Caglar Uyulan

Dr. Caglar Uyulan

İzmir Katip Çelebi University, Department of Mechanical Engineering
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 June 2020 in Clinical Eeg and Neuroscience
Verified
Journal Article
Closed access
PDF file
CUCaglar Uyulan
Caglar Uyulan
TETürker Tekin Ergüzel
Türker Tekin Ergüzel
HUHuseyin Unubol
Huseyin Unubol
MCMerve Cebi
Merve Cebi
GSGokben Hizli Sayar
Gokben Hizli Sayar
NTNevzat Tarhan
Nevzat Tarhan
The human brain is characterized by complex structural, functional connections that integrate unique cognitive characteristics. There is a fundamental hurdle for the evaluation of both structural and functional connections of the brain and the effects in the diagnosis and treatment of neurodegenerative diseases. Currently, there is no clinically specific diagnostic biomarker capable of confirming the diagnosis of major depressive disorder (MDD). Therefore, exploring translational biomarkers of mood disorders based on deep learning (DL) has valuable potential with its recently underlined promising outcomes. In this article, an electroencephalography (EEG)-based diagnosis model for MDD is built through advanced computational neuroscience methodology coupled with a deep convolutional neural network (CNN) approach. EEG recordings are analyzed by modeling 3 different deep CNN structure, namely, ResNet-50, MobileNet, Inception-v3, in order to dichotomize MDD patients and healthy controls. EEG data are collected for 4 main frequency bands (Δ, θ, α, and β, accompanying spatial resolution with location information by collecting data from 19 electrodes. Following the pre-processing step, different DL architectures were employed to underline discrimination performance by comparing classification accuracies. The classification performance of models based on location data, MobileNet architecture generated 89.33% and 92.66% classification accuracy. As to the frequency bands, delta frequency band outperformed compared to other bands with 90.22% predictive accuracy and area under curve (AUC) value of 0.9 for ResNet-50 architecture. The main contribution of the study is the delineation of distinctive spatial and temporal features using various DL architectures to dichotomize 46 MDD subjects from 46 healthy subjects. Exploring translational biomarkers of mood disorders based on DL perspective is the main focus of this study and, though it is challenging, with its promising potential to improve our understanding of the psychiatric disorders, computational methods are highly worthy for the diagnosis process and valuable in terms of both speed and accuracy compared with classical approaches.

1 July 2020 in Energy
Verified
Journal Article
Closed access
SASercan Acarer
Sercan Acarer
CUCaglar Uyulan
Caglar Uyulan
ZKZiya Haktan Karadeniz
Ziya Haktan Karadeniz


3 June 2021 in Clinical Eeg and Neuroscience
Verified
Journal Article
Closed access
PDF file
CUCaglar Uyulan
Caglar Uyulan
SSSara de la Salle
Sara de la Salle
TETurker T. Erguzel
Turker T. Erguzel
ELEmma Lynn
Emma Lynn
PBPierre Blier
Pierre Blier
NTNevzat Tarhan
Nevzat Tarhan
Electroencephalogram (EEG)-based automated depression diagnosis systems have been suggested for early and accurate detection of mood disorders. EEG signals are highly irregular, nonlinear, and nonstationary in nature and are traditionally studied from a linear viewpoint by means of statistical and frequency features. Since, linear metrics present certain limitations and nonlinear methods have proven to be an efficient tool in understanding the complexities of the brain in the identification of underlying behavior of biological signals, such as electrocardiogram, EEG and magnetoencephalogram and thus, can be applied to all nonstationary signals. Various nonlinear algorithms can be used in the analysis of EEG signals. In this research paper, we aim to develop a novel methodology for EEG-based depression diagnosis utilizing 2 advanced computational techniques: frequency-domain extended multivariate autoregressive (eMVAR) and deep learning (DL). We proposed a hybrid method comprising a pretrained ResNet-50 and long-short term memory (LSTM) to capture depression-specific information and compared with a strong conventional machine learning (ML) framework having eMVAR connectivity features. The following 8 causality measures, which interpret the interaction mechanisms among spectrally decomposed oscillations, were used to extract features from multivariate EEG time series: directed coherence (DC), directed transfer function (DTF), partial DC (PDC), generalized PDC (gPDC), extended DC (eDC), delayed DC (dDC), extended PDC (ePDC), and delayed PDC (dPDC). The classification accuracies were 84% with DC, 85% with DTF, 95.3% with PDC, 95.1% with gPDC, 84.8% with eDC, 84.6% with dDC, 84.2% with ePDC, and 95.9% with dPDC for the eMVAR framework. Through a DL framework (ResNet-50 + LSTM), the classification accuracy was achieved as 90.22%. The results demonstrate that our DL methodology is a competitive alternative to the strong feature extraction-based ML methods in depression classification.

