Ünay, Devrim
Loading...
Profile URL
Name Variants
Unay, Devrin
Ünay, D.
Unay, Devrim
Ünay, D.
Unay, Devrim
Job Title
Email Address
devrim.unay@ieu.edu.tr
Main Affiliation
05.02. Biomedical Engineering
Status
Former Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Sustainable Development Goals
Documents
109
Citations
1800
h-index
18
Documents
87
Citations
1333
Scholarly Output
29
Articles
7
Views / Downloads
2/0
Supervised MSc Theses
1
Supervised PhD Theses
0
WoS Citation Count
154
Scopus Citation Count
214
WoS h-index
6
Scopus h-index
8
Patents
0
Projects
0
WoS Citations per Publication
5.31
Scopus Citations per Publication
7.38
Open Access Source
10
Supervised Theses
1
| Journal | Count |
|---|
Current Page: 1 / NaN
Scopus Quartile Distribution
Competency Cloud
29 results
Scholarly Output Search Results
Now showing 1 - 10 of 29
Conference Object Dermoscopic Lesion Segmentation Via Optimal Color Channel Fusion(IEEE, 2024) Okur, Erdem; Unay, Devrim; Turkan, MehmetDeath caused by various kinds of cancer is on rise and skin cancer is one of the most common one worldwide. Due to the importance of early detection, dermoscopy is adopted for visualizing skin lesions and computer-aided detection benefits from these dermoscopic images for better diagnosis results. One of the most important phase of automated skin lesion detection or classification is segmentation, but it is a very challenging task because of several artifacts existing on these images. In this paper, a new method to improve skin lesion segmentation from the existing deep network architectures is proposed, based on the fusion of various results produced by existing models on different color channels. Experimental validations demonstrate that the proposed method increases the average accuracy, on lesion segmentation in terms of Sorensen-Dice and Jaccard indices, when compared to conventional techniques.Conference Object Accurate Dictionary Matching for Mr Fingerprinting Using Neural Networks and Feature Extraction(Institute of Electrical and Electronics Engineers Inc., 2020) Soyak R.; Ersoy E.O.; Navruz E.; Fakultesi M.; Unay D.; Oksuz I.Magnetic Resonance Fingerprinting is a recent technique which aims at providing simultaneous measurements of multiple parameters. MRF works by varying acquisition parameters in a pseudorandom manner so as to get unique, uncorrelated signal evolutions from each tissue. MRF is a dictionary based approach, and thus requires a database. This database can be created by simulating the signal evolutions from first principles using different physical models for a wide variety of tissue parameter combinations. Having this dictionary, a pattern recognition algorithm is used to match the acquired signal evolutions from each voxel with each signal evolution in the dictionary. In this paper, we compare the efficiency of deep learning based feature extraction method and neural network architectures in order to achieve state-of-the-art accuracy in dictionary matching for MRF. Our results showcase successful dictionary matching with high accuracy both quantitatively and qualitatively. © 2020 IEEE.Conference Object Coupled Shape Priors for Dynamic Segmentation of Dendritic Spines(Institute of Electrical and Electronics Engineers Inc., 2017) Atabakilachini N.; Erdil E.; Argunsah A.O.; Rada L.; Unay D.; Cetin M.Segmentation of biomedical images is a challenging task, especially when there is low quality or missing data. The use of prior information can provide significant assistance for obtaining more accurate results. In this paper we propose a new approach for dendritic spine segmentation from microscopic images over time, which is motivated by incorporating shape information from previous time points to segment a spine in the current time point. In particular, using a training set consisting of spines in two consecutive time points to construct coupled shape priors, and given the segmentation in the previous time point, we can improve the segmentation process of the spine in the current time point. Our approach has been evaluated on 2-photon microscopy images of dendritic spines and its effectiveness has been demonstrated by both visual and quantitative results. © 2017 IEEE.Master Thesis Data Mining for Emotion Recognition in Speech(İzmir Ekonomi Üniversitesi, 2019) Akkurt, Gamze; Ünay, DevrimKonuş¸ma sinyalinde duygu sınıflandırması için kullanılan