Yazar "Ozcinar, Beyza" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Diagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program
    (Springer, 2024) Seker, Mustafa Ege; Koyluoglu, Yilmaz Onat; Ozaydin, Ayse Nilufer; Gurdal, Sibel Ozkan; Ozcinar, Beyza; Cabioglu, Neslihan; Ozmen, Vahit
    ObjectivesWe 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.
  • Küçük Resim Yok
    Öğe
    Long-term outcomes of Türkiye's first population-based mammography screening program: a decade of breast cancer detection and survival analysis in Bahçeşehir
    (Bmc, 2025) Ozcinar, Beyza; Aribal, Erkin; Cabioglu, Neslihan; Gurdal, Sibel Ozkan; Varol, Gamze; Akyurt, Nuran; Sezgin, Efe
    BackgroundThe Bah & ccedil;e & scedil;ehir population-based mammography screening program (BMSP) is an example of T & uuml;rkiye's first population-based screening program. This study aims to reveal the successful implementation of population-based secreening program in one of the low- and middle-income countries, T & uuml;rkiye and long-term results of patients diagnosed with breast cancer during BMSP. MethodsThis study was conducted between 2009 and 2019, in the Bah & ccedil;e & scedil;ehir county of Istanbul. Women between the ages of 40 and 69 living in this region were invited every two years to undergo clinical breast examination (CBE) and mammography screening. All data was recorded in a dedicated software program. Women diagnosed with breast cancer were followed as a separate cohort. ResultsDuring the 10-year screening period, 8,825 women were screened and 146 (1.7%) breast cancers were detected. The median age at diagnosis for these patients was 52.9 years (40-69). The risk of breast cancer was 1.39 times higher (95% CI: 1.01-1.93) in women aged >= 50 compared to those less than 50 years (p = 0.045). The Cox regression analysis revealed that age at first birth, and number of births were significant predictors of breast cancer risk (p < 0.001, and p = 0.011). The breast cancer rate tends to increase as the breast density category progresses from A to D (p < 0.001). The median follow-up time for 146 breast cancer patients was 95.3 months. The 10-year breast cancer specific survival rate was 85%. ConclusionsThis study demonstrates that with a committed team and sufficient infrastructure, screening mammography can be effectively carried out in T & uuml;rkiye, leading to early detection and lower mortality rates. The recommended age to commence screening is 40 years old.