New research from Lund University’s MASAI trial shows that artificial intelligence (AI) can detect 29% more breast cancer cases than traditional screening methods.
The findings, published in The Lancet Digital Health, suggest that AI-supported mammography could significantly improve early cancer detection, including more invasive cases that require urgent treatment.
The MASAI trial (Mammography Screening with Artificial Intelligence) began in 2021, aiming to evaluate whether AI could enhance mammography screening. Initial results from 2023 already indicated that AI detected 20% more cancers than traditional methods.
Now, the latest report shows an even greater improvement, with AI spotting 29% more cases. The study’s lead researcher, Kristina Lång, a diagnostic radiology expert at Lund University and consultant at Unilabs Mammography Unit in Malmö, expressed excitement over these results.
How AI Screening Works
Each year, around one million Swedish women undergo mammograms, with each image traditionally reviewed by two breast radiologists. However, there is a shortage of specialists, making this process time-consuming and challenging.
In the MASAI trial, AI was used to analyze mammograms and identify cases with a higher risk of cancer. These high-risk cases were then reviewed by two radiologists, while lower-risk cases were examined by just one radiologist, all with AI assistance.
The study analyzed results from nearly 106,000 women. Half underwent traditional screening, while the other half had AI-supported screening. AI-assisted screening detected breast cancer in 338 women, compared to 262 in the traditional screening group. AI was also more effective in detecting early-stage invasive cancers, identifying 24% more cases (270 vs. 217).
Why Early Detection Matters
Detecting cancer early can significantly improve survival rates and reduce the need for aggressive treatments. Some of the cancers detected with AI were more aggressive types that benefit the most from early intervention.
Lång emphasized that finding these cancers sooner could mean less suffering for patients, better treatment outcomes, and reduced healthcare costs.
AI was also particularly effective in identifying pre-cancerous lesions, known as in situ cancers. The study found 51% more such cases in the AI group (68 vs. 45). Many of these cases were of a more severe type, which can develop into invasive cancer if left undetected.
AI Does Not Increase False Positives
One common concern with AI in medical diagnosis is the risk of false positives—cases where a patient is mistakenly recalled for further testing but does not have cancer. However, the MASAI trial found that AI did not significantly increase false positives. Only seven more women (a 1% increase) were mistakenly recalled in the AI group compared to traditional screening.
AI Reduces Radiologists’ Workload
Another major benefit of AI-supported screening is that it reduces the workload for radiologists. The study showed a 44% decrease in the amount of work required from breast radiologists, which could help address the shortage of specialists and allow more efficient use of medical resources.
What’s Next?
Despite AI’s success in detecting more cancers during screening, some cases still go undetected. Researchers are now focusing on “interval cancers”—cases diagnosed between regular screenings. The MASAI trial will track the 106,000 participants for two years to see if AI can also help detect these cancers earlier.
The results of the MASAI trial have already led to the adoption of AI-assisted mammography in several regional screening programs in Sweden. If AI continues to show strong results, it could become a standard tool in breast cancer screening worldwide, helping to save lives through earlier and more accurate detection.
If you care about breast cancer, please read studies about a major cause of deadly breast cancer, and this daily vitamin is critical to cancer prevention.
For more information about cancer, please see recent studies that new cancer treatment could reawaken the immune system, and results showing vitamin D can cut cancer death risk.
The research findings can be found in The Lancet Digital Health.
Copyright © 2025 Knowridge Science Report. All rights reserved.
