WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394
Browse
13 results
Search Results
Conference Object Detection of Variation Instances on Colonoscopy Videos using Structural Similarity Index(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2018) Kacmaz, Rukiye Nur; Yilmaz, BulentThe aim of this study is to reduce the number of images extracted from the videos recorded by the specialists during the colonoscopy process for further examination, thereby enabling the specialist to deal with fewer images. Since the images obtained from the videos are very similar, the main assumption of this study is that the whole video can be represented by fewer images. The approach used in this study is the structural similarity index. Totally, images were obtained from 4 different videos coming from healthy, ulcerative colitis, Crohn's, and polyp patients. The noisy images in these videos were eliminated manually. When the structural similarity index between two consecutive clear images was less than 0.83, the second image was selected and shown to the specialist for his/her examination. By this way, the frames carrying significantly new information from the videos were defined as the variation instances. The tests on healthy or diseased colon videos showed that only 5-10% of the clear images provide significantly new information.Article Citation - WoS: 5Citation - Scopus: 10Three Dimensional Patient-Specific Guides for Guide Pin Positioning in Reverse Shoulder Arthroplasty: An Experimental Study on Different Glenoid Types(Sage Publications Ltd, 2022-01) Sadeghi, Majid Mohammad; Kececi, Emin Faruk; Kapicioglu, Mehmet; Aralasmak, Ayse; Tezgel, Okan; Basaran, Murat Alper; Bilsel, Kerem; Mohammad Sadeghi, MajidIntroduction Incorrect positioning is one of the main factors for glenoid component loosening in reverse shoulder arthroplasty and component placement can be challenging. This study aimed to assess whether Patient-Specific Instrumentation (PSI) provides better guide pin positioning accuracy and is superior to standard guided and freehand instrumentation methods in cases of glenoid bone deformity. Materials and Methods Based on the Walch classification, five different scapula types were acquired by computed tomography (CT). For each type, two different surgeons placed a guide pin into the scapula using three different methods: freehand method, conventional non-patient-specific guide, and PSI guide. Each method was repeated five times by both surgeons. In these experiments, a total of 150 samples of scapula models were used (5 x 2 x 3 x 5 = 150). Post-operative CT scans of the samples with the guide pin were digitally assessed and the accuracy of the pin placement was determined by comparison to the preoperative planning on a three-dimensional (3D) model. Results The PSI method showed accuracies to the preoperative plan of 2.68 (SD 2.10) degrees for version angle (p < .05), 2.59 (SD 2.68) degrees for inclination angle (p < .05), and 1.55 (SD 1.26) mm for entry point offset (p < .05). The mean and standard deviation errors compared to planned values of version angle, inclination angle, and entry point offset were statistically significant for the PSI method for the type C defected glenoid and non-arthritic glenoid. Conclusion Using the PSI guide created by an image processing software tool for guide pin positioning showed advantages in glenoid component positioning over other methods, for defected and intact glenoid types, but correlation with clinical outcomes should be examined.Conference Object Citation - WoS: 1Citation - Scopus: 1Polyp Localization in Colonoscopy Images Using Vessel Density(Institute of Electrical and Electronics Engineers Inc., 2018-11) Doǧan, Refika Sultan; Yilmaz, BulentIn this paper, we present a new approach for polyp localization in colonoscopy images. This approach is based on the determination of the polyp location using the vessel density in colon images. Primarily, we used pre-processing procedures on the colon images, and then blood vessel extraction techniques were employed. Later, segmentation of the vessel boundaries was performed. With the help of vessel boundaries we calculated the vessel density, and used this for the localization of the polyps. We tested the success of this approach using a publicly available image set (CVC-ClinicDB database). This database consisted of 612 images from 29 different polyps. This approach succeeds in correct detection of 24 out of 29 different polyps. © 2019 Elsevier B.V., All rights reserved.Article Citation - WoS: 1Motion Artifact Detection in Colonoscopy Images(Sciendo, 2018-07-01) Kacmaz, Rukiye Nur; Yilmaz, Bulent; Dundar, Mehmet Sait; Dogan, SerkanComputer-aided detection is an integral part of medical