Diagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program

Basit Öğe Kaydı
dc.authoridSeker, Mustafa Ege/0000-0001-7664-5786
dc.authoridARIBAL, Erkin/0000-0002-5525-8696
dc.contributor.authorSeker, Mustafa Ege
dc.contributor.authorKoyluoglu, Yilmaz Onat
dc.contributor.authorOzaydin, Ayse Nilufer
dc.contributor.authorGurdal, Sibel Ozkan
dc.contributor.authorOzcinar, Beyza
dc.contributor.authorCabioglu, Neslihan
dc.contributor.authorOzmen, Vahit
dc.date.accessioned2024-10-29T17:58:18Z
dc.date.available2024-10-29T17:58:18Z
dc.date.issued2024
dc.departmentTekirdağ Namık Kemal Üniversitesi
dc.description.abstractObjectivesWe aimed to evaluate the early-detection capabilities of AI in a screening program over its duration, with a specific focus on the detection of interval cancers, the early detection of cancers with the assistance of AI from prior visits, and its impact on workload for various reading scenarios.Materials and methodsThe study included 22,621 mammograms of 8825 women within a 10-year biennial two-reader screening program. The statistical analysis focused on 5136 mammograms from 4282 women due to data retrieval issues, among whom 105 were diagnosed with breast cancer. The AI software assigned scores from 1 to 100. Histopathology results determined the ground truth, and Youden's index was used to establish a threshold. Tumor characteristics were analyzed with ANOVA and chi-squared test, and different workflow scenarios were evaluated using bootstrapping.ResultsThe AI software achieved an AUC of 89.6% (86.1-93.2%, 95% CI). The optimal threshold was 30.44, yielding 72.38% sensitivity and 92.86% specificity. Initially, AI identified 57 screening-detected cancers (83.82%), 15 interval cancers (51.72%), and 4 missed cancers (50%). AI as a second reader could have led to earlier diagnosis in 24 patients (average 29.92 +/- 19.67 months earlier). No significant differences were found in cancer-characteristics groups. A hybrid triage workflow scenario showed a potential 69.5% reduction in workload and a 30.5% increase in accuracy.ConclusionThis AI system exhibits high sensitivity and specificity in screening mammograms, effectively identifying interval and missed cancers and identifying 23% of cancers earlier in prior mammograms. Adopting AI as a triage mechanism has the potential to reduce workload by nearly 70%.Clinical relevance statementThe study proposes a more efficient method for screening programs, both in terms of workload and accuracy.Key Points center dot Incorporating AI as a triage tool in screening workflow improves sensitivity (72.38%) and specificity (92.86%), enhancing detection rates for interval and missed cancers.center dot AI-assisted triaging is effective in differentiating low and high-risk cases, reduces radiologist workload, and potentially enables broader screening coverage.center dot AI has the potential to facilitate early diagnosis compared to human reading.Key Points center dot Incorporating AI as a triage tool in screening workflow improves sensitivity (72.38%) and specificity (92.86%), enhancing detection rates for interval and missed cancers.center dot AI-assisted triaging is effective in differentiating low and high-risk cases, reduces radiologist workload, and potentially enables broader screening coverage.center dot AI has the potential to facilitate early diagnosis compared to human reading.Key Points center dot Incorporating AI as a triage tool in screening workflow improves sensitivity (72.38%) and specificity (92.86%), enhancing detection rates for interval and missed cancers.center dot AI-assisted triaging is effective in differentiating low and high-risk cases, reduces radiologist workload, and potentially enables broader screening coverage.center dot AI has the potential to facilitate early diagnosis compared to human reading.
dc.description.sponsorshipAcibadem Mehmet Ali Aydinlar University
dc.description.sponsorshipNo Statement Available
dc.identifier.doi10.1007/s00330-024-10661-3
dc.identifier.endpage6157
dc.identifier.issn0938-7994
dc.identifier.issn1432-1084
dc.identifier.issue9en_US
dc.identifier.pmid38388718
dc.identifier.scopus2-s2.0-85185941541
dc.identifier.scopusqualityQ1
dc.identifier.startpage6145
dc.identifier.urihttps://doi.org/10.1007/s00330-024-10661-3
dc.identifier.urihttps://hdl.handle.net/20.500.11776/14200
dc.identifier.volume34
dc.identifier.wosWOS:001169722300004
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofEuropean Radiology
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectMammography
dc.subjectScreening
dc.subjectBreast cancer
dc.subjectArtificial intelligence
dc.titleDiagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu