Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
17 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: 1Citation - Scopus: 1Prediction of Preference and Effect of Music on Preference: A Preliminary Study on Electroencephalography from Young Women(Tubitak Scientific & Technological Research Council Turkey, 2019-03-01) Yilmaz, Bulent; Gazeloglu, Cengiz; Altindis, FatihNeuromarketing is the application of the neuroscientific approaches to analyze and understand economically relevant behavior. In this study, the effect of loud and rhythmic music in a sample neuromarketing setup is investigated. The second aim was to develop an approach in the prediction of preference using only brain signals. In this work, 19-channel EEG signals were recorded and two experimental paradigms were implemented: no music/silence and rhythmic, loud music using a headphone, while viewing women shoes. For each 10-sec epoch, normalized power spectral density (PSD) of EEG data for six frequency bands was estimated using the Burg method. The effect of music was investigated by comparing the mean differences between music and no music groups using independent two-sample t-test. In the preference prediction part sequential forward selection, k-nearest neighbors (k-NN) and the support vector machines (SVM), and 5-fold cross-validation approaches were used. It is found that music did not affect like decision in any of the power bands, on the contrary, music affected dislike decisions for all bands with no exceptions. Furthermore, the accuracies obtained in preference prediction study were between 77.5 and 82.5% for k-NN and SVM techniques. The results of the study showed the feasibility of using EEG signals in the investigation of the music effect on purchasing behavior and the prediction of preference of an individual.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.Conference Object Citation - Scopus: 1Many-to Transfer Learning on Motor Imagery BCI(Institute of Electrical and Electronics Engineers Inc., 2024-12-11) Altindis, Fatih; Yilmaz, Bulent; Congedo, MarcoThis paper presents many-to-many domain adaptation strategy, named group learning, for motor imagery brain-computer interfaces (BCIs). Group learning, grounded in Riemannian geometry, simultaneously aligns multiple domains in a unified model, whereas fast alignment approach integrates new, unseen domains without re-estimating alignment matrices for all domains. Group learning creates a single machine learning model using data from previous subjects and/or sessions. Fast alignment utilizes the already trained model for an unseen domain without requiring any additional classifier training. The tests on five publicly available motor imagery databases demonstrate the robustness of group learning against negative learning. The classification accuracy scores of binary and multiclass databases show comparable, if not superior, performance to conventional subject-wise learning method. © 2025 Elsevier B.V., All rights reserved.Article Citation - WoS: 8Citation - Scopus: 10Lung Cancer Subtype Differentiation From Positron Emission Tomography Images(Tubitak Scientific & Technological Research Council Turkey, 2020-01-27) Ayyildiz, Oguzhan; Aydin, Zafer; Yilmaz, Bulent; Karacavus, Seyhan; Senkaya, Kubra; Icer, Semra; Kaya, Eser; Taşdemir, ArzuLung cancer is one of the deadly cancer types, and almost 85% of lung cancers are nonsmall cell lung cancer (NSCLC). In the present study we investigated classification and feature selection methods for the differentiation of two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The major advances in understanding the effects of therapy agents suggest that future targeted therapies will be increasingly subtype specific. We obtained positron emission tomography (PET) images of 93 patients with NSCLC, 39 of which had ADC while the rest had SqCC. Random walk segmentation was applied to delineate three-dimensional tumor volume, and 39 texture features were extracted to grade the tumor subtypes. We examined 11 classifiers with two different feature selection methods and the effect of normalization on accuracy. The classifiers we used were the k-nearest-neighbor, logistic regression, support vector machine, Bayesian network, decision tree, radial basis function network, random forest, AdaBoostM1, and three stacking methods. To evaluate the prediction accuracy we performed a leave-one-out cross-validation experiment on the dataset. We also considered optimizing certain hyperparameters of these models by performing 10-fold cross-validation separately on each training set. We found that the stacking ensemble classifier, which combines a decision tree, AdaBoostM1, and logistic regression methods by a metalearner, was the most accurate method for detecting subtypes of NSCLC, and normalization of feature sets improved the accuracy of the classification method.Article Citation - Scopus: 2Improving Short-Term Memory Performance of Healthy Young Males Using Alpha Band Neurofeedback(International Society for Neurofeedback and Research, 2019-03-24) Gökşin, Barış; Yilmaz, Bulent; İçöz, KutayTo examine whether it was possible to improve short-term memory performance of healthy participants by increasing relative alpha band power (7–11.5 Hz) using neurofeedback, we first converted a commercial EEG device (EmotivEpoc) to a neurofeedback tool and collected data from 11 healthy Turkish male graduate students in five neurofeedback sessions. Before and after neurofeedback training, a memorization task using 10 English words and their Turkish meanings was applied to all participants. The results indicated that 6 out of 11 participants were able to enhance their relative alpha band power with respect to other bands in the frequency spectrum during neurofeedback sessions. Although there was no obvious improvement in their short-term memory performance, we may conclude that neurofeedback training was beneficial for the participants to focus their minds consciously. However, it is not easy to mention that neurofeedback training certainly improved or was irrelevant with short-term memory performance. This study is important in the sense that for such a focused group the use of a commercial, customized low-cost EEG device was shown to be feasible for neurofeedback training sessions. © 2019 Elsevier B.V., All rights reserved.Article Citation - Scopus: 5Hyperplastic and Tubular Polyp Classification Using Machine Learning and Feature Selection(Elsevier B.V., 2024) Doǧan, Refika Sultan; Akay, Ebru; Doǧan, Serkan; Yilmaz, BulentPurpose: The aim of this study is to develop an effective approach for differentiating between hyperplastic and tubular adenoma colon polyps, which is one of the most difficult tasks in colonoscopy procedures. The main research challenge is how to improve the classification of these polyp subtypes applying various focusing levels on the polyp images, data preprocessing approaches, and classification algorithms. Methods: This study employed 202 colonoscopy videos from a total of 201 patients, focusing on 59 videos containing hyperplastic and tubular adenoma polyps. Manually extract key frames and several feature extraction and classification techniques were applied. The influence of different datasets with various focuses as well as data preprocessing steps on the performance of classification was examined, and AUC values were calculated using ten classifiers. Results: The study discovered that the optimal dataset, data preprocessing method, and classification algorithm all had significant effects on classification results. The Random Forest model with the Recursive Feature Elimination (RFE) feature selection approach, for example, consistently outperformed other models and achieved the highest AUC value of 0.9067. In terms of accuracy, F1 score, recall, and AUC, the suggested model outperformed a gastroenterologist, nevertheless precision remained slightly lower. Conclusion: This study emphasizes the importance of dataset selection, data preprocessing, and feature selection in enhancing the classification of difficult colon polyp subtypes. The suggested model offers a promising model for the clinical differentiation of hyperplastic and tubular adenoma polyps, potentially improving diagnostic accuracy in gastroenterology. © 2024 Elsevier B.V., All rights reserved.Article Citation - WoS: 15Citation - Scopus: 18Histopathology Image Classification: Highlighting the Gap Between Manual Analysis and AI Automation(Frontiers Media S.A., 2024-01-17) Dogan, Refika Sultan; Yilmaz, BulentThe field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.