• Posted January 30, 2026

AI-Assisted Mammograms Catch More Hard-To-Detect Breast Cancers, Clinical Trial Shows

Artificial intelligence (AI) can help reduce the number of breast cancers found between mammogram screenings, clinical trial results show.

There was a 12% reduction in cancer diagnoses in the years following AI-supported breast cancer screening — a key test of effectiveness, researchers reported Jan. 29 in The Lancet.

Researchers previously reported a 29% increase in cancer detection without an increase in false positives when doctors used AI-supported mammography.

“Our study is the first randomized controlled trial investigating the use of AI in breast cancer screening and the largest to date looking at AI use in cancer screening in general,” said senior researcher Dr. Kristina Lang, an associate professor at Lund University in Sweden.

“It finds that AI-supported screening improves the early detection of clinically relevant breast cancers, which led to fewer aggressive or advanced cancers diagnosed in between screenings,” Lang said in a news release.

Previous studies have estimated that as many as 30% of breast cancers diagnosed after a negative screening could have been spotted from that mammogram, researchers said in background notes.

Doctors and researchers have been training AI programs to help improve analysis of mammograms, with the aim of catching those hard-to-see cancers.

However, it’s been an open question whether AI-aided breast cancer screening actually translates into a reduction in cancers found between mammograms, researchers said.

For this new study, more than 100,000 Swedish women undergoing mammography screening were assigned to either AI-supported mammography or standard screening, in which two radiologists evaluated each mammogram. The screenings took place between April 2021 and December 2022.

The AI used in this clinical trial had been trained and tested using more than 200,000 prior examinations from multiple hospitals across more than 10 countries, researchers said.

In the AI-supported mammogram group, 81% of cancer cases were detected at screening compared to 74% in the standard screening group, the study said.

Between screenings, about 1.55 cancers per 1,000 women were detected in the AI group and 1.76 per 1,000 in the control group.

Cancers also tended to be caught at an earlier, more treatable stage with AI assistance.

There were 16% fewer invasive cancers, 21% fewer large cancers and 27% fewer aggressive cancers in the AI group compared to standard screening, the study said.

The rates of false positives were about the same, 1.5% in the AI group and 1.4% in the control group.

"Our study does not support replacing health care 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,” said lead researcher Jessie Gommers, a doctoral student at Radboud University Medical Center in The Netherlands.

“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,” Gommers said in a news release.

Earlier results reported from the clinical trial showed a 44% reduction in radiologists’ workload with AI assistance.

However, more study is needed to see if AI could help breast cancer screening in other countries, or could help less experienced radiologists read mammograms, researchers said.

“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,” Lang said.

“If they continue to suggest favorable 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,” she said.

More information

The U.S. Centers for Disease Control and Prevention has more on breast cancer screening.

SOURCE: The Lancet, news release, Jan. 29, 2026