TR-Dizin İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/396
Browse
8 results
Search Results
Research Project Kolon Polipleri için Kolonoskopi ve Histopatoloji Görüntülerinden Yapay Zekâ Destekli Prognostik Belirteç Tespiti(2023) Doğan, Serkan; Doğan, Refika Sultan; Aydın, Zafer; Akay, Ebru; Güzel, Ömer Faruk; Yilmaz, Bulent; Taşdemir, Sena Büşra YengeçKolon kanseri vakalarının çoğu kolon mukozasında anormal hücre çoğalmasından kaynaklanan poliplerle başlar. Bu projede Kayseri Şehir Hastanesi gastroenteroloji kliniğine gelen 201 hastada tespit edilen poliplere dair kolonoskopi video ve görüntülerinden ve biyopsi örneklerinden elde edilen patoloji raporu ve immunohistokimyasal (İHK) gen ve protein analizi sonuçlarını içeren kapsamlı bir veri seti oluşturulmuştur. Bu projede, elde ettiğimiz veri setinde yer alan görüntülerden kolon poliplerinin evresini/patolojisini tahmin etmek için yenilikçi derin öğrenme ve makine öğrenmesi yöntemlerini temel alan çevrim içi veya dışı kullanılabilen kapsamlı bir yapay zekâ destekli bilgisayarlı görü sistemi geliştirilmiştir. Bu proje kapsamında; kolonoskopi videolarından gerçek zamanlı polip lokalizasyonu, videolardan görüntülerin elde edilmesi, polip görüntülerinden hiperplastik ve tübüler polip ayrımının otomatik yapılması ve hekim performansıyla karşılaştırılması, bu görüntüler üzerinde ayırt edici özniteliklerin tespit edilmesi, farklı büyütmelerde alınan histopatoloji görüntülerinden adenomatöz olan ve olmayan poliplerin ve poliplerin alt tiplerinin yenilikçi derin öğrenme yöntemleriyle tespiti, Ki-67, p53, VEGF, PDL-lenfosit ve PDL-epitel, BRAF ve cd34 isimli gen ve proteinlerin İHK analizlerinin sonuçlarının polip tipleri ve alt tipleri için yorumlanması ve poliplerin bu bilgilere göre etiketlenmesi gerçekleştirilmiştir.Research Project Biyonik Elin Faaliyete Hazırlanmasında Kaldırılacak Cisme dair Ağırlık Algısının Beyin Sinyalleriyle Belirlenmesi(2022) Ulutabanca, Halil; Altindis, Fatih; Unal, Ramazan; Yilmaz, Bulent; Sarrafıkhosrowshah, MahsaThe upper extremity prostheses vary due to the patient?s articulation level and the methods used to move them. There are prostheses that are either cosmetic, or that work with shoulder movement (mechanical), or controlled by myoelectronic and electroencephalography (EEG) signals. However, intuitive and unnatural control of the prosthesis places a great mental burden on the user. In this project, the aim is to develop a system to improve the control of the bionic hand prosthesis by using EEG and EMG signals together, by making use of the user's visual weight perception. With this system, it is aimed to reduce the physical and mental burden/discomfort patients may experience while using a mechanical prosthesis. The preconditioning of the prototype hand to be produced is provided by evaluating the weight of the objects seen by the patients to the extent that the brain perceives them visually. In this way, the force exerted by the patient on the shoulder while holding the object will decrease and the mental load will be alleviated. For this purpose, EEG and electromyography (EMG) signals of the subjects were taken and processed, and then a real-time implementation was developed. In the first stage, a study was conducted that aimed to operate the prosthesis by using the motor intention waves of the prosthesis users and the classification success of the machine learning approaches (detection of the intention to activate the prosthesis) was examined by taking EEG data from 30 healthy participants. In the second stage, EEG and EMG signals of 31 healthy participants were recorded synchronously while reaching for the object, lifting the object and leaving the object in the starting position. After the features of these signals were determined, it was determined that the object was heavy, medium weight or light using various classification approaches. In parallel with biosignal processing studies, prosthetic hand and wrist designs and three- dimensional prints were obtained. It is aimed to use the shoulder movement to open and close the prosthetic hand, and to control the wrist stiffness, to process the biosignals and drive a tiny motor with high torque with the automatic decision produced. In addition, the characterization of the prosthesis was made. As a result of the classification of the multi-channel EEG signals from 20 healthy individuals with Fourier-based synchrosequeezing transform (FSST) and singular value decomposition (SVD) approaches by extracting features, the goal was to control the stiffness of the wrist part of the prosthesis. As a result, it was possible for the system to detect the weight of the object the user sees while employing the prosthesis and to precondition the prosthesis according to this weight when they want to hold and move that object.Research Project Biyonik Elin Faaliyete Hazırlanmasında Kaldırılacak Cisme Dair Ağırlık Algısının Beyin Sinyalleriyle Belirlenmesi(2022) Ulutabanca, Halil; Altindis, Fatih; Unal, Ramazan; Yilmaz, Bulent; Sarrafıkhosrowshah, MahsaThe upper extremity prostheses vary due to the patient?s articulation level and the methods used to move them. There are prostheses that are either cosmetic, or that work with shoulder movement (mechanical), or controlled by myoelectronic and electroencephalography (EEG) signals. However, intuitive and unnatural control of the prosthesis places a great mental burden on the user. In this project, the aim is to develop a system to improve the control of the bionic hand prosthesis by using EEG and EMG signals together, by making use of the user's visual weight perception. With this system, it is aimed to reduce the physical and mental burden/discomfort patients may experience while using a mechanical prosthesis. The preconditioning of the prototype hand to be produced is provided by evaluating the weight of the objects seen by the patients to the extent that the brain perceives