Browsing by Author "Aksahin, Mehmet Feyzi"

Now showing 1 - 18 of 18

Automatic Brain Tissue Segmentation on TOF MRA Image
(2020) Ozen, Sinasi Kutay; Aksahin, Mehmet Feyzi
For the segmentation of brain vessels from MRA images, brain tissue is used in the head, eye, skull, etc. must be separated from the structures. For this reason, studies are carried out for the segmentation of brain tissue. In this study, the method that automatically segregates brain tissue from magnetic resonance angiography images taken with time of flight (TOF) technique is presented. The method in the study consists of live steps. First of all, the tip contrast values in the image are filtered by anisotropic diffusion filtering method. Parameters of anisotropic diffusion method are determined automatically by the natural image quality evaluator method. Sudden density transitions arc detected by applying LoG edge detection filter on the filtered image. It is made ready for image analysis by applying etching on the image with density transitions. According to the conditions determined in image analysis, brain tissue is obtained separated from other head structures. As a result of this study, an easy-to-apply, fast-delivering, high-accuracy automatic algorithm has been introduced.
Automatic Glacoma Detection Using Whale Optimization and Support Vector Machines
(2022) Ozen, Sinasi Kutay; Aksahin, Mehmet Feyzi
Glaucoma is among the most common causes of permanent blindness in humans. The mass screening will aid in early diagnosis in a large population, as the initial symptoms are not obvious. This type of mass screening requires an automated diagnostic technique. Our proposed automation extracts feature by obtaining disk-to-cup ratio by applying histogram equalization, median filter, otsu thresholding, and whale optimization algorithm, respectively, on the optic disc region obtained by preprocessing. In addition, the optic disc circumference, optic disc area, optic cup circumference, and optic cup area values obtained from the optic disc region are given to the support vector machine model together with the cup-disc ratio, and glaucoma detection is made automatically. The proposed system has been validated on a real ophthalmological images of both normal and glaucoma cases. The results show the effectiveness of the proposed method when compared with other existing systems.
Brain tumor prediction on MR images with semantic segmentation by using deep learning network and 3D imaging of tumor region
(2021) Karayegen, Gokay; Aksahin, Mehmet Feyzi; 0000-0001-6294-9279
When it comes to medical image segmentation on brain MR images, using deep learning techniques has a significant impact to predict tumor existence. Manual segmentation of a brain tumor is a time-consuming task and depends on knowledge and experience of physicians. In this paper, we present a semantic segmentation method by utilizing convolutional neural network to automatically segment brain tumor on 3D Brain Tumor Segmentation (BraTS) image data sets that comprise four different imaging modalities (T1, T1C, T2 and Flair). In addition, our study includes 3D imaging of whole brain and comparison between ground truth and predicted labels in 3D. In order to obtain exact tumor region and dimensions such as height, width and depth, this method was successfully applied and images were displayed different planes including sagittal, coronal and axial. Evaluation results of semantic segmentation which was executed by a deep learning network are significantly promising in terms of tumor prediction. Mean prediction ratio was determined as 91.718. Mean IoU (Intersection over Union) and Mean BF score were calculated as 86.946 and 92.938, respectively. Finally, dice scores of the test images were showed significant similarity between ground truth and predicted labels. As a result, both semantic segmentation metrics and 3D imaging can be interpreted as meaningful for diagnosing brain tumor accurately.
Brain Tumor Prediction with Deep Learning and Tumor Volume Calculation
(2021) Karayegen, Gokay; Aksahin, Mehmet Feyzi
Classification of Heart Sound Recordings With Continuous Wavelet Transform Based Algorithm
(2018) Karaca, Busra Kubra; Oltu, Burcu; Kantar, Tugce; Kilic, Erkin; Aksahin, Mehmet Feyzi; Erdamar, Aykut
Cardiovascular diseases are the major cause of death in the world. Early diagnosis of heart diseases provide an effective treatment. Heart diseases can be diagnosed using data obtained from heart sounds. Heart sounds are listened by a physician with auscultation method and the disease diagnosis can vary depending on the physician's experience and hearing ability. For this reason, automatic detection of anomalies in heart sounds can give more objective results. In this study, features were obtained by processing phonocardiogram signals taken from Physionet database. The heart sounds are classified as normal and abnormal using these features and the k - nearest neighbor method. As a result, sensitivity, specificity and accuracy were determined as 100%, 96.1% and 98.2%, respectively.
