AI assistance increases cancer detection in routine mammography without prolonging reading time
The study reports a prospective alternating-month analysis of 4577 routine mammography examinations interpreted by four radiologists to evaluate the impact of a commercial AI system on workflow and diagnostic performance. Investigators found that AI assistance significantly increased the overall cancer detection rate to 22.3 per 1000 examinations compared with 11.5 per 1000 without AI, while mean reading times remained comparable at approximately 65 seconds. Abnormal interpretation rates rose only during diagnostic examinations (18.7% versus 12.1%), with no significant difference observed in screening exams. These findings indicate that AI integration can support routine mammography workflows by improving cancer detection without disrupting reading speed, though diagnostic applications require careful oversight to manage increased abnormal calls.
The original study
Impact of AI assistance on reading time, cancer detection rate, and abnormal interpretation rate in screening and diagnostic mammography: a prospective alternating-month study.
- Authors
- Lee SE, Heo SJ, Shin HJ, Kim EK
- Journal
- European radiology
- Type
- Journal Article
- PMID
- 42593499
Original abstract
OBJECTIVE: To compare reading time, cancer detection rate (CDR), and abnormal interpretation rate (AIR) between AI-assisted and non-AI-assisted periods in screening and diagnostic mammography performed in routine clinical practice. MATERIALS AND METHODS: We prospectively collected reading times for consecutive two-view full-field digital mammography interpreted by four radiologists between August 2023 and July 2024. Both screening and diagnostic examinations were included. A commercially available AI system was integrated into the clinical workflow, with results displayed or hidden on a monthly basis. Reading time, CDR, and AIR were compared between two periods. For reading time analysis, a subset of 2917 examinations with times ≤ 5 min was included to minimize the impact of non-interpretive interruptions. Reading time was extracted from the PACS log. RESULTS: Among 4577 mammography examinations (mean age 51.7 ± 10.4 years), the overall CDR was higher during the AI-assisted period (22.3 vs 11.5 per 1000; p = 0.005). AIR did not differ for screening mammography (9.5% vs 8.4%; p = 0.293) but was higher with AI assistance for diagnostic mammography (18.7% vs 12.1%; p = 0.026). Mean reading times were comparable between AI-assisted and non-AI-assisted periods (65.0 vs 64.3 s; p = 0.723). CONCLUSION: AI assistance in routine mammography interpretation was not associated with prolonged reading time and was associated with a higher overall CDR. KEY POINTS: Question Does artificial intelligence assistance in routine mammography affect radiologists' reading time, cancer detection, or abnormal interpretation in daily practice? Findings Artificial intelligence assistance was not associated with prolonged reading time and was associated with a higher overall cancer detection rate. Abnormal interpretation increased only for diagnostic examinations, with no difference in screening examinations. Clinical relevance AI assistance may support screening mammography by aiding cancer detection without disrupting workflow, whereas diagnostic use should be applied carefully due to higher abnormal interpretation rates.