Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
20 results
Search Results
Article Vim-Polyp: Multimodal Colon Polyp Dataset with Video, Histopathology, and Protein Expression(Nature Portfolio, 2025-12-03) Dogan, Refika Sultan; Akay, Ebru; Dogan, Serkan; Yilmaz, BulentThe dataset in this study includes 202 videos with a total of 422 minutes, reaching Kayseri City Hospital's gastroenterology department as colonoscopy videos and 1903 microscopy images between 2019 and 2021. It includes 399 colonoscopy, microscopy images, and pathological diagnoses of polyps, as well as immunohistochemical staining results for proteins that play an important role in the assessment of cancerous cells, such as staining results for p53 (clone: bp53-11), Ki-67 (clone: 30-9), CD34 (clone: QBend/10), PD-L1 (clone: SP142), BRAF (clone: V600E) and VEGF (clone: SP125). By sharing the data openly, we aim to facilitate benchmarking, exploratory analysis and transfer-learning studies on colorectal polyps and cancer. In combination with external datasets or pretrained models, the resource can help advance data-driven detection and characterisation work. The diverse range of polyps assigned to cancer stages from 201 patients makes this tool valuable for researchers and clinicians in furthering diagnosis and treatment.Article Citation - WoS: 5Citation - Scopus: 6Transfer Learning for P300 Brain-Computer Interfaces by Joint Alignment of Feature Vectors(IEEE-Inst Electrical Electronics Engineers Inc, 2023-10) Altindis, Fatih; Banerjee, Antara; Phlypo, Ronald; Yilmaz, Bulent; Congedo, MarcoThis article presents a new transfer learning method named group learning, that jointly aligns multiple domains (many-to-many) and an extension named fast alignment that aligns any further domain to previously aligned group of domains (many-to-one). The proposed group alignment algorithm (GALIA) is evaluated on brain-computer interface (BCI) data and optimal hyper-parameter values of the algorithm are studied for classification performance and computational cost. Six publicly available P300 databases comprising 333 sessions from 177 subjects are used. As compared to the conventional subject-specific train/test pipeline, both group learning and fast alignment significantly improve the classification accuracy except for the database with clinical subjects (average improvement: 2.12 +/- 1.88%). GALIA utilizes cyclic approximate joint diagonalization (AJD) to find a set of linear transformations, one for each domain, jointly aligning the feature vectors of all domains. Group learning achieves a many-to-many transfer learning without compromising the classification performance on non-clinical BCI data. Fast alignment further extends the group learning for any unseen domains, allowing a many-to-one transfer learning with the same properties. The former method creates a single machine learning model using data from previous subjects and/or sessions, whereas the latter exploits the trained model for an unseen domain requiring no further training of the classifier.Article Citation - WoS: 56Citation - Scopus: 69Synchrosqueezing Transform Based Feature Extraction From EEG Signals for Emotional State Prediction(Elsevier Sci Ltd, 2019-07) Ozel, Pinar; Akan, Aydin; Yilmaz, BulentThis paper presents a novel method for emotion recognition based on time-frequency analysis using multivariate synchrosqueezing transform (MSST) of multichannel electroencephalography (EEG) signals. With the advancements of the multichannel sensor applications, the need for multivariate algorithms has become obvious for extracting features that stem from multichannel dependency in addition to mono-channel features. In order to model the joint oscillatory structure of these multichannel signals, MSST has recently been proposed. It uses the concepts of joint instantaneous frequency and bandwidth. Electrophysiological data processing mostly requires joint time-frequency analysis in addition to both time and frequency analysis separately. The short-time Fourier transform (STFT) and wavelet transform (WT) are the main approaches utilized in time-frequency analysis. In this paper, the feasibility and performance of multivariate wavelet-based synchrosqueezing algorithm was demonstrated on EEG signals obtained from publically available DEAP database by comparing with its univariate version. Eight emotional states were considered by combining arousal-valence and dominance dimensions. Using linear support vector machines (SVM) as a classifier, MSST and its univariate version resulted in the highest prediction accuracy rates of (9) over tilde3% among all emotional states. (C) 2019 Elsevier Ltd. All rights reserved.Article Citation - WoS: 27Citation - Scopus: 30Super Resolution Convolutional Neural Network Based Pre-Processing for Automatic Polyp Detection in Colonoscopy Images(Pergamon-Elsevier Science Ltd, 2021-03) Tas, Merve; Yilmaz, BulentColonoscopy is the most common methodology used to detect polyps on the colon surface. Increasing the image resolution has the potential to improve the automatic colonoscopy based diagnosis and polyp detection and localization. In this study, we proposed a pre-processing approach that uses convolutional neural network based super resolution method (SRCNN) to increase the resolution of