AI-supported mammography could improve cancer detection and reduce radiologist workload

AI-supported mammography can potentially detect more cancers compared with the routine double reading of mammograms by two breast radiologists, according to a new study published in The Lancet Oncology.

The use of artificial intelligence did not increase false positives and reduced the mammogram reading workload by 44%. This means the technique could free up radiologist time, an important finding considering there is a shortage of breast radiologists in many countries.

In the UK, there is a shortfall of around 41 radiologists, and it takes over a decade to train a radiologist capable of interpreting mammograms.

Recall rates in AI-supported screening similar to previous six months in clinic

The interim findings of study are based on a cohort of over 80,000 women in Sweden who had undergone a mammogram screening between April 2021 and July 2022.

The women were aged 40-80 years and were randomly assigned in a 1:1 ratio to either AI-supported analysis or standard analysis performed by two radiologists without AI.

This interim analysis compared early screening performance (e.g. cancer detection, recalls, false positives) and screen reading workload in both the intervention and control group.

In the AI-supported analysis, the AI system first analysed the mammography image and predicted the risk of cancer on a scale of one to 10 (where one is the lowest risk and 10 is the highest). If the risk score was less than 10, the image was further analysed by one radiologist, whereas if the risk was 10, then two radiologists analysed the image.

Women were recalled for additional testing if suspicious findings were detected. This was based on a final decision by the radiologists themselves, who were instructed to call back the cases with the highest 1% risk.

The recall rates averaged 2.2% (861 women) for AI-supported screening and 2.0% (817 women) for standard double reading without AI – similar to the recall rate in the clinic six months before the trial started.

AI-supported mammography detected 41 more cancers than standard screening

In total, 244 women (28%) recalled from AI-supported screening were found to have cancer compared with 203 women (25%) recalled from standard screening—resulting in 41 more cancers detected with the support of AI (of which 19 were invasive and 22 were in situ cancers). The false-positive rate was 1.5% in both arms.

Overall, AI-supported screening resulted in a cancer detection rate of six per 1,000 screened women compared to five per 1,000 for standard double reading without AI—equivalent to detecting one additional cancer for every 1,000 women screened.

Importantly, there were 36,886 fewer screen readings by radiologists in the AI-supported group than in the control group (46,345 vs 83,231), resulting in a 44% reduction in the screen-reading workload of radiologists.

However, the study’s authors are warning that AI is not yet ready to be implemented as standard practice in radiology clinics.

“These promising interim safety results should be used to inform new trials and programme-based evaluations to address the pronounced radiologist shortage in many countries. But they are not enough on their own to confirm that AI is ready to be implemented in mammography screening,” explains lead author Dr Kristina Lång from Lund University, Sweden.

“We still need to understand the implications on patients’ outcomes, especially whether combining radiologists’ expertise with AI can help detect interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology.”

However, Dr Lang says the findings suggest that AI could allow radiologists to be “less burdened by the excessive amount of reading.”

“While our AI-supported screening system requires at least one radiologist in charge of detection, it could potentially do away with the need for double reading of the majority of mammograms easing the pressure on workloads and enabling radiologists to focus on more advanced diagnostics while shortening waiting times for patients” she said.