AI-supported mammography is safer for patients, slashes missed cancers, and boosts workload efficiency for radiologists.
AI-supported mammography is not only safer but significantly more efficient than traditional techniques, based on findings of the landmark Mammography Screening with Artificial Intelligence (MASAI) randomized controlled trial (RCT) conducted in Sweden, and published in The Lancet.(1✔ ✔Trusted Source
Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading without AI in the MASAI study: a randomised, controlled, non-inferiority, single-blinded, population-based, screening-accuracy trial
Go to source
)
The study confirmed AI-powered mammography as a new benchmark for breast cancer screening.
By incorporating artificial intelligence in healthcare, especially in the breast cancer diagnosis, the study found that AI identifies 9% more cancers during earlier scans and, most importantly, reduces the rate of missed or interval cancers by 12% (which are not found by radiologists manually) in the follow-up.(2✔ ✔Trusted Source
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
Go to source)
Patients in the AI group saw a 27% reduction in aggressive cancer subtypes that are diagnosed between scheduled screenings.
According to lead author Dr. Kristina Lång, “the findings justify a comprehensive launch of AI in mammography, providing a ‘win’ for patient outcomes and clinical efficiency.”
AI-supported mammography lowers screen-reading workload for doctors by up to 44.3%, proving as an effective tool for future breast cancer screening.(3✔ ✔Trusted Source
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
Go to source)(4✔ ✔Trusted Source
Artificial intelligence (AI) for breast cancer screening: BreastScreen population-based cohort study of cancer detection
Go to source)
Can AI Reduce “Missed” Interval Cancers in Modern Screening?
Mammography screening has been associated with a lower breast cancer death rate, largely due to the early detection and treatment of the cancer. However, despite European guidelines recommending two radiologists read mammograms, some cancers still go undetected in screening.
Estimates suggest that 20-30% of breast cancers diagnosed after a negative screen and before the next scheduled screen (interval cancers) could have been spotted at the preceding mammogram. Interval cancers are often more aggressive or advanced than cancers detected during routine screening, making them harder to treat effectively.
Previous observational studies and interim results of this trial have found AI-supported mammography increases breast cancer detection compared with standard screening, however a key question has been if this increase in breast cancer detection translates into a reduction in interval cancers.
AI Reduces Aggressive Cancer Diagnoses by 27% in Earlier Screening
Between April 2021 and Dec 2022, over 100,000 women who were part of mammography screening at four sites in Sweden were randomly assigned to either AI-supported mammography screening (intervention arm) or to standard double reading by radiologists without AI (control arm). Double reading, where two radiologists read each mammogram, is standard practice in European screening programmes.
In the intervention arm, a specialist AI system analysed the mammograms and triaged low-risk cases to single reading and high-risk cases to double reading performed by radiologists. AI was also used as detection support to the radiologists, in which it highlighted suspicious findings in the image.
The AI system was trained, validated, and tested with more than 200,000 examinations from multiple institutions across more than ten countries.
During the two years follow up, there were 1.55 interval cancers per 1,000 women (82/53,043) in the AI-supported mammography group, compared to 1.76 interval cancers per 1,000 women (93/52,872) in the control group: a 12% reduction in interval cancer diagnosis for the AI arm.
AI Addresses the Radiologist Workload Shortage, Enhancing the Performance
In the AI-supported mammography group, 81% of cancer cases (338/420) were detected at screening, compared to 74% of cancer cases (262/355) in the control group: a 9% increase. The rate of false positives was similar for both groups, at 1.5% in the intervention group and 1.4% in the control group.
First author Jessie Gommers, PhD student, Radboud University Medical Centre, Netherlands, says, “Our study does not support replacing healthcare professionals with AI as the AI-supported mammography screening still requires at least one human radiologist to perform the screen reading, but with support from AI.”
“However, our results potentially justify using AI to ease the substantial pressure on radiologists’ workloads, enabling these experts to focus on other clinical tasks, which might shorten the waiting times for patients.”
Researchers Suggest for Widespread Implementation of AI in Breast Screening
The authors note several limitations including that the analysis was conducted in one country (Sweden), was limited to one type of mammography device and one AI system which might limit the generalisability of the results.
Dr. Lång says, “Further studies on future screening rounds with this group of women and cost-effectiveness will help us understand the long-term benefits and risks of using AI-supported mammography screening.”
“If they continue to suggest favourable outcomes for AI-supported mammography screening compared with standard screening, there could be a strong case for using AI in widespread mammography screening, especially as we face staff shortages.”
Reference:
- Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading without AI in the MASAI study: a randomised, controlled, non-inferiority, single-blinded, population-based, screening-accuracy trial – (https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(25)02464-X/abstract)
- 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://www.thelancet.com/journals/lanonc/article/PIIS1470-2045(23)00298-X/abstract)
- 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://www.thelancet.com/journals/landig/article/PIIS2589-7500(24)00267-X/fulltext)
- Artificial intelligence (AI) for breast cancer screening: BreastScreen population-based cohort study of cancer detection – (https://www.thelancet.com/journals/ebiom/article/PIIS2352-3964(23)00063-4/fulltext)
Source-Eurekalert