the training colonoscopy images before the localization of polyps. We also investigated the use of CNN based models such as the Single Shot MultiBox Detector (SSD) and Faster Regional CNN (RCNN) for real-time polyp detection and localization. Our results showed that using SRCNN method before the training process provides better results in terms of accuracy in both models compared to the low-resolution cases. Furthermore, we reached an F2 score of 0.945 for the correct localization of colon polyps using Faster RCNN with ResNet-101 feature extractor.Article Citation - WoS: 7Citation - Scopus: 9Split-Attention Effects in Multimedia Learning Environments: Eye-Tracking and EEG Analysis(Springer, 2022-02-02) Mutlu-Bayraktar, Duygu; Ozel, Pinar; Altindis, Fatih; Yilmaz, BulentThis study aimed to evaluate the split-attention effect in multimedia learning environments via objective measurements as EEG and eye-tracking. Two different multimedia learning environments in a focused (integrated) and split-attention (separated) format were designed. The experimental design method was used. The participants consisted of 44 students divided into two groups for focused attention and split-attention. There were significant differences between the fixation, brain wave, and retention performance of the two groups. Fixations of the split-attention group were higher than the focused attention group. A significant difference was found in the focused attention group in the alpha brain wave in the frontal region for intra-group comparisons and in the split-attention group in the beta brain wave in the frontal area for the inter-group comparison. The retention performance of the focused attention group was higher than the split-attention group. Accordingly, more cognitive activity emerged in environments where the text was not integrated into the picture. Additionally, the narration of text instead of printed text is effective for focusing attention. To prevent the emergence of a split-attention effect, the text should be integrated into the picture in designs. Due to the split-attention effect, the eye-tracking and EEG data were different between the groups.Article Citation - WoS: 14Citation - Scopus: 15Relationship Between Objective and Subjective Cognitive Load Measurements in Multimedia Learning(Routledge Journals, Taylor & Francis Ltd, 2020-11-15) Mutlu-Bayraktar, Duygu; Ozel, Pinar; Altindis, Fatih; Yilmaz, BulentThe aim of this study is to compare subjective and objective cognitive load measurements in a multimedia learning environment. For this purpose, 20 university students studied in multimedia environments designed by researchers during which eye movements and multichannel electroencephalography (EEG) signals were recorded. Self-report ratings were obtained at the end of the experiment, and retention performances of the students were measured. After the data were collected, Pearson Correlation analysis was applied. According to the results, significant relationship between the number of fixations and EEG frequency band powers was found. In addition, there was a negative relationship between retention performance and number of fixations. Moreover, a negative relationship was found between retention performance and self-reported measurements.Article Citation - WoS: 18Citation - Scopus: 21Parameter Investigation of Topological Data Analysis for EEG Signals(Elsevier Sci Ltd, 2021-01) Altindis, Fatih; Yilmaz, Bulent; Borisenok, Sergey; Icoz, KutayTopological data analysis (TDA) methods have become appealing in EEG signal processing, because they may help the scientists explore new features of complex and large amount of data by simplifying the process from a geometrical perspective. Time delay embedding is a common approach to embed EEG signals into the state space. Parameters of this embedding method are variable and the structure of the state space can be entirely different depending on their selection. Additionally, extracted persistent homologies of the state spaces depend on filtration level and the number of points used. In this study, we showed how to adapt false nearest neighbor (FNN) test to find out the suitable/optimal time embedding parameters (i.e., time delay and embedding dimension) for EEG signals, and compared their effects on different types of artefacts and motor intention waves that are commonly used in brain-computer interfaces. We extracted and compared persistent homologies of state spaces that were reconstructed with four different sets of parameters. Later, the effect of filtration level on extracted persistent homologies was compared, and statistical significance levels were computed between leftand right-hand movement imaginations. Finally, computational cost of the discussed methods was found, and the adaptability of this method to a real-time application was evaluated. We demonstrated that the discussed parameters of the TDA approach were highly crucial to extract true topological features of the EEG signals, and the adapted testing approaches depicted the applicability of this approach on real-time analysis of EEG signals.Article Citation - WoS: 3Citation - Scopus: 3Object Weight Perception in Motor Imagery Using Fourier-Based Synchrosqueezing Transform and Regularized Common Spatial Patterns(IEEE-Inst Electrical