1 January 2017 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
CUCaglar Uyulan
Caglar Uyulan
TETurker Tekin Erguzel
Turker Tekin Erguzel
Many endogenous and external components may affect the physiological, mental and behavioral states in humans. Monitoring tools are required to evaluate biomarkers, identify biological events, and predict their outcomes. Being one of the valuable indicators, brain biomarkers derived from temporal or spectral electroencephalography (EEG) signals processing, allow for the classification of mental disorders and mental tasks. An EEG signal has a nonstationary nature and individual frequency feature, hence it can be concluded that each subject has peculiar timing and data to extract unique features. In order to classify data, which are collected by performing four mental task (reciting the alphabet backwards, imagination of rotation of a cube, imagination of right hand movements (open/close) and performing mathematical operations), discriminative features were extracted using four competitive time-frequency techniques; Wavelet Packet Decomposition (WPD), Morlet Wavelet Transform (MWT), Short Time Fourier Transform (STFT) and Wavelet Filter Bank (WFB), respectively. The extracted features using both time and frequency domain information were then reduced using a principal component analysis for subset reduction. Finally, the reduced subsets were fed into a multi-layer perceptron neural network (MP-NN) trained with back propagation (BP) algorithm to generate a predictive model. This study mainly focuses on comparing the relative performance of time-frequency feature extraction methods that are used to classify mental tasks. The real-time (RT) conducted experimental results underlined that the WPD feature extraction method outperforms with 92% classification accuracy compared to three other aforementioned methods for four different mental tasks.

1 June 2022 in Molecular Imaging and Radionuclide Therapy
Verified
Journal Article
Open access
YSYavuz Sami Salihoğlu
Yavuz Sami Salihoğlu
RERabiye Uslu Erdemir
Rabiye Uslu Erdemir
BPBüşra Aydur Püren
Büşra Aydur Püren
SOSemra OZDEMIR
Semra OZDEMIR
CUCaglar Uyulan
Caglar Uyulan
Huseyin Ozan TekinHuseyin Ozan Tekin
Huseyin Ozan Tekin
This study aimed to evaluate the ability of 18fluorine-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic features combined with machine learning methods to distinguish between benign and malignant solitary pulmonary nodules (SPN). Data of 48 patients with SPN detected on 18F-FDG PET/CT scan were evaluated retrospectively. The texture feature extraction from PET/CT images was performed using an open-source application (LIFEx). Deep learning and classical machine learning algorithms were used to build the models. Final diagnosis was confirmed by pathology and follow-up was accepted as the reference. The performances of the models were assessed by the following metrics: Sensitivity, specificity, accuracy, and area under the receiver operator characteristic curve (AUC). The predictive models provided reasonable performance for the differential diagnosis of SPNs (AUCs ~0.81). The accuracy and AUC of the radiomic models were similar to the visual interpretation. However, when compared to the conventional evaluation, the sensitivity of the deep learning model (88% vs. 83%) and specificity of the classic learning model were higher (86% vs. 79%). Machine learning based on 18F-FDG PET/CT texture features can contribute to the conventional evaluation to distinguish between benign and malignant lung nodules.