Classification of Sleep Apnea by Photoplethysmography Signal
(2018) Aksahin, Mehmet Feyzi; Karaca, Busra Kubra; Oltu, Burcu
Sleep apnea is a very common respiratory disorder in the community that includes a range from upper airway obstruction to respiratory abnormalities and the absence of a breathing effort, which can lower people's standard of living and even cause death. Therefore, the sleep apnea needs to be diagnosed in a practical way and with high accuracy. The diagnosis of apnea is made by recording the physiological parameters of the patient with polysomnography (PSG) method and by examination of these parameters by specialist physicians, but it is a tedious and time consuming process. In order to simplify the apnea diagnosis process, phospletismography (PPG) signals are used instead of PSG records. PPG signals are suitable for diagnosis of apnea because they reflect changes in respiration. In the proposed study, a decision support system was developed to automatically diagnose apnea and to make apnea diagnosis easier and more objective using PPG signals. In the decision support system, the peaks of the PPG signal were determined and the heart rate variability (HRV) vector was generated depending on the time difference between these peaks. The mean and standard deviation values of the generated vector are determined as features for each epoch. The presence of the apnea at each epoch is classified using "Subspace K Nearest Neighbor (Subspace KNN)" and specified features. The "Subspace KNN" classifier was trained with 85% accuracy and then system was tested. As a result, sensitivity, accuracy and specificity rates were calculated as 91%, 95% and 90% respectively.
Detection of Epilepsy Disease From EEG Signals With Artificial Neural Networks
(2016) Ozkan, Cansu; Dogan, Seda; Kantar, Tugce; Aksahin, Mehmet Feyzi; Erdamar, Aykut; 0000-0001-8588-480X; AAA-6844-2019
The diagnosis of the epilepsy diseases are made by physicians with analyzing the electroencephalography (EEG) records. The epilepsy diseases can be determined with observing the main properties of before and on-time seizure signals in time and frequency domain. Physicians are evaluating the results after some necessary scoring on EEG records. However, this evaluation is specialistic, time consuming processes and also may subjective results. At this point, to allow detection of epilepsy diseases, a decision support system can give more objective results to the physicians for diagnosing. The subject of the study is automatically diagnosing the epilepsy diseases on EEG signals. In the proposed study, analyses of EEG signals in time and frequency domain were done and features of diseases were obtained. As a result, using artificial neural network (ANN) and obtained features, a decision support system is realized to diagnose the epilepsy. The specificity and the sensitivity of the algorithm are 94% and 66% respectively.
Detection of Hypopnea Using Respiratory Signals
(2019) Oktan, Aynur Didem; Aksahin, Mehmet Feyzi
Hypopnea is a respiratory disorder that affects people's sleep quality and reduces their standard of living. Detection and treatment of sleep disorders are costly. It requires time and effort. Because patients have to spend their time with special systems in which their physiological signals are recorded and specialist personnel in their sleep laboratories. Polysomnograms should be analyzed by medical doctors every night. Reliable sleep stage scoring is done manually by experts. This means that each morning, a specialist visually analyzes the 960 period of an eight-hour polysomnogram to create a hypnogram. This requires a long time. In this study, a method for automatic detection of hypopnea by eliminating the effect of the doctor is proposed. In this method, epoxes were scored by using air flow, thorax and abdominal amplitude information obtained from the person. A training data was created using hypopnea and normal epochs and grading was performed using the determined attributes. Quadratic Support Vector Machines (SVM) gave the highest accuracy when determining the presence of hypopnea. The linear DVM method was trained in 90.6% accuracy and the system was then tested. It was found that hioped epochs can be detected with 90% sensitivity.