image evaluation process because examination of each image takes a long time and generally experts' do not have enough time for the elimination of images with motion artifact (blurred images). Computer-aided detection is required for both increasing accuracy rate and saving experts' time. Large intestine does not have straight structure thus camera of the colonoscopy should be moved continuously to examine inside of the large intestine and this movement causes motion artifact on colonoscopy images. In this study, images were selected from open-source colonoscopy videos and obtained at Kayseri Training and Research Hospital. Totally 100 images were analyzed half of which were clear. Firstly, a modified version of histogram equalization was applied in the pre-processing step to all images in our dataset, and then, used Laplacian, wavelet transform (WT), and discrete cosine transform-based (DCT) approaches to extract features for the discrimination of images with no artifact (clear) and images with motion artifact. The Laplacian-based feature extraction method was used for the first time in the literature on colonoscopy images. The comparison between Laplacian-based features and previously used methods such as WT and DCT has been performed. In the classification phase of our study, support vector machines (SVM), linear discriminant analysis (LDA), and k nearest neighbors (k-NN) were used as the classifiers. The results showed that Laplacian-based features were more successful in the detection of images with motion artifact when compared to popular methods used in the literature. As a result, a combination of features extracted using already existing approaches (WT and DCT) and the Laplacian-based methods reached 85% accuracy levels with SVM classification approach.Article Citation - WoS: 2Citation - Scopus: 3Magnetic Separation of Micro Beads and Cells on a Paper-Based Lateral Flow System(Gazi Univ, 2023-12-01) Farooqi, Muhammed Fuad; Icoz, KutayPaper based lateral flow systems are widely used biosensor platforms to detect biomolecules in a liquid sample. Proteins, bacteria, oligonucleotides, and nanoparticles were investigated in the literature. In this work we designed a magnetic platform including dual magnets and tested the flow of micron size immunomagnetic particles alone and when loaded with cells on two different types of papers. The prewetting conditions of the paper and the applied external magnetic field are the two dominant factors affecting the particle and cell transport in paper. The images recorded with a cell phone, or with a bright field optical microscope were analyzed to measure the flow of particles and cells. The effect of prewetting conditions and magnetic force were measured, and it was shown that in the worst case, minimum 90% of the introduced cells reached to the edge of the paper. The paper based magnetophoretic lateral flow systems can be used for cell assays.Article Citation - WoS: 14Citation - Scopus: 15Image-Analysis Based Readout Method for Biochip: Automated Quantification of Immunomagnetic Beads, Micropads and Patient Leukemia Cell(Pergamon-Elsevier Science Ltd, 2020-06) Uslu, Fatma; Icoz, Kutay; Tasdemir, Kasim; Dogan, Refika S.; Yilmaz, BulentFor diagnosing and monitoring the progress of cancer, detection and quantification of tumor cells is utmost important. Beside standard bench top instruments, several biochip-based methods have been developed for this purpose. Our biochip design incorporates micron size immunomagnetic beads together with micropad arrays, thus requires automated detection and quantification of not only cells but also the micropads and the immunomagnetic beads. The main purpose of the biochip is to capture target cells having different antigens simultaneously. In this proposed study, a digital image processing-based method to quantify the leukemia cells, immunomagnetic beads and micropads was developed as a readout method for the biochip. Color, size-based object detection and object segmentation methods were implemented to detect structures in the images acquired from the biochip by a bright field optical microscope. It has been shown that manual counting and flow cytometry results are in good agreement with the developed automated counting. Average precision is 85 % and average error rate is 13 % for all images of patient samples, average precision is 99 % and average error rate is 1% for cell culture images. With the optimized micropad size, proposed method can reach up to 95 % precision rate for patient samples with an execution time of 90 s per image.Article Citation - WoS: 5Citation - Scopus: 9Image Processing and Cell Phone Microscopy to Analyze the Immunomagnetic Beads on Micro-Contact Printed Gratings(MDPI Ag, 