# MASAI (Mammography Screening with Artificial Intelligence)

Source: https://onco.cc/trials/masai/  
OnCo record `masai` (Trial). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

The first randomised trial of AI in breast screening found more cancers and cut radiologists' reading work almost in half without more false alarms.

## Summary

The prespecified interim safety analysis (Lancet Oncology 2023) of 80,020 women reported a cancer detection rate of 6.1 per 1,000 in the AI-supported arm versus 5.1 per 1,000 with standard double reading, similar recall rates (2.2% versus 2.0%) and false-positive rates (1.5% in both), and a 44.3% reduction in screen-reading workload. The final analysis of the full cohort (published 2025) confirmed a 29% increase in cancer detection, driven by small invasive cancers and in situ disease, with the interval-cancer endpoint to follow. MASAI is the evidence base for the AI-as-one-reader model that several European programmes, and the NHS EDITH trial, are now adopting.

## Fields

- Kind: Trial
- Status: positive
- Last checked: 2026-09-10
- Registry id: NCT04838756
- Phase: 3
- Setting: Population screening in Sweden: AI-supported reading (Transpara, single or double reading by risk score) versus standard double reading
- Sponsor: Lund University / Region Skåne
- Enrolled: 105934
- Result: Cancer detection 6.1 vs 5.1 per 1,000; screen-reading workload reduced 44.3% (interim).
- Outcomes: Cancer detection rate (interim analysis): AI-supported screening 6.1 per 1,000 screened vs Standard double reading 5.1 per 1,000 screened

## Sources

- ClinicalTrials.gov NCT04838756: https://clinicaltrials.gov/study/NCT04838756
- MASAI interim analysis (Lancet Oncol 2023): https://doi.org/10.1016/S1470-2045(23)00298-X

## Connected records

- cancers: [HR-positive / HER2-negative breast cancer](https://onco.cc/cancers/breast-hr-positive/), [Triple-negative breast cancer (TNBC)](https://onco.cc/cancers/tnbc/)
- technologies: [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [Mammography & tomosynthesis](https://onco.cc/technologies/mammography/)
- drugs: [Transpara](https://onco.cc/drugs/transpara/)
- companies: [ScreenPoint Medical](https://onco.cc/companies/screenpoint-medical/)
- terms: [Screening](https://onco.cc/terms/screening/)
- key papers: [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](https://onco.cc/key-papers/paper-masai-lancet-digit-health-2025/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/), [Diagnostics roadmap: stains → gene panels → blood tests that decide treatment](https://onco.cc/roadmaps/diagnostics-roadmap/)

---
JSON: https://onco.cc/api/v1/entities/masai.json