Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
2 results
Search Results
Article A Comparative Study of Unet Variants for Low-Grade Glioma Segmentation in Magnetic Resonance Imaging(Inonu University, 2025-06-25) Guzel, Yasin; Aydin, ZaferBrain tumors originating from glial cells are pathological entities that significantly impact quality of life and are classified based on their malignancy into low-grade gliomas (LGGs) and high-grade gliomas (HGGs). While the more aggressive HGGs have been extensively studied, LGGs are of critical importance for early diagnosis due to their potential progression to HGGs if left untreated. This has driven researchers to develop methods for the rapid and consistent diagnosis of LGGs. In this study, three models—UNet, Transformer UNet, and Super Vision UNet—were comparatively evaluated for the automatic segmentation of LGGs using magnetic resonance imaging (MRI) data. Multimodal MRI scans from 110 patients, retrieved from The Cancer Imaging Archive (TCIA), were used to train the models. Performance was evaluated using Dice Coefficient, Tversky Index, and Intersection over Union (IoU) metrics. The Super Vision UNet achieves the highest Dice (0.9115) and Tversky (0.9154) scores, while the Transformer UNet attains the highest IoU (0.8789). Both advanced models demonstrate superior segmentation performance with lower loss values compared to the conventional UNet. Visual outputs indicate that the modern architectures delineate tumor contours with greater precision. These results highlight the effectiveness and reliability of contemporary UNet-based and Transformer-based architectures in segmenting complex tumor structures such as LGGs. Integrating these models into clinical decision support systems holds promise for enhancing the speed and accuracy of the diagnostic process. © 2025 Elsevier B.V., All rights reserved.Article Citation - Scopus: 13Paclitaxel-Loaded Polycaprolactone Nanoparticles for Lung Tumors: Formulation, Comprehensive In Vitro Characterization, and Release Kinetic Studies(University of Ankara, 2022-09-29) Ünal, Sedat; Dogan, Osman Talha; Aktaş, YeşimObjective: Today, cancer is still among the most common chronic diseases. Nanoparticular drug delivery systems prepared with biocompatible and biodegradable polymers such as polycaprolactone are rational solution for anticancer agents with poor solubility and low bioavailability. The aim of this study is to prepare paclitaxel-loaded polycaprolactone nanoparticles, which is known to be a potent anticancer, and to elucidate in vitro characteristics and release kinetic mechanisms. Material and Method: It was aimed to prepare paclitaxel-loaded polycaprolactone nanoparticles by nanoprecipitation. Preformulation studies were carried out with different molecular weights of polycaprolactone (Mw: 14.000, Mw: 80.000). Nanoparticles were coated with Chitosan or Poly-l-lysine to obtain cationic surface charge and to increase cellular interaction. Comprehensive characterization of formulations and release kinetic studies were performed. Result and Discussion: The particle size of the formulations ranged from 188 nm to 383 nm. Encapsulation efficiency increased to 77% in different formulations. SEM analysis confirmed the nanoparticles were spherical. Within the scope of in vitro release studies, the release continued for up to 96 hours and less than 50% of the therapeutic load was released in the first 24 hours. Mathematical modeling indicated that the release kinetics fit more than one model with the Korsmeyer-Peppas, Peppas-Sahlin and Weibull models, which show high correlation. © 2023 Elsevier B.V., All rights reserved.