Detection of Multiple Sclerosis Disease by EEG Coherence Analysis
(2019) Karaca, Busra Kubra; Aksahin, Mehmet Feyzi; Ocal, Ruhsen; V-3553-2017
Multiple sclerosis (MS) is a chronic and inflammatory disease affecting the brain and spinal cord. Although the exact cause of MS is not known, genetic, environmental and immunological factors are involved in the etiology of the disease. The lack of a single diagnostic test for early diagnosis of MS and the similarity of clinical features in MS to other diseases is a serious problem. Early detection of MS is important, and therefore a rapid and reliable pre-diagnosis of MS is important for the treatment and prognosis of the disease. Electroencephalography (EEG) signals provide important information about brain and nerve diseases. Therefore, in the proposed study, a decision support system has been developed which will contribute to the pre-diagnosis by using EEG signals. In this context, coherence analysis of bipolar channel pairs of EEG signals obtained from MS patients and healthy individuals was performed and feature extraction was performed from certain frequency bands. Using the obtained features, the "Subspace Discriminant" classifier was trained with 95.8% accuracy and then the system was tested. As a result, accuracy, sensitivity and specificity rates were 91.67%, 85.71% and 100%, respectively.
Detection of multiple sclerosis from photic stimulation EEG signals
(2021) Karaca, Busra Kubra; Aksahin, Mehmet Feyzi; Ocal, Ruhsen
Background: Multiple Sclerosis (MS) is characterized as a chronic, autoimmune and inflammatory disease of the central nervous system. Early diagnosis of MS is of great importance for the treatment and course of the disease. In addition to the many methods, cost-effective and non-invasive electroencephalogram signals may contribute to the pre-diagnosis of MS. Objectives: The aim of this paper is to classify male subjects who have MS and who are healthy control using photic stimulation electroencephalogram signals. Methods: Firstly the continuous wavelet transformation (CWT) method was applied to electroencephalogram signals under photic stimulation with 5Hz, 10Hz, 15Hz, 20Hz, and 25Hz frequencies. The sum, maximum, minimum and standard deviation values of absolute CWT coefficients, corresponding to "1-4 Hz" and "4-13 Hz" frequency ranges, were extracted in each stimulation frequency region. The ratios of these values obtained from the frequency ranges "1-4Hz" and "4-13Hz" was decided as features. Finally, various machine learning classifiers were evaluated to test the effectivity of determined features. Results: Consequently, the overall accuracy, sensitivity, specificity and positive predictive value of the proposed algorithm were 80 %, 72.7 %, 88.9 %, and 88.9 %, respectively by using the Ensemble Subspace k-NN classifier algorithm. Conclusions: The results showed how photic stimulation electroencephalogram signals can contribute to the prediagnosis of MS.
Heart sound recording and automatic S1-S2 waves detecting system design
(2020) Aksahin, Mehmet Feyzi; Oltu, Burcu; Karaca, Busra Kubra
The second leading cause of death in the world is cardiovascular diseases. Diagnosis of vast majority of cardiovascular diseases is made by listening to heart sounds by specialists (auscultation method). However, since the method of auscultation depends on the experience and hearing ability of the specialist, obtained results can be subjective. Therefore, digitization and visualization of heart sounds enables accurate, rapid and economical diagnosis of cardiovascular diseases, especially heart valve diseases. For this purpose, a device prototype that collects the heart sound from human body and also amplifies, filters, displays and records collected data on digital environment was designed in the first part of this study. In order to test the working accuracy of the designed device, clinical applications were carried out with the permission of the ethics committee and as the result of this application 15 heart sound recordings from 5 different disease groups(mitral insufficiency, mitral-aortic insufficiency, mitral-tricuspid insufficiency, mitral-aortic tricuspid insufficiency and healthy heart sound recordings) were collected.and obtained recordings were examined. The most effective parameter for the diagnosis of heart valve diseases is the location of the S1-S2 heart sounds. For this reason, in the second part of the study, a medical decision support system was established to detect the S1-S2 locations to assist physicians in their diagnosis. In this context, heart sounds are first filtered by discrete wavelet transform. Then, the S1-S2 waves in the filtered signal are made evident by the teager energy operator and rule-based algorithm. As a result, S1-S2 locations in normal and pathological data were detected with 98.67% sensitivity, 97.69% specificity and 98.18% accuracy.
Idfatification Using FCG Signals
(2020) Kilicer, Elif Cansu; Ay, Sevval; Aksahin, Mehmet Feyzi
Systems that determine identity with individual features are called biometric systems. Today, voice, fingerprint, retina/iris, and facial recognition systems are some of the biometric identification methods. These methods have become replicable with the advancement of technology. Accordingly, Electrocardiogram (ECG) signals are universal, unique, easy to measure, and can only be obtained from living people. For this reason, it can be accepted that ECG is an effective method that can he used to prevent counterfeiting among biometric identification methods. In this study, an algorithm that can make identification via ECG is proposed. Within the scope of the study, the time and time-frequency domain analyzes of the ECG signals obtained from the PhsiyoNet database are performed then various features are determined. These determined features were classified using machine learning methods. The performance of the developed algorithm has been calculated as 100% accuracy, 1000/0 specificity, and 100% sensitivity.
