Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299225
Duygu Degirmenci, Melike Yalcin, Mehmet Akif Ozdemir, A. Akan
Time-frequency representation (TFR) provides a good analysis for periodic signals; however, they are insufficient for nonstationary signals. The synchrosqueezing transform (SST) provides a strong analysis of nonstationary signals. The signal has different synchrosqueezing transformations that are implemented using different TFR. This paper provides a review of the different SST methods implemented using different TFR available in the literature, a comparison of these, and their use with different techniques in biomedical signal processing applications. Adding different techniques to the applied SST method affects the signal processing and classification ability of the selected SST method.
{"title":"Synchrosqueezing Transform in Biomedical Applications: A mini review","authors":"Duygu Degirmenci, Melike Yalcin, Mehmet Akif Ozdemir, A. Akan","doi":"10.1109/TIPTEKNO50054.2020.9299225","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299225","url":null,"abstract":"Time-frequency representation (TFR) provides a good analysis for periodic signals; however, they are insufficient for nonstationary signals. The synchrosqueezing transform (SST) provides a strong analysis of nonstationary signals. The signal has different synchrosqueezing transformations that are implemented using different TFR. This paper provides a review of the different SST methods implemented using different TFR available in the literature, a comparison of these, and their use with different techniques in biomedical signal processing applications. Adding different techniques to the applied SST method affects the signal processing and classification ability of the selected SST method.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132351225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299299
S. Kbah, N. Sengor
The effect of network connections on the synchronization is an area of interest in different disciplines. Several well-known methods have been developed as Kuramoto model. Recently, the relations between synchronization in the cortex and cognitive processes as selective attention, perception begin to draw attention in computational neuroscience. Also, there are works focusing on the relation between neurodegenerative diseases and synchronization in the cortex. Here, we focused on the role of connection sparseness in the cortex. To investigate the effect of sparseness, we built networks inspired by the structure of the cortex using Izhikevich Neuron model.
{"title":"Neuronal Synchronization and The Sparseness of The Cortico-cortical Connections","authors":"S. Kbah, N. Sengor","doi":"10.1109/TIPTEKNO50054.2020.9299299","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299299","url":null,"abstract":"The effect of network connections on the synchronization is an area of interest in different disciplines. Several well-known methods have been developed as Kuramoto model. Recently, the relations between synchronization in the cortex and cognitive processes as selective attention, perception begin to draw attention in computational neuroscience. Also, there are works focusing on the relation between neurodegenerative diseases and synchronization in the cortex. Here, we focused on the role of connection sparseness in the cortex. To investigate the effect of sparseness, we built networks inspired by the structure of the cortex using Izhikevich Neuron model.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133167078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299311
Muharrem Çelebi
Nowadays, due to the rapid development of digital platforms, digital signal processing has become realizable into small size processors. The purpose of this study is to test the filtering process on both PC-based platform and embedded system. The first goal of this study is to compare the results of the filtering process obtained in MATLAB and ARDUINO environments. For the second purpose, filtering process will be tried in real-time on ARDUINO platform with the produced filter coefficients. Findings obtained as a result of the study are presented and discussed.
{"title":"Digital Filter Design Based on ARDUINO and Its Applications","authors":"Muharrem Çelebi","doi":"10.1109/TIPTEKNO50054.2020.9299311","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299311","url":null,"abstract":"Nowadays, due to the rapid development of digital platforms, digital signal processing has become realizable into small size processors. The purpose of this study is to test the filtering process on both PC-based platform and embedded system. The first goal of this study is to compare the results of the filtering process obtained in MATLAB and ARDUINO environments. For the second purpose, filtering process will be tried in real-time on ARDUINO platform with the produced filter coefficients. Findings obtained as a result of the study are presented and discussed.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"593 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114003459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299233
Begüm Erkal, S. Başak, Alper Çiloğlu, Duygu Dede Sener
Brain cancer is one the most important disease to be treated all around the world. Classification of brain cancer using machine learning techniques has been widely studied by researchers. Microarray gene expression data are commonly used medical data to get observable results in this manner. In this study, multiclass classification of brain cancer is aimed by using different machine learning approaches. Some preprocessing methods were applied to get improved results. According to the result, feature selection has greatly affected the overall performance of each method in terms of overall accuracy and per class accuracy. Experimental results show that Multilayer Perceptron (MP) method has higher accuracy rate compared with other machine learning methods.