them visually. In this way, the force exerted by the patient on the shoulder while holding the object will decrease and the mental load will be alleviated. For this purpose, EEG and electromyography (EMG) signals of the subjects were taken and processed, and then a real-time implementation was developed. In the first stage, a study was conducted that aimed to operate the prosthesis by using the motor intention waves of the prosthesis users and the classification success of the machine learning approaches (detection of the intention to activate the prosthesis) was examined by taking EEG data from 30 healthy participants. In the second stage, EEG and EMG signals of 31 healthy participants were recorded synchronously while reaching for the object, lifting the object and leaving the object in the starting position. After the features of these signals were determined, it was determined that the object was heavy, medium weight or light using various classification approaches. In parallel with biosignal processing studies, prosthetic hand and wrist designs and three- dimensional prints were obtained. It is aimed to use the shoulder movement to open and close the prosthetic hand, and to control the wrist stiffness, to process the biosignals and drive a tiny motor with high torque with the automatic decision produced. In addition, the characterization of the prosthesis was made. As a result of the classification of the multi-channel EEG signals from 20 healthy individuals with Fourier-based synchrosequeezing transform (FSST) and singular value decomposition (SVD) approaches by extracting features, the goal was to control the stiffness of the wrist part of the prosthesis. As a result, it was possible for the system to detect the weight of the object the user sees while employing the prosthesis and to precondition the prosthesis according to this weight when they want to hold and move that object.Research Project Artificial Intelligence Assisted Prognostic Marker Determination from Colonoscopy and Histopathology Images for Colon Polyps(2023) Doğan, Serkan; Doğan, Refika Sultan; Aydın, Zafer; Akay, Ebru; Güzel, Ömer Faruk; Yilmaz, Bulent; Taşdemir, Sena Büşra YengeçIn this project our goal is to develop a computer vision and artificial intelligence-based system to be used in the real-time or offline differentiation (and characterization) of colon polyps that are known to be the precursors of colon cancer. The system will use image/video processing, machine learning and deep learning approaches. It is expected to provide a real-time optical biopsy opportunity to the endoscopists to examine the polyps in terms of type, phase, malignancy potential, etc. during the colonoscopy procedure without a need to send the extracted tissue to the pathology clinic. The system will allow to make sense of the molecular level of the tissues from the colonoscopy and histopathology images.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: 4Citation - Scopus: 5Noise-Assisted Multivariate Empirical Mode Decomposition Based Emotion Recognition(Istanbul Univ-Cerrahapasa, 2018-08-03) Ozel, Pinar; Akan, Aydin; Yilmaz, BulentEmotion state detection or emotion recognition cuts across different disciplines because of the many parameters that embrace the brain's complex neural structure, signal processing methods, and pattern recognition algorithms. Currently, in addition to classical time-frequency methods, emotional state data have been processed via data-driven methods such as empirical mode decomposition (EMD). Despite its various benefits, EMD has several drawbacks: it is intended for univariate data; it is prone to mode mixing; and the number of local extrema must be enough before the EMD process can begin. To overcome these problems, this study employs a multivariate EMD and its noise-assisted version in the emotional state classification of electroencephalogram signals. Emotion state detection or emotion recognition cuts across different disciplines because of the many parameters that embrace the brain's complex neural structure, signal processing methods, and pattern recognition algorithms. Currently, in addition to classical time-frequency methods, emotional state data have been processed via data-driven methods such as empirical mode decomposition (EMD). Despite its various benefits, EMD has several drawbacks: it is intended for univariate data; it is prone to mode mixing; and the number of local extrema must be enough before the EMD process can begin. To overcome these problems, this study employs a multivariate EMD and its noise-assisted version in the emotional state classification of electroencephalogram signals.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 3D Sampling of K-Space With Non-Cartesian Trajectories in MR Imaging(Gazi Univ, Fac Engineering Architecture, 2025-02-03) Dundar, Mehmet Sait; Gumus, Kazim Z.; Yilmaz, BulentThis study presents an innovative approach to 3D k-space sampling in MR imaging using non-Cartesian concentric shell trajectories. The method involves 32 concentric shells of varying radii, allowing for rapid data acquisition through undersampling techniques. Simulations using IDEA software demonstrate that this approach can fill the k-space in less than one second, a significant time reduction compared to traditional FLASH sequences that can take 3-4 minutes. The concentric shell model enhances imaging efficiency by minimizing artifacts and ensuring uniform k-space filling, leading to higher resolution and faster scans. This technique shows promise for clinical applications, particularly in dynamic imaging scenarios such as acute stroke and pediatric radiology, where speed and precision are critical. As illustrated in Figure A, the concentric shell trajectories enable uniform k-space filling, significantly reducing scan times and improving image quality. These results are based on the simulations conducted with IDEA software.