Multi-scale classification of single-cell gel electrophoresis assay using deep learning algorithm
(2020) Erdamar, Aykut; Aksahin, Mehmet Feyzi; 0000-0001-8588-480X; AAA-6844-2019
Structural and functional integrity of deoxyribonucleic acid (DNA) is crucial for the maintenance of hereditary information. However, by-products of cellular metabolism and physical or chemical factors may cause spontaneous DNA damage. The alkaline single-cell gel electrophoresis or comet assay analysis is an easy and reliable method for the determination genotoxic effects of chemical and physical factors. Simply, it is the electrophoretic analysis of intact damaged DNA of a single cell on in a thin layer of agarose gel. The quantitative analysis of the comet assay images is performed manually by an expert researcher. In visual scoring, DNA nuclei are scored as 0, 1, 2, 3, and 4; and the correct scoring is crucial for the determination of the DNA damage. However, visual scoring depends on the professional experience of the researcher and it is a time consuming and exhausting task. Therefore, this evaluation is inevitable to have subjective results. To avoid this subjectivity and to show the effectiveness of deep learning algorithm on cell images, a Convolution Neural Network (CNN) based deep learning method is proposed to classify comet assay images. According to the results, CNN is trained and tested with high accuracy. The results show that CNN algorithm can successfully classify five different scores of comet assay images, and these results can also reduce the subjectivity. (C) 2019 Elsevier Ltd. All rights reserved.
Neurofeedback System Design Based On Discrete Wavelet Transform
(2018) Ozen, Sinasi Kutay; Aksahin, Mehmet Feyzi
Neurofeedback is a learning strategy that helps to alter brain waves called electroencephalography (EEG). Neurofeedback technique is used in the treatment of various diseases such as epilepsy, sleep disorders, attention deficit and learning disability. In the first stage of this study, a device was developed in which the EEG signals are collected and transferred to the computer. In the second stage of the study, the obtained EEG signals were analyzed by the discrete wavelet transform method, and according to the analysis result, a system was designed by which the patients could be treated using visual feedback. The usability of the visual feedback part based on theta/ beta protocol with EEG subbands has been tested in real time.
A novel electroencephalography based approach for Alzheimer's disease and mild cognitive impairment detection
(2021) Oltu, Burcu; Aksahin, Mehmet Feyzi; Kibaroglu, Seda; 0000-0002-3964-268X; AAJ-2956-2021
Background and objective: Alzheimer's disease (AD) is characterized by cognitive, behavioral and intellectual deficits. The term mild cognitive impairment (MCI) is used to describe individuals whose cognitive impairment departing from their expectations for the age that does not interfere with daily activities. To diagnose these disorders, a combination of time-consuming, expensive tests that has difficulties for the target population are evaluated, moreover, the evaluation may yield subjective results. In the presented study, a novel methodology is developed for the automatic detection of AD and MCI using EEG signals. Methods: This study analyzed the EEGs of 35 subjects (16 MCI, 8 AD, 11 healthy control) with the developed algorithm. The algorithm consists of 3 methods for analysis, discrete wavelet transform(DWT), power spectral density (PSD) and coherence. In the first approach, DWT is applied to the signals to obtain major EEG sub-bands, afterward, PSD of each sub-band is calculated using Burg's method. In the second approach, interhemispheric coherence values are calculated. The variance and amplitude summation of each sub-bands' PSD and the amplitude summation of the coherence values corresponding to the major sub-bands are determined as features. Bagged Trees is selected as a classifier among the other tested classification algorithms. Data set is used to train the classifier with 5-fold cross-validation. Results: As a result, accuracy, sensitivity, and specificity of 96.5%, 96.21%, 97.96% are achieved respectively. Conclusion: In this study, we have investigated whether EEG can provide efficient clues about the neuropathology of Alzheimer's Disease and mild cognitive impairment for early and accurate diagnosis. Accordingly, a decision support system that produces reproducible and objective results with high accuracy is developed.