{"title":"Multiclass Classification of Brain Cancer with Machine Learning Algorithms","authors":"Begüm Erkal, S. Başak, Alper Çiloğlu, Duygu Dede Sener","doi":"10.1109/TIPTEKNO50054.2020.9299233","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299233","url":null,"abstract":"Brain cancer is one the most important disease to be treated all around the world. Classification of brain cancer using machine learning techniques has been widely studied by researchers. Microarray gene expression data are commonly used medical data to get observable results in this manner. In this study, multiclass classification of brain cancer is aimed by using different machine learning approaches. Some preprocessing methods were applied to get improved results. According to the result, feature selection has greatly affected the overall performance of each method in terms of overall accuracy and per class accuracy. Experimental results show that Multilayer Perceptron (MP) method has higher accuracy rate compared with other machine learning methods.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"33 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113938472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299265
H. Durmuş, Emel Çetin Ari, B. Karaböce, MirHasan Seyitsoy
In this study, the temperature effects created by the IPL light source (epilation device) applied by a commercial epilation device at regular intervals on four thermocouples placed 15 mm inside the agar phantom were investigated at five different power levels designed for different skin tones of the device. The determined temperatures have been found to be safe for human use.
{"title":"Investigation of Temperature Effects Produced by an Epilation Device Within Agar Phantom","authors":"H. Durmuş, Emel Çetin Ari, B. Karaböce, MirHasan Seyitsoy","doi":"10.1109/TIPTEKNO50054.2020.9299265","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299265","url":null,"abstract":"In this study, the temperature effects created by the IPL light source (epilation device) applied by a commercial epilation device at regular intervals on four thermocouples placed 15 mm inside the agar phantom were investigated at five different power levels designed for different skin tones of the device. The determined temperatures have been found to be safe for human use.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121477807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299253
B. Erk, Öykü Kabar, Hilal Er, Emel Bakay, Yeşim BÜYÜKSöKMEN, D. Karaman, N. Topaloglu
The discovery of the antibiotics is considered as a major development for the medical world from past to present. However, today due to the unnecessary and wrong use of antibiotics, most pathogenic bacteria have gained resistance to them. Methicillin Resistant Staphylococcus aureus (MRSA), one of the most common types of drug resistant bacteria, causes serious diseases such as hospital infections, and it is difficult to treat the disease with its resistance mechanism. Therefore, new searches for treatment have emerged to prevent infections caused by drug resistant bacteria. One of these new alternative treatments is antibacterial photothermal therapy, which will be supported by the use of nanoparticles in photothermal therapy. In this study, photothermal therapy was performed using zinc oxide (ZnO) nanoparticles which are known to have an antibacterial effect. ZnO concentrations for the applications performed were 100 ×g/ml and 250 ×g/ml. Light applications were carried out with a diode laser with 808-nm of wavelength using various output powers (1, 2, and 2.3 W) and energy densities (42.3, 100, 250, and 600 J/cm2) in the presence of both determined concentrations. The most effective result was more than 99.99% bacterial cell death when the concentration of 250 ×g/ml ZnO was applied with 2.3 W output power and 600 J/cm2 energy density. As a result of this study, it is thought that photothermal therapy in the presence of ZnO nanoparticles has great promise in the treatment of infections caused by antibiotic resistant strains when appropriate parameters are provided.
