Cloud Hosting

By Matthew StengerPosted: 8/14/2023 11:32:00 AM Last Updated: 8/14/2023 12:54:38 PM

In a Swedish study (Mammography Screening with Artificial Intelligence [MASAI]) reported in The Lancet Oncology, Lng et al found that artificial intelligence (AI)-supported screen reading was associated with a similar cancer detection rate and a lower screen-reading workload vs standard double reading for patients undergoing mammography screening for breast cancer.

Study Details

The current report is a prespecified clinical safety analysis, performed after 80,000 patients were enrolled in the study. In the MASAI trial, women aged 40 to 80 years eligible for mammography screening at four sites in Sweden were randomly assigned to receive AI-supported screening (n = 39,996) or standard double reading without AI (n = 40,024). The lowest acceptable safety limit in the AI group was a cancer detection rate of > 3 per 1,000 screened participants.

Key Findings

AI-supported screening among 39,996 participants resulted in 244 screen-detected cancers, 861 recalls, and a total of 46,345 screen readings. Standard screening among 40,024 participants resulted in 203 screen-detected cancers, 817 recalls, and a total of 83,231 screen readings. The screen-reading workload was reduced by 44.3% in the AI group.

Cancer detection rates were 6.1 (95% confidence interval [CI] = 5.46.9) per 1,000 screened in the AI group and 5.1 (95% CI = 4.45.8) per 1,000 in the control group (ratio = 1.2; 95% CI = 1.01.5, P = .052). Recall rates were 2.2% (95% CI = 2.0%2.3%) and 2.0% (95% CI = 1.9%2.2%). False-positive rates were 1.5% (95% CI = 1.4%1.7%) in both groups. The positive predictive value of recall was 28.3% (95% CI = 25.3%31.5%) and 24.8% (95% CI = 21.9%28.0%).

A total of 184 (75%) of 244 detected cancers in the AI group and 165 (81%) of 203 in the control group were invasive. Totals of 60 (25%) and 38 (19%) were in situ.

The investigators concluded: AI-supported mammography screening resulted in a similar cancer detection rate compared with standard double reading, with a substantially lower screen-reading workload, indicating that the use of AI in mammography screening is safe. The trial was thus not halted, and the primary endpoint of interval cancer rate will be assessed in 100,000 enrolled participants after 2 years of follow-up.

Kristina Lng, PhD, of the Division of Diagnostic Radiology, Department of Translational Medicine, Lund University, Malm, is the corresponding author for The Lancet Oncology article.

Disclosure: The study was funded by the Swedish Cancer Society, Confederation of Regional Cancer Centres, and Swedish governmental funding for clinical research. For full disclosures of the study authors, visit thelancet.com.

Read this article:

AI-Supported Screen Reading vs Standard Double Reading in ... - The ASCO Post