Quantitative sleep EEG synchronization analysis for automatic arousals detection
(2020) Erdamar, Aykut; Aksahin, Mehmet Feyzi; 0000-0001-8588-480X; AAA-6844-2019
Background and objective: Electroencephalographic arousals are considered to be the main reason for the interruption of sleep and are visually examined by sleep physicians. Visual scoring of all-night recordings has inter-scorer variability which may lead to subjective results. Hence, we aimed to develop a novel automated method to detect arousals from two electroencephalographic channels in terms of the synchronic events of the right and left hemispheres. Methods: In the context of the occurrence of arousal pattern, the relationship between two synchronic C3-A2 and C4-A1 channels were quantified using by coherence spectrum and mutual information. The power and the ratio values of the sub-bands of the coherence spectrum were selected as the five features. Furthermore, the mutual information value was determined as the sixth feature. The automatic detection performance was evaluated using six features and machine learning techniques, on five different patients' whole-night electroencephalography recordings. The presented method does not include any signal conditioning, pre-processing steps, any manual involvement, meta-rule-based approaches, and some empirical thresholds. Results: The significant increases were found in sub-bands of the coherence spectrum in case of arousal. Moreover, the mutual information of these channels was distinctive during the arousal state. Consequently, the overall accuracy, sensitivity, specificity, and PPV values were achieved as 99.5 %, 99.8 %, 99.6 %, and 99.3 %, respectively with using ensemble bagged tree. Conclusion: The novelty of the present study is the practical determination of the relationship between electroencephalographic synchronization and the occurrence of the arousals between the central regions of the right and left hemispheres. (C) 2020 Elsevier Ltd. All rights reserved.
Sleep Apnea Detection Using Blood Pressure Signal
(2018) Aksahin, Mehmet Feyzi; Oltu, Burcu; Karaca, Busra Kubra
Sleep apnea is a common respiratory disease. Apnea affects sleep quality, reduces people's life standards, and it can result in death at advanced stage. Therefore the ability to detect the apnea quickly and accurately is important for the treatment of this disease. Apnea is diagnosed by specialists however this is a long and exhausting process. Accordingly, a decision support system that automatically diagnoses apnea has been developed to facilitate this process and make it more objective. The developed decision support system in this study is based on patient's blood pressure signals instead of traditional Polysomnography (PSG) records, which requires various physiological signals measured from the patients. In the examined blood pressure signals, the change that results from each heart beat was determined and heart rate variability (HRV) was calculated based on these changes. At the same time, maximum and minimum amplitude values were found for each change period and amplitude variability vector was created. The features for each epoch were determined using the generated amplitude variability vector and HRV data. Presence of apnea in each epoch is classified with determined features and with the use of "Quadratic SVM" classifier. The Quadratic SVM classifier was trained with 87.5% accuracy and then the system is tested. As a result 75.4% sensitivity and 75% positive predictive values were obtained.
Sleep Apnea Detection Using With EEG, ECG and Respiratory Signals
(2017) Aksahin, Mehmet Feyzi; Erdamar, Aykut; Isik, Atakan; Karaduman, Asena; 0000-0001-8588-480X; AAA-6844-2019
Sleep apnea is one of the major sleep disorders of today. The diagnosis of sleep apnea is performed by specialist physicians. This siruation extends the duration of the diagnosis. To shorten this period and at the same time to avoid the mistakes that may occur in diagnosis, an automated decision support system has been considered in the diagnosis and classification of sleep apnea. In this study, ECG signal was analyzed to obtain Heart Rate Variability (HRV) signal and the power spectral density (PSD) of this signal was examined. It has been observed that the low and high frequency energy ratios are different in the PSD of examined HRV. Parallel to this analysis, the energy of the respiratory signal is obtained and it is understood that there is a significant energy exchange in the apnea cases. However, the powers of the frequency bands in the EEG signal were found separately and the ratios of these bands to each other were calculated. In the analysis, it was observed that the ratios of and non-apnea periods. By using these differences, an artificial neural network (ANN) algorithm is constructed to diagnose and classify the sleep apnea. This algorithm was tested on two patient data; ANN was trained and tested separately for each patient. As a result, it was determined that the average accuracy rate of ANN is high.