broader generalisability remain to be established.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1016/s1470-2045(23)00298-x

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 0 Not valid · 0 Not checked · 31 Own results and interpretations

15 more claims

Create a free account to see all 31 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 10
  • It may state two separate claims as one. 2

Create a free account to see these claims.

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?

1 more claim about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Citations

Cites

Show all 30 references

Cited by

See all 598

Metadata

Authors
Lång, K., Josefsson, V., Larsson, A.-M., Larsson, S., Högberg, C., Sartor, H., Hofvind, S., Andersson, I., & Rosso, A.
Affiliations
  • Lund University (SE)
  • Cancer Registry of Norway (NO)
Corresponding author
Lång, Kristina
Venue
The Lancet Oncology
Publisher
Elsevier BV
Published
2023-08
Volume
24
Issue
8
Pages
936-944
ISSN
1470-2045 (ISSN-L)
OpenAlex
W4385448527
Cited by
598
References
30
Citations by year
2026: 197 · 2025: 205 · 2024: 164 · 2023: 31
FWCI
56.30
Type
journal article
Language
en
Open access
Locations
  • The Lancet Oncology (publishedVersion)
  • PubMed (publishedVersion)
  • Lund University Publications (Lund University) (submittedVersion)
  • NORA - Norwegian Open Research Archives (submittedVersion, other-oa)
Funders
  • Swedish Cancer Society (22 0611FE)
  • Skånes universitetssjukhus
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Digital Radiography and Breast Imaging
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
artificial intelligence, mammography screening, computer-aided detection, double reading, clinical safety, breast cancer detection, recall rate, false positive rate, positive predictive value, non-inferiority, breast cancer screening, breast cancer in situ
MeSH terms
Artificial Intelligence, Breast Neoplasms, Female, Humans, Mammography, Mass Screening, Middle Aged, Predictive Value of Tests, Retrospective Studies, 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.

A language model drew the claims from the paper on 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: 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. https://app.cochat.ai/papers/10.1016/s1470-2045(23)00298-x
The paper
Lång, K., Josefsson, V., Larsson, A.-M., Larsson, S., Högberg, C., Sartor, H., Hofvind, S., Andersson, I., & Rosso, A. (2023). 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. The Lancet Oncology. https://doi.org/10.1016/s1470-2045(23)00298-x

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.