popüler özellikler temel frekans, ses kalitesi, enerji, spektral ve MFCC'dir. Çalışmaların çoğu konuşmadaki duyguların tanınmasında bu akustik özelliklere odaklanırken, bu tezde biz; duygusal kalıplardan elde edilen özellikleri kullanarak duygu tanıma sorunu ele alınmıstır. Yaklaşımımızda, konuş¸ma sinyalini ayrıklaştırılmış, sinyale dönüştürür ve farklı duygular arasında ayrım yapabilen ayırt edici kalıplar çıkartılmaktadır. Ardından, sınıflandırıcıyı güçlendirmek için; çıkartılan kalıplarla bir dizi vektör özelliği oluşturulur. Deneysel sonuçlar, önerilen yaklaşımın, hem desene dayalı özelliklerden hem de desene ait özelliklerle desteklenen akustik özelliklerden duygusal konuşma durumunu etkili bir şekilde öğrendiğini göstermektedir. Desen bazlı özellikler, son teknoloji akustik özelliklere kıyasla iki sınıflandırıcı teknik kullanılarak doğrulukta %35 'lik artış ile sonuçlanmaktadır. Ayrca, bütün akustik özellikler, desen bazlı özelliklerile desteklendiğinde % 80 'nin üzerinde artış göstermektedir.Conference Object MANUAL AND AUTOMATIC SIZE MEASUREMENT OF LATERAL VENTRICLES AND CENTRAL SULCI AND THEIR COMPLIANCE WITH ATROPHY GRADE(IEEE, 2015) Gokay, Gokhan; Kandemir, Melek; Tepe, M. Savas; Yalciner, Betul; Unay, DevrimDiagnosis and treatment of various brain diseases occurring due to aging such as dementia, take an important role in contemporary research for elderly population in the world and in our country with increasing progressively. Cerebral atrophy is a feature observed in dementia patients and described as neuronal loss or cell death affecting part or all of the brain, to determine the presence and severity of atrophy, experts visually evaluate magnetic resonance images of the brain, especially at locations such as lateral ventricles and central sulci. The aim of this study is measuring the sizes (e.g. length, area and volume) of lateral ventricles and central sulci in 3D and to compare these measurements with experts' atrophy ratings. Lateral ventricle width shows high agreement (around 0.84) with atrophy grades.Conference Object Dendritic Spine Classification Based on Two-Photon Microscopic Images Using Sparse Representation(Institute of Electrical and Electronics Engineers Inc., 2016) Ghani M.U.; Kanik S.D.; Argunşah A.O.; Israely I.; Ünay D.; Çetin M.Dendritic spines, membranous protrusions of neurons, are one of the few prominent characteristics of neurons. Their shapes change with variations in neuron activity. Spine shape analysis plays a significant role in inferring the inherent relationship between neuron activity and spine morphology variations. First step towards integrating rich shape information is to classify spines into four shape classes reported in literature. This analysis is currently performed manually due to the deficiency of fully automated and reliable tools, which is a time intensive task with subjective results. Availability of automated analysis tools can expedite the analysis process. In this paper, we compare ?1-norm-based sparse representation based classification approach to the least squares method, and the ?2-norm method for dendritic spine classification as well as to a morphological feature-based approach. On a dataset of 242 automatically segmented stubby and mushroom spines, ?1 representation with non-negativity constraint resulted in classification accuracy of 88.02%, which is the highest performance among the techniques considered here. © 2016 IEEE.Article Citation - WoS: 6Citation - Scopus: 8An Evaluation on the Robustness of Five Popular Keypoint Descriptors To Image Modifications Specific To Laser Scanning Microscopy(IEEE-Inst Electrical Electronics Engineers Inc, 2018) Unay, Devrim; Stanciu, Stefan G.Laser scanning microscopy (LSM) techniques are of paramount importance at this time for key domains such as biology, medicine, or materials science. Computer vision methods are instrumental for boosting the potential of LSM, providing reliable results for important tasks, such as image segmentation, registration, classification, or retrieval in a fraction of the time that a human expert would require (at similar or even higher accuracy levels). Image keypoint extraction and description represent essential building blocks of modern computer vision approaches, and the development of such techniques has gained massive interest over the past couple of decades. In this paper, we