2016-09-28) Icoz, KutayIn this paper we report an ultra-low-cost spherical ball lens based cell phone microscopy and image processing algorithms to analyze the amount of immunomagnetic beads on micro-contact printed gratings. The spherical ball lens provides approximately 100x magnification but the recorded images are not clear and are noisy. By using the image-processing algorithms, the noise can be reduced and the images can be enhanced to quantify the amount of immunomagnetic beads on micro-contact printed lines. This method, which is portable and low-cost, can be an alternative read out mechanism for biosensing applications using immunomagnetic beads on micro-contact printed surface receptors. Further, 0.0335 mg/mL was the lowest magnetic bead concentration that could be detected above the inherent noise level of the spherical ball lens.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.Article Citation - WoS: 7Citation - Scopus: 5Effect of Interpolation on Specular Reflections in Texture-Based Automatic Colonic Polyp Detection(Wiley, 2020-06-26) Kacmaz, Rukiye Nur; Yilmaz, Bulent; Aydin, ZaferReflections of LED light cause unwanted noise effects called specular reflection (SR) on colonoscopic images. The aim of this study was to seek answers to the following two questions. (a) How are the texture features used in automatic detection of polyps affected by the interpolation on specular reflections? (b) If they are affected does it really affect the classification performance? In order to answer these questions, we used 610 colonoscopy images, and divided each image into tiles whose sizes were 32-by-32 pixels. From these tiles, we selected the ones without any specular reflection. We added different shape and size specular reflections cropped from real images onto the reflection-free tiles. We then used the nearest neighbors, bilinear and bicubic interpolation techniques on the tiles on which SRs were added. On these tiles we extracted 116 texture features using 3 second-order approaches, and 4 first-order statistics. First, we used paired samplettest. Second, we performed automatic classification of polyps and background using random forest and k nearest neighbors (k-NN) approaches using the texture features for different combinations of specular reflections added on the tiles from the polyp or background. The results showed that depending on the size of specular reflection, interpolation can cause a significant difference between the texture features that were coming from reflection-free tiles and the same tiles on which interpolation was performed. In addition, we note that bicubic interpolation may be preferred to eliminate specular reflection when texture features are used for background and polyp discrimination.Article Citation - WoS: 2Citation - Scopus: 3A Comprehensive Study on Automatic Non-Informative Frame Detection in Colonoscopy Videos(Wiley, 2024-01) Kacmaz, Rukiye Nur; Dogan, Refika Sultan; Yilmaz, BuelentDespite today's developing healthcare technology, conventional colonoscopy is still a gold-standard method to detect colon abnormalities. Due to the folded structure of the intestine and visual disturbances caused by artifacts, it can be hard for specialists to detect abnormalities during the procedure. Frames that include artifacts such as specular reflection, improper contrast levels from insufficient or excessive illumination gastric juice, bubbles, or residuals should be detected to increase an accurate diagnosis rate. In this work, both conventional machine learning and transfer learning methods have been used to detect non-informative frames in colonoscopy videos. The conventional machine learning part consists of 5 different types of texture features, which are gray level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), neighborhood gray-tone difference matrix (NGTDM), focus measure operators (FMOs), and first-order statistics. In addition to these methods, we utilized 8 different transfer learning models: AlexNet, SqueezeNet, GoogleNet, ShuffleNet, ResNet50, ResNet18, NasNetMobile, and MobileNet. The results showed that FMOs and decision tree combination gave the best accuracy and f-measure values with almost 89% and 0.79%, respectively, for the conventional machine learning part. When the transfer learning part is taken into account, AlexNet (99.85%) and SqueezeNet (98.80%) have the highest performance metric results. This study shows the potential of both transfer learning and conventional machine learning algorithms to provide fast and accurate non-informative frame detection to be used during a colonoscopy, which may be considered the initial step in identifying and classifying colon-related diseases automatically to help guide physicians.