Browsing by Author "Dedeoglu, Serkan"

Now showing 1 - 3 of 3

Automated Mucormycosis Diagnosis from Paranasal CT Using ResNet50 and ConvNeXt Small
(MDPI, 2025) Toprak, Serdar Ferit; Dedeoglu, Serkan; Kozan, Gunay; Ayral, Muhammed; Can, Sermin; Turk, Omer; Akdag, Mehmet
Purpose: Mucormycosis is a life-threatening fungal infection, where rapid diagnosis is critical. We developed a deep learning approach using paranasal computed tomography (CT) images to test whether mucormycosis can be detected automatically, potentially aiding or expediting the diagnostic process that traditionally relies on biopsy. Methods: In this retrospective study, 794 CT images (from patients with mucormycosis, nasal polyps, or normal findings) were analyzed. Images were resized and augmented for training. Two transfer learning models (ResNet50 and ConvNeXt Small) were fine-tuned to classify images into the three categories. We employed a 70/30 train-test split (with five-fold cross-validation) and evaluated performance using accuracy, precision, recall, F1-score, and confusion matrices. Results: The ConvNeXt Small model achieved 100% accuracy on the test set (precision/recall/F1-score = 1.00 for all classes), while ResNet50 achieved 99.16% accuracy (precision approximate to 0.99, recall approximate to 0.99). Cross-validation yielded consistent results (ConvNeXt accuracy similar to 99% across folds), indicating no overfitting. An ablation study confirmed the benefit of transfer learning, as training ConvNeXt from scratch led to lower accuracy (similar to 85%) Conclusions: Our findings demonstrate that deep learning models can accurately and non-invasively detect mucormycosis from CT scans, potentially flagging suspected cases for prompt treatment. These models could serve as rapid screening tools to complement standard diagnostic methods (histopathology), although we emphasize that they are adjuncts and not replacements for biopsy. Future work should validate these models on external datasets and investigate their integration into clinical workflows for earlier intervention in mucormycosis.
Psychiatric Comorbidity in Chronic Tinnitus: Depression and Anxiety in an Otolaryngology Outpatient Cohort
(Dove Medical Press Ltd, 2026) Sirma, Enes; Toprak, Serdar Ferit; Dedeoglu, Serkan; Donmezdil, Suleyman
Purpose: Chronic subjective tinnitus is commonly accompanied by psychological distress; however, its independent relationship with depressive and anxiety symptoms in otolaryngology outpatients has not been fully delineated. This study sought to estimate the prevalence of mood symptoms among adults with chronic tinnitus and to determine whether tinnitus severity contributes independently to psychological burden. Patients and Methods: In this cross-sectional study, 100 adults with subjective tinnitus of at least six months' duration were evaluated at a tertiary otolaryngology clinic. Participants completed the Tinnitus Handicap Inventory (THI), Beck Depression Inventory-II (BDI-II), and Beck Anxiety Inventory (BAI). Prevalence estimates were compared with population-level data. Associations between tinnitus severity and mood symptoms were examined using correlation analyses and multivariable linear regression adjusted for age, sex, and hearing status. Results: Mean scores were 47.2 +/- 18.3 for THI, 16.1 +/- 10.4 for BDI-II, and 19.5 +/- 11.2 for BAI. Tinnitus severity showed moderate positive associations with depressive (r = 0.50) and anxiety symptoms (r = 0.48), both p < 0.001. After adjustment, THI scores remained independently associated with higher BDI-II ((3 = 0.42, p < 0.001) and BAI scores ((3 = 0.39, p < 0.001). Severe tinnitus (THI >= 58) was linked to increased odds of moderate-to-severe depression (OR 3.10, 95% CI 1.52-6.30) and anxiety (OR 2.84, 95% CI 1.40-5.72). Clinically relevant depressive and anxiety symptoms were identified in 28% and 31% of participants, respectively. Conclusion: Greater tinnitus severity is independently associated with elevated symptom severity of depression and anxiety. These findings underscore the importance of routine mental health screening and multidisciplinary management in ENT practice.
Retrospective Observational Study of Computed Tomography-Based Vascular Risk Assessment During Needle Drainage of Peritonsillar Abscess
(Journal of Visualized Experiments, 2026) Samanci, Serhat; Toprak, Serdar Ferit; Ayral, Muhammed; Dedeoglu, Serkan; Temiz, Hakan
Peritonsillar abscess (PTA) is a common deep neck infection in which bedside drainage is performed close to major cervical vessels. Although catastrophic vascular complications are rare, clinicians have limited quantitative information on how far the internal carotid artery (ICA), external carotid artery (ECA), and internal jugular vein (IJV) lie from the abscess in individual patients. This protocol describes a contrast-enhanced computed tomography (CT)-based workflow to confirm unilateral PTA, acquire neck CT images under standard clinical settings, measure linear distances from the anterior and posterior abscess capsule to the ipsilateral ICA, ECA, and IJV, compare these distances with the contralateral healthy side as an internal control, and classify the theoretical risk of ICA injury during needle drainage using a modified Pfeiffer system. The procedure includes patient selection, safety screening for iodinated contrast, contrast-enhanced CT acquisition, standardized axial image review by a head and neck radiologist, and structured data recording and analysis. In a retrospective cohort of 94 adult patients, PTA consistently displaced the ICA, ECA, and IJV away from the tonsillar space, increasing both anterior and posterior distances compared with the healthy side. The mean posterior PTA-ICA distance was approximately 14 mm, whereas the contralateral tonsil-ICA distance was about 9 mm. ICA course anomalies (tortuosity or coiling) were detected in a minority of patients, and roughly one in seven cases met moderate-risk criteria because of shorter distances and/or aberrant ICA anatomy. Age, sex, and abscess volume did not significantly alter these relationships. This CT-based protocol provides a reproducible method to quantify PTA-vessel distances and identify patients with potentially higher vascular risk anatomy prior to drainage. It supports cautious, controlled-depth needle aspiration in most cases and highlights scenarios in which image-guided or operating-room drainage may be preferable.