Yazar "Emre, Elif" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Can the Posterior Segment Findings of the Eye and Serum Microbiota Metabolites Be a Biomarker in Schizophrenia?
    (Mdpi, 2026) Keser, Sinem; Yildiz, Sevler; Aydin, Suleyman; Keles, Julide; Aksoy, Aziz; Emre, Elif
    Background and Objectives: In many neurodegenerative diseases, the pathological changes occurring in the central nervous system may be reflected in the periphery. The aim of this study was to examine the possible relationship between the retina, choroid, and nerve fibre layer thicknesses measured on optic coherence tomography (OCT) and the serum microbiota metabolite levels of trimethyl amine-N-oxide (TMAO), S-equol, Indoxyl sulphate (IS), and Maresin 1 (MaR1). Materials and Methods: This study included a total of 60 subjects, comprising 30 patients diagnosed with schizophrenia and a control group of 30 healthy individuals. A sociodemographic form was given to all the subjects and the Positive and Negative Syndrome Scale (PANSS) to the schizophrenia patients. The eye fundus was evaluated with OCT. A 5 mL blood sample was taken from the arm of each subject, and the microbiota metabolite levels of TMAO, S-equol, IS, and MaR1 were examined. Results: The retina nerve fibre layer (RNFL) analysis results showed that the RNFL superior (p = 0.016), inferior (p = 0.002), central choroid (p = 0.033), nasal choroid (p = 0.004), temporal choroid (p = 0.038), and TMAO (p = 0.001) values were significantly lower in the schizophrenia patients than in the control group. In the patient group, a significant negative correlation was determined between the RNFL temporal measurements and IS, as well as a significant positive correlation between the central choroid measurement and the nasal choroid and temporal choroid measurements and between the nasal choroid and temporal choroid measurements. A statistically significant positive correlation was seen between S-equol and TMAO. A significant negative correlation was seen between the MaR1 level and age and disease duration. Conclusions: The study results showed that fundus changes are associated with serum microbiota metabolite levels in schizophrenia patients. Therefore, these parameters may be considered potential exploratory biomarkers; however, their clinical applicability requires validation in larger longitudinal studies.
  • Küçük Resim Yok
    Öğe
    Vocal Fold Disorders Classification and Optimization of a Custom Video Laryngoscopy Dataset Through Structural Similarity Index and a Deep Learning-Based Approach
    (Mdpi, 2025) Emre, Elif; Cetintas, Dilber; Yildirim, Muhammed; Emre, Sadettin
    Background/Objectives: Video laryngoscopy is one of the primary methods used by otolaryngologists for detecting and classifying laryngeal lesions. However, the diagnostic process of these images largely relies on clinicians' visual inspection, which can lead to overlooked small structural changes, delayed diagnosis, and interpretation errors. Methods: AI-based approaches are becoming increasingly critical for accelerating early-stage diagnosis and improving reliability. This study proposes a hybrid Convolutional Neural Network (CNN) architecture that eliminates repetitive and clinically insignificant frames from videos, utilizing only meaningful key frames. Video data from healthy individuals, patients with vocal fold nodules, and those with vocal fold polyps were summarized using three different threshold values with the Structural Similarity Index Measure (SSIM). Results: The resulting key frames were then classified using a hybrid CNN. Experimental findings demonstrate that selecting an appropriate threshold can significantly reduce the model's memory usage and processing load while maintaining accuracy. In particular, a threshold value of 0.90 provided richer information content thanks to the selection of a wider variety of frames, resulting in the highest success rate. Fine-tuning the last 20 layers of the MobileNetV2 and Xception backbones, combined with the fusion of extracted features, yielded an overall classification accuracy of 98%. Conclusions: The proposed approach provides a mechanism that eliminates unnecessary data and prioritizes only critical information in video-based diagnostic processes, thus helping physicians accelerate diagnostic decisions and reduce memory requirements.