{"title":"The Effect of Zinc Oxide Nanoparticles in Antibacterial Photothermal Therapy against MRSA","authors":"B. Erk, Öykü Kabar, Hilal Er, Emel Bakay, Yeşim BÜYÜKSöKMEN, D. Karaman, N. Topaloglu","doi":"10.1109/TIPTEKNO50054.2020.9299253","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299253","url":null,"abstract":"The discovery of the antibiotics is considered as a major development for the medical world from past to present. However, today due to the unnecessary and wrong use of antibiotics, most pathogenic bacteria have gained resistance to them. Methicillin Resistant Staphylococcus aureus (MRSA), one of the most common types of drug resistant bacteria, causes serious diseases such as hospital infections, and it is difficult to treat the disease with its resistance mechanism. Therefore, new searches for treatment have emerged to prevent infections caused by drug resistant bacteria. One of these new alternative treatments is antibacterial photothermal therapy, which will be supported by the use of nanoparticles in photothermal therapy. In this study, photothermal therapy was performed using zinc oxide (ZnO) nanoparticles which are known to have an antibacterial effect. ZnO concentrations for the applications performed were 100 ×g/ml and 250 ×g/ml. Light applications were carried out with a diode laser with 808-nm of wavelength using various output powers (1, 2, and 2.3 W) and energy densities (42.3, 100, 250, and 600 J/cm2) in the presence of both determined concentrations. The most effective result was more than 99.99% bacterial cell death when the concentration of 250 ×g/ml ZnO was applied with 2.3 W output power and 600 J/cm2 energy density. As a result of this study, it is thought that photothermal therapy in the presence of ZnO nanoparticles has great promise in the treatment of infections caused by antibiotic resistant strains when appropriate parameters are provided.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122817806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299263
Gülşah Sunal, Günnur Onak, Oğuzhan Gökmen, Ilayda Namli, O. Karaman
Cartilage is a tissue type that doesn’t have blood vessels, neural networks and lymphatic vessels. Regeneration of the cartilage tissue is limited due to the small number of cells in the articular cartilage, low vascularization and low cell migration to the damage site. Biomaterial scaffolds are used for regeneration of cartilage since the cartilage needs structural and metabolic support in case of any damage. Mimicking the network structure of the natural cartilage is extremely important and hydrogels are good candidates for cartilage tissue engineering due to 3-D structure and the high-water holding capacity similar to the natural tissue. Also, biomimetic self-assembling peptides (SAP) can self-assemble with physiological conditions and form SAP hydrogels. Glycosaminoglycan (GAG) is crucial components of natural cartilage matrix, they are negatively charged chains, and they maintain the mechanical properties of tissue. In this study, it was develop GAG mimetic SAP hydrogels that can mimic original cartilage, and to determine the effect of these peptide hydrogels on cell viability and cell proliferation. SAP hydrogel structures were successfully produced by functionalization of SAP with GAG mimetic peptide epitope, and effect of these hydrogels on cell viability was evaluated by cell culture methods in this work.
{"title":"Determination of the Effect of Glycosaminoglycan Mimetic Peptide Hydrogels on Cell Viability for Cartilage Tissue Engineering Applications","authors":"Gülşah Sunal, Günnur Onak, Oğuzhan Gökmen, Ilayda Namli, O. Karaman","doi":"10.1109/TIPTEKNO50054.2020.9299263","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299263","url":null,"abstract":"Cartilage is a tissue type that doesn’t have blood vessels, neural networks and lymphatic vessels. Regeneration of the cartilage tissue is limited due to the small number of cells in the articular cartilage, low vascularization and low cell migration to the damage site. Biomaterial scaffolds are used for regeneration of cartilage since the cartilage needs structural and metabolic support in case of any damage. Mimicking the network structure of the natural cartilage is extremely important and hydrogels are good candidates for cartilage tissue engineering due to 3-D structure and the high-water holding capacity similar to the natural tissue. Also, biomimetic self-assembling peptides (SAP) can self-assemble with physiological conditions and form SAP hydrogels. Glycosaminoglycan (GAG) is crucial components of natural cartilage matrix, they are negatively charged chains, and they maintain the mechanical properties of tissue. In this study, it was develop GAG mimetic SAP hydrogels that can mimic original cartilage, and to determine the effect of these peptide hydrogels on cell viability and cell proliferation. SAP hydrogel structures were successfully produced by functionalization of SAP with GAG mimetic peptide epitope, and effect of these hydrogels on cell viability was evaluated by cell culture methods in this work.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128526488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299236
Fatih Onay, A. Mert
The classification of EMG signals for the amputees is important to develop a powered-prosthetic that is capable of replacing with lost limbs. The EMG signals collected from residual limbs reduce the classification accuracy due to muscle movements that cannot be realized properly. In thıs study, classification performance is aimed to be increased by combining CNN with root mean square (RMS) and waveform length (WL) that are used in analysis of EMG signals successfully. The features such as RMS and WL extracted from EMG signals for the classification of six hand movements at the low, medium, and high force levels were applied to CNN input, and classification results were compared with nearest neighbour and linear discriminant analysis.
