Mühendislik-Mimarlık Fakültesi

Permanent URI for this communityhttps://hdl.handle.net/20.500.12514/16

Browse

Browsing Mühendislik-Mimarlık Fakültesi by WoS Q "Q1"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Article
    Citation - WoS: 6
    Citation - Scopus: 6
    Can deep learning replace histopathological examinations in the differential diagnosis of cervical lymphadenopathy?
    (Springer, 2024) Can, Sermin; Türk, Ömer; Ayral, Muhammed; Kozan, Günay; Arı, Hamza; Akdağ, Mehmet; Yıldırım Baylan, Müzeyyen
    Introduction: We aimed to develop a diagnostic deep learning model using contrast-enhanced CT images and to investigate whether cervical lymphadenopathies can be diagnosed with these deep learning methods without radiologist interpretations and histopathological examinations. Material method: A total of 400 patients who underwent surgery for lymphadenopathy in the neck between 2010 and 2022 were retrospectively analyzed. They were examined in four groups of 100 patients: the granulomatous diseases group, the lymphoma group, the squamous cell tumor group, and the reactive hyperplasia group. The diagnoses of the patients were confirmed histopathologically. Two CT images from all the patients in each group were used in the study. The CT images were classified using ResNet50, NASNetMobile, and DenseNet121 architecture input. Results: The classification accuracies obtained with ResNet50, DenseNet121, and NASNetMobile were 92.5%, 90.62, and 87.5, respectively. Conclusion: Deep learning is a useful diagnostic tool in diagnosing cervical lymphadenopathy. In the near future, many diseases could be diagnosed with deep learning models without radiologist interpretations and invasive examinations such as histopathological examinations. However, further studies with much larger case series are needed to develop accurate deep-learning models.
  • Thumbnail Image
    Article
    A comparative approach to using photogrammetry in the structural analysis of historical buildings
    (2024) Kutlu, İzzettin; Soyluk, Asena
    Finite element method (FEM) provides the numerically solving differential equations arising in engineering and mathematical modeling of physical systems. This process begins by determining the assignment of a theoretical node. A node is a single point on a frame, shell, or solid element and each element can be programmed with its location's material and structural data. Programming with the FEM is quite time-consuming for complex geometry such as historical buildings. This study aims to examine a low-cost and time-saving technology to build a FEM model using photogrammetry. In accordance with this aim, classical modeling techniques and photogrammetric modeling techniques were discussed. The results demonstrated that similar values were revealed in stress and deformation values. Consequently, the study emphasizes the potential of photogrammetry technology as an integrated approach for bringing together the disciplines of architecture and engineering that usually require two distinct expertise in analysing the structural behavior of historical buildings.