Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
21 results
Search Results
Publication Metadata only Augmenting clinical observations with visual features from longitudinal MRI data for improved dementia diagnosis(2010) Ünay, Devrim; Ünay, Devrim, Bahçeşehir Üniversitesi, Istanbul, TurkeyImage-based diagnosis in the medical area often requires qualitative interpretation from the experts, despite the high-resolution of the acquired images. Computation of quantitative measures and comparison of multiple patients using automated medical image analysis tools will help improve the diagnosis and efficiency, especially in the areas such as neurology, where diagnosis from one patient's data has limitations and the prevalence of neurodegenerative diseases is expected to substantially increase in the near future due to the aging population. To this end, this paper presents a novel work on fusing clinical and patient-demographics related observations with visual features computed from brain longitudinal MRI (magnetic resonance imaging) data for improved dementia diagnosis. Experiments with real data showed that augmenting cognitive scores with visual features from a subset of subcortical structures results in more accurate diagnosis. Moreover, subset of structures typically selected are consistent with those (being) investigated in the literature. Copyright 2010 ACM. © 2010 Elsevier B.V., All rights reserved.Publication Metadata only Automated X-ray image annotation single versus ensemble of support vector machines(2010) Ünay, Devrim; Soldea, Octavian; Akyüz, Süreyya; Çetin, Müjdat; Erçil, Aytül; Ünay, Devrim, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Soldea, Octavian, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Akyüz, Süreyya, Bahçeşehir Üniversitesi, Istanbul, Turkey; Çetin, Müjdat, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Erçil, Aytül, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, TurkeyAdvances in the medical imaging technology has lead to an exponential growth in the number of digital images that needs to be acquired, analyzed, classified, stored and retrieved in medical centers. As a result, medical image classification and retrieval has recently gained high interest in the scientific community. Despite several attempts, such as the yearly-held ImageCLEF Medical Image Annotation Challenge, the proposed solutions are still far from being sufficiently accurate for real-life implementations. In this paper we summarize the technical details of our experiments for the ImageCLEF 2009 medical image annotation challenge. We use a direct and two ensemble classification schemes that employ local binary patterns as image descriptors. The direct scheme employs a single SVM to automatically annotate X-ray images. The two proposed ensemble schemes divide the classification task into sub-problems. The first ensemble scheme exploits ensemble SVMs trained on IRMA sub-codes. The second learns from subgroups of data defined by frequency of classes. Our experiments show that ensemble annotation by training individual SVMs over each IRMA sub-code dominates its rivals in annotation accuracy with increased process time relative to the direct scheme. © 2010 Springer-Verlag Berlin Heidelberg. © 2010 Elsevier B.V., All rights reserved.Publication Metadata only Segmentation of anatomical structures in brain MR images using atlases in FSL - A quantitative approach(2010) Soldea, Octavian; Ekin, Ahmet; Soldea, Diana F.; Ünay, Devrim; Çetin, Müjdat; Erçil, Aytül; Uzunbaş, Mustafa Gökhan; Fırat, Zeynep; Cihangiroǧlu, Mutlu M.; Soldea, Octavian, Video Processing and Analysis Group, Philips Research, Eindhoven, Netherlands; Ekin, Ahmet, Video Processing and Analysis Group, Philips Research, Eindhoven, Netherlands; Soldea, Diana F., Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Ünay, Devrim, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Çetin, Müjdat, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Erçil, Aytül, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Uzunbaş, Mustafa Gökhan, Department of Computer Science, Rutgers University–New Brunswick, New Brunswick, United States; Fırat, Zeynep, Department of Radiology, Yeditepe University, Istanbul, Turkey; Cihangiroǧlu, Mutlu M., Department of Radiology, Yeditepe University, Istanbul, TurkeySegmentation of brain structures from MR images is crucial in understanding the disease progress, diagnosis, and treatment monitoring. Atlases, showing the expected locations of the structures, are commonly used to start and guide the segmentation process. In many cases, the quality of the atlas may have a significant effect in the final result. In the literature, commonly used atlases may be obtained from one subject's data, only from the healthy, or depict only certain structures that limit their accuracy. Anatomical variations, pathologies, imaging artifacts all could aggravate the problems related to application of atlases. In this paper, we propose to use multiple atlases that are sufficiently different from each other as much as possible to handle such problems. To this effect, we have built a library of atlases and computed their similarity values to each other. Our study showed that the existing atlases have varying levels of similarity for different structures. © 2010 IEEE. © 2010 Elsevier