compare side-by-side five popular keypoint description techniques, scale invariant feature transform (SIFT), speeded-up robust features (SURF), binary robust invariant scalable keypoints (BRISK), fast retina keypoint (FREAK) and BLOCK, with respect to their capacity to represent in a reproducible manner image regions contained in LSM data sets acquired under different acquisition conditions. We evaluate this capacity in terms of descriptor matching performance, using data sets acquired in a principled manner and a thorough Precision-Recall analysis. We identify which of the five evaluated techniques is most robust to specific LSM image modifications associated to the laser beam power, photomultiplier gain, or pixel dwell, and show that certain pre-processing steps have the potential to enhance keypoint matching.Conference Object Citation - WoS: 1Citation - Scopus: 15Blockchain Applications in Healthcare(Institute of Electrical and Electronics Engineers Inc., 2018) Ekin A.; Unay D.In this paper, we present the applications of blockchain technology in healthcare. Furthermore, we evaluate the choice and deployment of Blockchain technology in such applications, review the advantages and disadvantages of such an approach. We review the Estonian system, which is the first blockchain-based health system at the national level, in detail and discuss its ramifications to Turkey. This paper is one of the first papers in this domain and, to the best of authors' knowledge, the first in Turkish. © 2018 IEEE.Conference Object Citation - WoS: 2Citation - Scopus: 3Combining Nonparametric Spatial Context Priors With Nonparametric Shape Priors for Dendritic Spine Segmentation in 2-Photon Microscopy Images(IEEE Computer Society, 2019) Erdil E.; Ozgurargunsah A.; Tasdizen T.; Unay D.; Cetin M.Data driven segmentation is an important initial step of shape prior-based segmentation methods since it is assumed that the data term brings a curve to a plausible level so that shape and data terms can then work together to produce better segmentations. When purely data driven segmentation produces poor results, the final segmentation is generally affected adversely. One challenge faced by many existing data terms is due to the fact that they consider only pixel intensities to decide whether to assign a pixel to the foreground or to the background region. When the distributions of the foreground and back-ground pixel intensities have significant overlap, such data terms become ineffective, as they produce uncertain results for many pixels in a test image. In such cases, using prior information about the spatial context of the object to be segmented together with the data term can bring a curve to a plausible stage, which would then serve as a good initial point to launch shape-based segmentation. In this paper, we propose a new segmentation approach that combines nonparametric context priors with a learned-intensity-based data term and nonparametric shape priors. We perform experiments for dendritic spine segmentation in both 2 D and 3 D 2-photon microscopy images. The experimental results demonstrate that using spatial context priors leads to significant improvements. © 2019 IEEE.Conference Object Citation - WoS: 2Citation - Scopus: 4Deep Learning Based Melanoma Detection From Dermoscopic Images(Institute of Electrical and Electronics Engineers Inc., 2019) Berkay M.; Mergen E.H.; Binici R.C.; Bayhan Y.; Gungor A.; Okur E.; Unay D.; Türkan, MehmetMelanoma which occurs with non-healing DNA degradation in melanocyte cells, is the most deadly type of skin cancers. Importantly, it can be identified for a treatment before it spreads to other tissues, i.e., early diagnosis. To identify, a specialist visually inspects whether the suspected lesion is melanoma or not. However, due to different education and experience levels of specialists or as a result of the patient not being in a facility that is specialized to this area, the problem of 'subjectivity' arises, and a good visual investigation accuracy may not always be achieved. Therefore, there is a significant need for automatic detection tools and systems. In this study, a method based on deep learning for automatic detection of melanoma from dermoscopic images is proposed. The developed system is tested with a large dataset and encouraging results are obtained. © 2019 IEEE.
- «
- 1 (current)
- 2
- 3
- »