TR-Dizin İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/396

Browse

Filters

2022 - 20255

Settings

Author: search.filters.author.Yilmaz, BulentLanguage: search.filters.language.tr

Search Results

Now showing 1 - 5 of 5
  • 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 Yengeç
    Kolon 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, Mahsa
    The 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, Mahsa
    The 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 Yengeç
    In 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
    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, Bulent
    This 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.