dc.contributor.author | Larsen, Marthe | |
dc.contributor.author | Olstad, Camilla Flåt | |
dc.contributor.author | Lee, Christoph I. | |
dc.contributor.author | Hovda, Tone | |
dc.contributor.author | Hoff, Solveig Kristin Roth | |
dc.contributor.author | Martiniussen, Marit Almenning | |
dc.contributor.author | Mikalsen, Karl Øyvind | |
dc.contributor.author | Lund-Hanssen, Håkon | |
dc.contributor.author | Solli, Helene | |
dc.contributor.author | Silberhorn, Marko | |
dc.contributor.author | Sulheim, Åse Ø. | |
dc.contributor.author | Auensen, Steinar Gøytil | |
dc.contributor.author | Nygård, Jan Franz | |
dc.contributor.author | Hofvind, Solveig Sand-Hanssen | |
dc.date.accessioned | 2024-09-10T11:21:06Z | |
dc.date.available | 2024-09-10T11:21:06Z | |
dc.date.created | 2024-08-19T16:22:36Z | |
dc.date.issued | 2024 | |
dc.identifier.citation | Radiology: Artificial Intelligence (RAI). 2024, 6 (3), .1-9 | en_US |
dc.identifier.issn | 2638-6100 | |
dc.identifier.uri | https://hdl.handle.net/11250/3151120 | |
dc.description.abstract | A commercially available artificial intelligence system showed high performance in detecting breast cancers within 2 years of screening mammography and may help triage low-risk mammograms to reduce radiologist workload.
Purpose: To explore the stand-alone breast cancer detection performance, at different risk score thresholds, of a commercially available artificial intelligence (AI) system.
Materials and Methods: This retrospective study included information from 661 695 digital mammographic examinations performed among 242 629 female individuals screened as a part of BreastScreen Norway, 2004–2018. The study sample included 3807 screen-detected cancers and 1110 interval breast cancers. A continuous examination-level risk score by the AI system was used to measure performance as the area under the receiver operating characteristic curve (AUC) with 95% CIs and cancer detection at different AI risk score thresholds.
Results: The AUC of the AI system was 0.93 (95% CI: 0.92, 0.93) for screen-detected cancers and interval breast cancers combined and 0.97 (95% CI: 0.97, 0.97) for screen-detected cancers. In a setting where 10% of the examinations with the highest AI risk scores were defined as positive and 90% with the lowest scores as negative, 92.0% (3502 of 3807) of the screen-detected cancers and 44.6% (495 of 1110) of the interval breast cancers were identified with AI. In this scenario, 68.5% (10 987 of 16 040) of false-positive screening results (negative recall assessment) were considered negative by AI. When 50% was used as the cutoff, 99.3% (3781 of 3807) of the screen-detected cancers and 85.2% (946 of 1110) of the interval breast cancers were identified as positive by AI, whereas 17.0% (2725 of 16 040) of the false-positive results were considered negative.
Conclusion: The AI system showed high performance in detecting breast cancers within 2 years of screening mammography and a potential for use to triage low-risk mammograms to reduce radiologist workload. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Radiological Society of North America | en_US |
dc.relation.uri | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11140504/ | |
dc.title | Performance of an Artificial Intelligence System for Breast Cancer Detection on Screening Mammograms from BreastScreen Norway | en_US |
dc.title.alternative | Performance of an Artificial Intelligence System for Breast Cancer Detection on Screening Mammograms from BreastScreen Norway | en_US |
dc.type | Journal article | en_US |
dc.type | Peer reviewed | en_US |
dc.description.version | publishedVersion | en_US |
dc.rights.holder | This version of the article is not available due to the publisher copyright restrictions. | en_US |
dc.source.pagenumber | 1-9 | en_US |
dc.source.volume | 6 | en_US |
dc.source.journal | Radiology: Artificial Intelligence (RAI) | en_US |
dc.source.issue | 3 | en_US |
dc.identifier.doi | 10.1148/ryai.230375 | |
dc.identifier.cristin | 2287630 | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |