Yazar "Deniz, Birgul" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    An Explainable Approach to Parkinson's Diagnosis Using the Contrastive Explanation Method-CEM
    (Mdpi, 2025) Cicek, Ipek Balikci; Kucukakcali, Zeynep; Deniz, Birgul; Algul, Fatma Ebru
    Background/Objectives: Parkinson's disease (PD) is a progressive neurodegenerative disorder that requires early and accurate diagnosis. This study aimed to classify individuals with and without PD using volumetric brain MRI data and to improve model interpretability using explainable artificial intelligence (XAI) techniques. Methods: This retrospective study included 79 participants (39 PD patients, 40 controls) recruited at Inonu University Turgut Ozal Medical Center between 2013 and 2025. A deep neural network (DNN) was developed using a multilayer perceptron architecture with six hidden layers and ReLU activation functions. Seventeen volumetric brain features were used as the input. To ensure robust evaluation and prevent overfitting, a stratified five-fold cross-validation was applied, maintaining class balance in each fold. Model transparency was explored using two complementary XAI techniques: the Contrastive Explanation Method (CEM) and Local Interpretable Model-Agnostic Explanations (LIME). CEM highlights features that support or could alter the current classification, while LIME provides instance-based feature attributions. Results: The DNN model achieved high diagnostic performance with 94.1% accuracy, 98.3% specificity, 90.2% sensitivity, and an AUC of 0.97. The CEM analysis suggested that reduced hippocampal volume was a key contributor to PD classification (-0.156 PP), whereas higher volumes in the brainstem and hippocampus were associated with the control class (+0.035 and +0.150 PP, respectively). The LIME results aligned with these findings, revealing consistent feature importance (mean = 0.1945) and faithfulness (0.0269). Comparative analyses showed different volumetric patterns between groups and confirmed the DNN's superiority over conventional machine learning models such as SVM, logistic regression, KNN, and AdaBoost. Conclusions: This study demonstrates that a deep learning model, enhanced with CEM and LIME, can provide both high diagnostic accuracy and interpretable insights for PD classification, supporting the integration of explainable AI in clinical neuroimaging.
  • Küçük Resim Yok
    Öğe
    Investigation of the effects of radiotherapy and chemotherapy on brain volume in cancer patients: brain tumor study
    (Springer, 2026) Deniz, Birgul; Arpaci, Muhammed Furkan; Pekmez, Hidir; Uzun, Gokce Bagci; Inceoglu, Feyza; Harputluoglu, Hakan
    Purpose Brain tumors, characterized by the uncontrolled proliferation of abnormal cells within cerebral tissue, remain clinically challenging entities. Radiotherapy and chemotherapy constitute fundamental therapeutic modalities; however, their effects on healthy brain structures are not fully understood. This study aimed to evaluate the impact of these treatments on volumetric changes in brain structures and tumor size in patients with primary or metastatic brain tumors. Methods A retrospective cohort of 47 patients aged 18-90 years treated at Inonu University Turgut & Ouml;zal Medical Center between 2012 and 2023 was analyzed. Brain MRI scans were evaluated at three time points: pre-treatment, post-radiotherapy, and post-chemotherapy. Radiotherapy was delivered at a median dose of 60 Gy in 30-33 fractions, and temozolomide was used as the chemotherapy agent. Volumetric measurements of the telencephalon, diencephalon, ventricles, white matter, brainstem, cerebellum, and cerebral cortex were performed using MRICloud, while tumor volumes were quantified using the VolBrain platform. All volumetric differences were statistically tested using repeated-measures ANOVA with corresponding p-values reported. Results A statistically significant increase in telencephalon volume was observed after radiotherapy, followed by a return toward baseline measurements after chemotherapy. The diencephalon demonstrated a significant and persistent volume reduction following radiotherapy (p < 0.05). No statistically significant volumetric changes were identified in the ventricles, white matter, brainstem, cerebellum, or cerebral cortex (p > 0.05). Tumor volume changes were also statistically evaluated and showed no significant differences across the three time points (p = 0.456), indicating stable disease during the treatment course. Conclusion Radiotherapy and chemotherapy lead to region-specific volumetric alterations in the brain. The transient telencephalon enlargement is more likely attributable to treatment-related edema or inflammatory processes rather than functional improvement. The persistent diencephalon volume decline may reflect early treatment-related tissue vulnerability. Incorporating automated volumetric assessment into routine follow-up may support early detection of therapy-related structural changes and facilitate more personalized treatment planning.