{"title":"Amputee Electromyography Signal Classification Using Convolutional Neural Network","authors":"Fatih Onay, A. Mert","doi":"10.1109/TIPTEKNO50054.2020.9299236","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299236","url":null,"abstract":"The classification of EMG signals for the amputees is important to develop a powered-prosthetic that is capable of replacing with lost limbs. The EMG signals collected from residual limbs reduce the classification accuracy due to muscle movements that cannot be realized properly. In thıs study, classification performance is aimed to be increased by combining CNN with root mean square (RMS) and waveform length (WL) that are used in analysis of EMG signals successfully. The features such as RMS and WL extracted from EMG signals for the classification of six hand movements at the low, medium, and high force levels were applied to CNN input, and classification results were compared with nearest neighbour and linear discriminant analysis.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125917850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299294
Hüseyin Cihad Güler, V. Yildiz, U. Baysal, ve Funda B. Cinyol, D. Köksal, E. Babaoğlu, S. Sarınç Ulaşlı
Lung sounds can vary according to various respiratory diseases of the person. Specialist physicians use these sound data to make a diagnosis. Diagnostic success varies according to the physician’s experience. computer-aided diagnostic systems can help physicians in this regard. In this study, disease diagnosis system was developed by using lung sound data obtained by auscultation method. In experimental studies, various machine learning methods have been tried on 20 normal, 20 ral and 20 rhoncus sound data taken from 60 patients. In addition, the data set was tripled with two different artificial data generation methods. The results obtained by applying k- Nearest Neighbor (kNN), Support Vector Machine (SVM), Naive Bayes, Decision Tree and Random Forest Classifier to all data obtained by real data set and artificial data production are presented. A 95% accuracy value was obtained with 10 cross- validation using the Naive Bayes classification method. In the results obtained after artificial data production, an accuracy value of 94% was obtained with 10 cross-validation with the kNN method.
{"title":"Classification of Abnormal Respiratory Sounds Using Machine Learning Techniques","authors":"Hüseyin Cihad Güler, V. Yildiz, U. Baysal, ve Funda B. Cinyol, D. Köksal, E. Babaoğlu, S. Sarınç Ulaşlı","doi":"10.1109/TIPTEKNO50054.2020.9299294","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299294","url":null,"abstract":"Lung sounds can vary according to various respiratory diseases of the person. Specialist physicians use these sound data to make a diagnosis. Diagnostic success varies according to the physician’s experience. computer-aided diagnostic systems can help physicians in this regard. In this study, disease diagnosis system was developed by using lung sound data obtained by auscultation method. In experimental studies, various machine learning methods have been tried on 20 normal, 20 ral and 20 rhoncus sound data taken from 60 patients. In addition, the data set was tripled with two different artificial data generation methods. The results obtained by applying k- Nearest Neighbor (kNN), Support Vector Machine (SVM), Naive Bayes, Decision Tree and Random Forest Classifier to all data obtained by real data set and artificial data production are presented. A 95% accuracy value was obtained with 10 cross- validation using the Naive Bayes classification method. In the results obtained after artificial data production, an accuracy value of 94% was obtained with 10 cross-validation with the kNN method.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129746458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299318
Mecit Yüzkat, Hamza Osman Ilhan, N. Aydin
The fertility of men and women are examined separately in the diagnosis of infertility. Clinical studies have shown that male infertility rate has a high rate of 25-30% in general diagnosis. Sperm concentration, motility and morphological abnormality are evaluated in male based infertility. In morphological analysis, sperm images should be obtained in detail to obtain objective results. However, the usage of low quality video camera or vibrations occurred in camera module causes to obtain low quality images. In this study, in order to increase the classification performance of the SCIAN-Morpho dataset with low quality sperm images, firstly interpolation methods were applied to increase the data quality. Then, data augmentation techniques have been applied for the data imbalance problem. In the classification phase, pre-trained convolutional neural networks were applied. As a result of the classification, 62% accuracy, 85% precision and 75% sensitivity were obtained by using the VGG-19 networks with the data augmentation and interpolation techniques.
{"title":"Morphological Classification of Low Quality Sperm Images Using Deep Learning Networks","authors":"Mecit Yüzkat, Hamza Osman Ilhan, N. Aydin","doi":"10.1109/TIPTEKNO50054.2020.9299318","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299318","url":null,"abstract":"The fertility of men and women are examined separately in the diagnosis of infertility. Clinical studies have shown that male infertility rate has a high rate of 25-30% in general diagnosis. Sperm concentration, motility and morphological abnormality are evaluated in male based infertility. In morphological analysis, sperm images should be obtained in detail to obtain objective results. However, the usage of low quality video camera or vibrations occurred in camera module causes to obtain low quality images. In this study, in order to increase the classification performance of the SCIAN-Morpho dataset with low quality sperm images, firstly interpolation methods were applied to increase the data quality. Then, data augmentation techniques have been applied for the data imbalance problem. In the classification phase, pre-trained convolutional neural networks were applied. As a result of the classification, 62% accuracy, 85% precision and 75% sensitivity were obtained by using the VGG-19 networks with the data augmentation and interpolation techniques.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125731573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：