B.V., All rights reserved.Publication Metadata only Air drums: A computer vision based drums simulator, Bilgisayarla görü tabanli davul benzetimcisi(2010) Fidan, Kaan Can; Kehribar, İhsan; Şahin, M. Tuǧçe; Cosar, Serhan; Ünay, Devrim; Fidan, Kaan Can, Mühendislik ve Doǧa Bilimleri Fakültesi, Sabancı Üniversitesi, Tuzla, Turkey; Kehribar, İhsan, Mühendislik ve Doǧa Bilimleri Fakültesi, Sabancı Üniversitesi, Tuzla, Turkey; Şahin, M. Tuǧçe, Mühendislik ve Doǧa Bilimleri Fakültesi, Sabancı Üniversitesi, Tuzla, Turkey; Cosar, Serhan, Mühendislik ve Doǧa Bilimleri Fakültesi, Sabancı Üniversitesi, Tuzla, Turkey; Ünay, Devrim, Bahçeşehir Üniversitesi, Istanbul, TurkeyThe aim of this paper is to present a novel system which tracks the motion of a drummer and generates the corresponding drum sounds. The input video sequence from a camera is processed in real-time by using local and adaptive color segmentation and Kalman filter based tracking. The Kalman filter is used to predict the hits so that we can overcome the processing delays and provide a more-realistic drumming experience. We use a local and adaptive search to detect the effective points of the drum sticks, which ensures robustness to background clutter and reduces the computational burden. We have developed a working demo and evaluated its performance by comparing with the output signal of an electronic drum pad. We observed that the timing errors have an average of -8.4 ms and a standard deviation of 5.4 ms in a real drumming experiment consisting of 121 hits. ©2010 IEEE. © 2011 Elsevier B.V., All rights reserved.Publication Metadata only Dementia diagnosis using similar and dissimilar retrieval items(2011) Ünay, Devrim; Ekin, Ahmet; Ünay, Devrim, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ekin, Ahmet, Video Processing and Analysis Group, Philips Research, Eindhoven, NetherlandsImage-based disease diagnosis often requires radiologists' qualitative interpretations that are highly dependent on their levels of expertise, and physical and mental status. Automated image analysis tools can help radiologists increase the diagnosis accuracy by providing quantitative measures. Accordingly, this paper presents an automated method for dementia diagnosis using search and retrieval of brain MR (magnetic resonance) images. The main contributions of the method are 1)its generic decision-making based on similar and dissimilar cases retrieved from a database that can be used to diagnose various brain disorders, 2)it realizes dementia diagnosis utilizing a tailored version of histogram of oriented gradients (HOGs) as features, and 3)it achieves high performance in dementia diagnosis that is independent of the database size. Comprehensive experiments with real data showed that combining information from similar and dissimilar cases leads to improved diagnostic accuracy than using similar or dissimilar cases alone, accuracy diminishes with extreme quantization of the HOGs and with small databases, and our method achieves high performance with comparable sensitivity score to the most skilled experts at better specificity figures. © 2011 IEEE. © 2011 Elsevier B.V., All rights reserved.Publication Metadata only Medical multimedia analysis and retrieval(2011) Cao, Yu X.; Kalpathy-Cramer, Jayashree; Ünay, Devrim; Cao, Yu X., College of Engineering and Computer Science, Chattanooga, United States; Kalpathy-Cramer, Jayashree, Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, United States; Ünay, Devrim, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyAdvances in sensor technology, processing speed, high-speed networking, and the massive digital storages are being incorporated into today's healthcare practice. Tremendous amounts of medical multimedia data are captured and recorded in digital format during the daily clinical practice, medical research, and education. Intelligent medical knowledge discovery and retrieval from medical multimedia data is very useful and highly desirable. Motivated by the huge potential benefits, we have organized the ACM International Workshop on Medical Multimedia Analysis and Retrieval (MMAR2011), held in conjunction with The Annual ACM International Conference on Multimedia (ACM Multimedia 2011). In this paper, we first introduce the background and overview of the workshop. Then we introduce the workshop review process, followed with a brief introduction of the accepted papers in this workshop, as well as the conclusion. © 2011 ACM. © 2012 Elsevier B.V., All rights reserved.Publication Metadata only Inter-hemispheric atrophy better correlates with expert ratings than hemispheric cortical atrophy, İnterhemi̇sferi̇k atrofi̇ ölçümleri̇ hemi̇sferi̇k korti̇kal atrofi̇ ölçümleri̇ i̇le karşilaştirildiǧinda uzman derecelendi̇ rmesi̇ i̇le daha uyumludur(2012) Başkaya, Osman; Kandemir, Melek; Tepe, Muzaffer Savaş; Acar, M.; Unal, Gozde Bozkurt; Yalçıner, Zehra Betül; Ünay, Devrim; Başkaya, Osman, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kandemir, Melek,; Tepe, Muzaffer Savaş, Radyoloji Departmani, Istanbul, Turkey; Acar, M., Radyoloji Departmani, Istanbul, Turkey; Unal, Gozde Bozkurt, Mühendislik ve Doǧa Bilimleri Fakültesi, Sabancı Üniversitesi, Tuzla, Turkey; Yalçıner, Zehra Betül,; Ünay, Devrim, Bahçeşehir Üniversitesi, Istanbul, TurkeyBrain atrophy is one of the parameters considered