Yazar "Köremezli Keskin, Nevin" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Detection of the differences in the apparent diffusion coefficient values in different histopathological types of malignant breast lesions and comparison of cellular region/ stroma ratio and histopathological results
    (2018) Köremezli Keskin, Nevin; Balcı, Pınar; Basara Akın, Işıl; Yavuz Gürkan, Esra; Sevınç, Ali İbrahim; Durak, Merih Güray; Ersen Danyeli, Ayça
    Background/aim: This study aimed to compare the apparent diffusion coefficient (ADC) values of malignant breast lesions with differenthistopathological types on diffusion-weighted imaging (DWI) and the cellular region/stroma (CR/S) ratio and histopathological results.Materials and methods: Breast diffusion-weighted magnetic resonance findings of 59 patients were retrospectively analyzed formalignant breast lesions. The CR/S ratio was calculated using breast wide-excisional biopsy or mastectomy specimens.Results: Receiver operating characteristic analysis was performed for malignant lesions and subtypes. An ADC threshold of 1.260 ×10–3 mm2/s was set to detect invasive ductal carcinoma with 80.8% sensitivity and 81.4% specificity. An ADC threshold of 1.391 × 10–3mm2/s was set to detect invasive lobular carcinoma lesions with 88.2% sensitivity and 79.5% specificity. The ADC value for lesions withlow CR/S ratio (n = 21) was 1.135 ± 0.429 × 10–3 mm2/s and it was 1.155 ± 0.429 × 10–3 mm2/s in the high CR/S ratio group (n = 18).Conclusion: ADC value calculation does not seem to be used as an alternative for histopathological detection, which is the gold standardfor the differentiation of subtypes of malignant breast cancer. In addition, since there is a positive correlation between CR/S ratio andADC values, it may be a strong marker to evaluate the stromal component of lesions.
  • Küçük Resim
    Öğe
    Gender estimation using machine learning algorithms from computed tomography images of clivus
    (2024) Yılmaz, Nesibe; Seçgin, Yusuf; Atay, İlayda; Köremezli Keskin, Nevin
    The clivus, which is involved in the formation of the skull base, is an important material in gender prediction with its fusion structure. The aim of this study is to predict the gender of adult individuals using Machine Learning (ML) algorithms and Artificial Neural Networks (ANN) with parameters obtained from Computed Tomography (CT) images. The study was performed on CT images of 349 individuals aged 18-65 years. Clivus length, 1/3 upper, middle, and lower 1/3 width were measured on CT images and used in ML entry. As a result of the study, it was found that the clivus length, 1/3 upper, middle, and lower width had a significant difference in terms of gender, and ML algorithms showed accuracy up to 0.74. An accuracy of 0.67 was obtained with the ANN model. The study shows that clivus is a bone material that is open to research in terms of gender estimation and can be obtained with high accuracy. In this respect, we believe that it will guide the studies in forensic sciences.