Electronics Engineers Inc, 2024) Karakullukcu, Nedime; Altindis, Fatih; Yilmaz, BulentThis study addresses the challenge faced by individuals with upper-limb prostheses in regulating grip force and adapting movements to different object weights. Despite limited exploration, this research pioneers the use of EEG to estimate object weight perception in the context of upper-limb prostheses. Investigating neural correlates in this population provides valuable insights and aids the development of neurofeedback-based strategies for weight perception. Our objective is to identify EEG features predicting the weight perception of held objects. Employing Fourier-based synchrosqueezing transform (FSST) and regularized Common Spatial Patterns (CSP) features, we classify motor imagery waves representing three weight categories (light, medium, heavy). Subjects perform actual motor tasks before imagery sessions, and our approach integrates EEG features of both movements to train subject-specific machine learning models. Results reveal that FSST- singular value decomposition (SVD) features for medium and heavy objects are most distinctive. Achieving up to 90% accuracy, spatial features demonstrate effective classification of motor imagery for different weights. Unlike weight prediction studies, our focus is on visual perception and imagination of object weights, enhancing prosthetic hand system preconditioning. Binary classification surpasses 70% accuracy in predicting object weights, uniquely utilizing actual movement data for CSP algorithm regularization coefficient estimation.Article Citation - WoS: 26Citation - Scopus: 48Metabolic Imaging Based Sub-Classification of Lung Cancer(IEEE-Inst Electrical Electronics Engineers Inc, 2020) Bicakci, Mustafa; Ayyildiz, Oguzhan; Aydin, Zafer; Basturk, Alper; Karacavus, Seyhan; Yilmaz, BulentLung cancer is one of the deadliest cancer types whose 84% is non-small cell lung cancer (NSCLC). In this study, deep learning-based classification methods were investigated comprehensively to differentiate two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The study used 1457 F-18-FDG PET images/slices with tumor from 94 patients (88 men), 38 of which were ADC and the rest were SqCC. Three experiments were carried out to examine the contribution of peritumoral areas in PET images on subtype classification of tumors. We assessed multilayer perceptron (MLP) and three convolutional neural network (CNN) models such as SqueezeNet, VGG16 and VGG19 using three kinds of images in these experiments: 1) Whole slices without cropping or segmentation, 2) cropped image portions (square subimages) that include the tumor and 3) segmented image portions corresponding to tumors using random walk method. Several optimizers and regularization methods were used to optimize each model for the diagnostic classification. The classification models were trained and evaluated by performing stratified 10-fold cross validation, and F-score and area-under-curve (AUC) metrics were used to quantify the performance. According to our results, it is possible to say that inclusion of peritumoral regions/tissues both contributes to the success of models and makes segmentation effort unnecessary. To the best of our knowledge, deep learning-based models have not been applied to the subtype classification of NSCLC in PET imaging, therefore, this study is a significant cornerstone providing thorough comparisons and evaluations of several deep learning models on metabolic imaging for lung cancer. Even simpler deep learning models are found promising in this domain, indicating that any improvement in deep learning models in machine learning community can be reflected well in this domain as well.Article Citation - WoS: 20Citation - Scopus: 26Medical Infrared Thermal Image Based Fatty Liver Classification Using Machine and Deep Learning(Taylor & Francis Ltd, 2023-01-10) Ozdil, Ahmet; Yilmaz, BulentNon-alcoholic fatty liver disease (NAFLD) causes accumulation of excess fat in the liver affecting people who drink little to no alcohol. Non-alcoholic steatohepatitis (NASH) is an aggressive form of fatty liver disease (inflammation in the liver), may progress to cirrhosis and liver failure. Liver function tests, ultrasound (US) and magnetic resonance imaging (MRI) are used to help diagnose and monitor liver disease or damage. In this study, the feasibility of medical infrared thermal imaging (MITI) in automatic detection of NAFLD was investigated, and 167 MITI images (44 positive) from 32 patients (7 positive) were evaluated using image processing and classification methods. Convolutional neural network (CNN) architectures and texture analysis methods were used in the feature selection phase. After feature selection and binary classification, the highest values from different setups for recall, f-score, specificity, accuracy, and area-under-curve (AUC) were 1.00, 1.00, 0.83, 1.0, 0.94, and 0.92, respectively. The highest values were achieved by CNN based methods on different datasets, however, texture analysis method performed lower. Here, it is shown that some of the CNN architectures have high potential on extracting features from thermal images. Finally, machine and deep learning approaches can be combined in detecting NAFLD using infrared thermal images.