by experts for rating dementia from neuro-imaging findings. Research efforts have focused on measuring brain atrophy from images through experts' visual assessment or computer-based approaches. However, agreement between the visual assessment and computer-based measurement of atrophy is not yet investigated. Accordingly, this paper presents an automated method for cerebral atrophy assessment from cross-sectional MRI through hemispheric volume loss. For this purpose, the proposed method quantifies inter-hemispheric distance, and the distance between the cranium and the brain parenchyma, separately. Discriminative power of the proposed method is evaluated on two datasets with experts' visual gradings: Yue et al.'s data and a newly created reference dataset. Results show that inter-hemispheric atrophy better correlates with visual grades, and inconsistencies at the skull-stripping or brain tissue extraction steps can degrade the agreement between computer-based measurements and expert gradings. © 2012 IEEE. © 2013 Elsevier B.V., All rights reserved.Publication Metadata only A tool for automatic dendritic spine detection and analysis. Part I: Dendritic spine detection using multi-level region-based segmentation(2012) Erdil, Ertunç; Yağcı, A. Murat; Argunşah, Ali Özgür; Ramiro-Cortés, Yazmín; Hobbiss, Anna Felicity; Israely, Inbal; Ünay, Devrim; Erdil, Ertunç, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Yağcı, A. Murat, Department of Computer Engineering, Boğaziçi Üniversitesi, Bebek, Turkey; Argunşah, Ali Özgür, Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal; Ramiro-Cortés, Yazmín, Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal; Hobbiss, Anna Felicity, Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal; Israely, Inbal, Champalimaud Neuroscience Programme, Champalimaud Centre for the Unknown, Lisbon, Portugal; Ünay, Devrim, Biomedical Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyWe propose an image processing pipeline for dendritic spine detection in two-photon fluorescence microscopy images. Spines of interest to neuroscientists often contain high intensity regions with respect to their surroundings. We find such maxima regions using morphological image reconstruction. These regions facilitate a multi-level segmentation algorithm to detect spines. First, watershed algorithm is applied to extract initial rough regions of spines. Then, these results are further refined using a graph-theoretic region-growing algorithm which incorporates segmentation on a sparse representation of image data and hierarchical clustering as a post-processing step. We compare our final results to segmentation results of the domain expert. Our pipeline produces promising segmentation results with practical run times for monitoring streaming data. © 2012 IEEE. © 2013 Elsevier B.V., All rights reserved.Publication Metadata only Region growing on frangi vesselness values in 3-D CTA data, 3-BOYUTLU bt anjiyografi verilerinde frangi damarlik yöntemi üzerine bölge büyütme yaklasimi(2013) Oksuz, Ilkay; Ünay, Devrim; Kadipaşaoǧlu, Kâmuran A.; Oksuz, Ilkay, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ünay, Devrim, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kadipaşaoǧlu, Kâmuran A., Bahçeşehir Üniversitesi, Istanbul, TurkeyIn cardiac related diagnostic methods, the shape and curvature of coronary arteries is essential. Consequently, one of the most important requirements for Computer Aided Diagnosis (CAD) Systems is automated segmentation of vasculature. In this paper, we propose a new hybrid algorithm, which segment the coronary arterial tree in CTA images by merging methodologies-, namely, Region Growing and Frangi Approach. The algorithm first runs a region growing on Frangi vesselness values and subsequently optimizes the results with several threshold values. Comparison of the present results with optimal results of existing segmentation algorithms reveals that the proposed approach outperforms its predecessors. The diagnostic accuracy of the algorithm will next be validated on the segmentation of coronary arteries from real CT data. © 2013 IEEE. © 2013 Elsevier B.V., All rights reserved.Publication Metadata only Text mining in radiology reports, Radyoloji raporlarinda metin madenciligi(2013) Kocatekin, Tugberk; Ünay, Devrim; Kocatekin, Tugberk, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ünay, Devrim, Bahçeşehir Üniversitesi, Istanbul, TurkeyText mining is a popular research topic with application areas ranging from security to media and marketing. More specifically, text mining has been applied in biomedical area for the categorization of radiology reports, which is a challenging problem due to their free-text and unstructured format. State-of-the-Art in radiology report mining has mostly focused on English text, while studies on Turkish reports are scarce. Accordingly, in this work we propose to employ text mining for categorization of Turkish radiology reports. We automatically remove header and footer of the reports, apply frequency analysis on the remaining report text, and perform categorization of reports to anatomical regions using pre-selected keywords. The accuracy of the proposed solution is measured as 84.3% over a 66-report test set. © 2013 IEEE. © 2013 Elsevier B.V., All rights reserved.
- «
- 1 (current)
- 2
- 3
- »