Dr. Kristina Lång from Lund University in Sweden published in The Lancet Oncology.
A Swedish trial revealed that AI-assisted breast screenings detected 20% more cancers compared to double reading of mammograms by two radiologists, without increasing false positives. The AI also reduced radiologists' screen-reading workload by 44.3%. The preliminary findings involved over 80,000 women and were published in The Lancet Oncology journal. Despite concerns, the researchers clarified that AI isn't intended to replace radiologists but to aid them. Future goals include determining if AI can reduce the number of missed cancer cases in annual screenings. The trial, involving a total of 100,000 participants, continues until around December 2024.
The European Commission’s guidelines recommend the double reading of mammograms by two radiologists but this means they have a large workload amidst a shortage of breast radiologists in many countries.
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.
The participants and the radiographers acquiring the screening examinations, but not the radiologists reading the screening examinations, were masked to study group allocation. The AI system (Transpara version 1.7.0) provided an examination-based malignancy risk score on a 10-level scale that was used to triage screening examinations to single reading (score 1–9) or double reading (score 10), with AI risk scores (for all examinations) and computer-aided detection marks (for examinations with risk score 8–10) available to the radiologists doing the screen reading. Here we report the prespecified clinical safety analysis, to be done after 80 000 women were enrolled, to assess the secondary outcome measures of early screening performance (cancer detection rate, recall rate, false positive rate, positive predictive value [PPV] of recall, and type of cancer detected [invasive or in situ]) and screen-reading workload.
In the AI-supported group, 244 cancers were detected and 861 women were recalled, while in the double-reading group without AI, 203 cancers were detected and 817 women were recalled.
