A groundbreaking interim safety analysis of the first randomized trial investigating the use of artificial intelligence (AI) in a national breast cancer screening program has revealed encouraging results.
The trial, conducted in Sweden with over 80,000 women, demonstrated that AI-supported screening detected 20% more cancers compared to routine double reading of mammograms by two breast radiologists. Moreover, the use of AI did not increase false positives and significantly reduced the mammogram reading workload by 44%.
The findings were published in The Lancet Oncology journal, highlighting the potential of AI to make mammography screening more accurate and efficient.
However, researchers caution that the primary outcome results, evaluating whether AI reduces interval cancers (cancers diagnosed between screenings), are not expected for several years. This will determine whether the use of AI in mammography screening is fully justified.
The study aims to assess whether combining radiologists’ expertise with AI can help detect interval cancers that are often missed by traditional screening. Additionally, the cost-effectiveness of integrating AI technology will be evaluated.
“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,” cautions 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.”
Breast cancer screening with mammography is crucial in detecting breast cancer at an early and treatable stage. However, up to 30% of interval cancers that should have been identified in preceding screening mammograms are missed. AI has been proposed as an automated second reader for mammograms to reduce workload and improve accuracy.
Between April 2021 and July 2022, over 80,000 women aged 40-80 years were randomly assigned to either AI-supported analysis or standard analysis without AI. The interim analysis compared screening performance and workload in both groups. The AI system first analyzed mammography images and predicted the risk of cancer on a scale of one to ten. Based on the risk score, one or two radiologists further analyzed the image.
Results revealed that AI-supported screening detected six cancers per 1,000 women screened, compared to five per 1,000 with standard double reading without AI. The recall rates for additional testing were similar in both groups, indicating that cancer detection rates did not decline. Importantly, AI significantly reduced radiologists’ workload, leading to 44% fewer screen readings.
Despite the promising findings, researchers acknowledged limitations, including the trial’s single-center analysis and the dependence on radiologists’ performance. The final results, expected in several years, will provide comprehensive insights into AI’s potential in detecting interval cancers and its overall effectiveness in mammography screening.
The trial’s interim analysis highlights the promising role of AI in mammography screening, offering the possibility of enhancing diagnostic accuracy and easing radiologist workload.
“The greatest potential of AI right now is that it could allow radiologists to be less burdened by the excessive amount of reading,” says Lång. “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.”
However, more research is required to fully understand its impact on patients’ outcomes and the cost-effectiveness of incorporating AI technology.
Despite the promising findings, the authors note several limitations including that the analysis was conducted at a single centre and was limited to one type of mammography device and one AI system which might limit the generalisability of the results.
They also note that while technical factors will affect the performance and processing of the AI system, these will likely be less important than the experience of radiologists. Because the AI-supported system places the final decision on whether to recall women on radiologists, the results are dependent on their performance. In this trial, radiologists were moderately to highly experienced, which could limit the generalisability of the findings to less experienced readers. Lastly, information on race and ethnicity was not collected.
Writing in a linked Comment, Dr Nereo Segnan, former Head of the Unit of Cancer Epidemiology and past Director of Department of Screening at CPO Piemonte in Italy (who was not involved in the study) notes that the AI risk score for breast cancer seems very accurate at being able to separate high risk from low-risk women, adding that, “In risk stratified screening protocols, the potential for appropriately modulating the criteria for recall in low-risk and high-risk groups is remarkable.”
However, he cautions that: “In the AI-supported screening group of the MASAI trial, the possible presence of overdiagnosis (ie, the system identifying non-cancers) or over-detection of indolent lesions, such as a relevant portion of ductal carcinomas in situ, should prompt caution in the interpretation of results that otherwise seem straightforward in favouring the use of AI…It is, therefore, important to acquire biological information on the detected lesions. The final results of the MASAI trial are expected to do so, as the characteristics of identified cancers and the rate of interval cancers—not just the detection rate—are indicated as main outcomes. An important research question thus remains: is AI, when appropriately trained, able to capture relevant biological features—or, in other words, the natural history of the disease—such as the capacity of tumours to grow and disseminate?”
The use of AI in breast cancer screening has the potential to revolutionize early detection and improve patient outcomes, making it a significant step forward in the fight against breast cancer.
Note: Further updates on the trial and its implications will be reported as the study progresses.