Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299216
Muge Anil-Inevi, Y. Unal, Sena Yaman, H. Tekin, Gulistan Mese, E. Ozcivici
Label-free magnetic levitation is one of the most recent Earth-based in vitro t echniques that simulate the microgravity. This technique offers a great opportunity to biofabricate scaffold-free 3-dimensional (3D) structures and to study the effects of microgravity on these structures. In this study, self-assembled 3D living structures were fabricated in a paramagnetic medium by magnetic levitation technique and effects of the technique on cellular health was assessed. This magnetic force-assisted assembly system applied here offers broad applications in several fields, such as space biotechnology and bottom-up tissue engineering.
{"title":"Assessment of cell cycle and viability of magnetic levitation assembled cellular structures","authors":"Muge Anil-Inevi, Y. Unal, Sena Yaman, H. Tekin, Gulistan Mese, E. Ozcivici","doi":"10.1109/TIPTEKNO50054.2020.9299216","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299216","url":null,"abstract":"Label-free magnetic levitation is one of the most recent Earth-based in vitro t echniques that simulate the microgravity. This technique offers a great opportunity to biofabricate scaffold-free 3-dimensional (3D) structures and to study the effects of microgravity on these structures. In this study, self-assembled 3D living structures were fabricated in a paramagnetic medium by magnetic levitation technique and effects of the technique on cellular health was assessed. This magnetic force-assisted assembly system applied here offers broad applications in several fields, such as space biotechnology and bottom-up tissue engineering.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"65 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":"114991826","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/TIPTEKNO50054.2020.9299290
Özkan Arslan
In this study, a new approach has been presented based on perceptual wavelet packet transform and support vector machines for analysis and classification of pathological and healthy voice signals. Feature extraction and development of classification algorithm play important role in the area of automatic classification of pathological and healthy voice signals. The critical sub-bands are obtained by separating pathological and healthy voice signals with perceptual wavelet packet trans- form. The energy and entropy measures are extracted at each sub-bands used for training and testing of the classifier. In the study, the VIOCED database are used and it consists of 208 voice signals which are 58 healthy and 150 pathological. Experimental results demonstrate that the proposed features and classification algorithm provide 93.1% sensitivity, 96.5% specificity and 97.1% accuracy rates and it shows that the proposed method can be used to help medical professionals for diagnosing pathological status of a voice signal.
{"title":"Classification of Pathological and Healthy Voice Using Perceptual Wavelet Packet Decomposition and Support Vector Machine","authors":"Özkan Arslan","doi":"10.1109/TIPTEKNO50054.2020.9299290","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299290","url":null,"abstract":"In this study, a new approach has been presented based on perceptual wavelet packet transform and support vector machines for analysis and classification of pathological and healthy voice signals. Feature extraction and development of classification algorithm play important role in the area of automatic classification of pathological and healthy voice signals. The critical sub-bands are obtained by separating pathological and healthy voice signals with perceptual wavelet packet trans- form. The energy and entropy measures are extracted at each sub-bands used for training and testing of the classifier. In the study, the VIOCED database are used and it consists of 208 voice signals which are 58 healthy and 150 pathological. Experimental results demonstrate that the proposed features and classification algorithm provide 93.1% sensitivity, 96.5% specificity and 97.1% accuracy rates and it shows that the proposed method can be used to help medical professionals for diagnosing pathological status of a voice signal.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"3 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":"115320014","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/TIPTEKNO50054.2020.9299267
Nuh Hatipoglu, G. Bilgin
In this study, it is intended to increase the clas- sification accuracy results of malignant lymphoma images by evaluating spatial relations. As a first step, convolutional neural network (CNN) based features are extracted in the original RGB color space of digital histopathalogical images. Classification models of each feature vectors are obtained by employing CNN, support vector machines (SVM) and random forest (RF) methods. For comparison purposes, the classification accuracy results obtained from supervised learning methods are presented in the experimental results section.
{"title":"Classification of Malignant Lymphoma Types Using Convolutional Neural Network","authors":"Nuh Hatipoglu, G. Bilgin","doi":"10.1109/TIPTEKNO50054.2020.9299267","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299267","url":null,"abstract":"In this study, it is intended to increase the clas- sification accuracy results of malignant lymphoma images by evaluating spatial relations. As a first step, convolutional neural network (CNN) based features are extracted in the original RGB color space of digital histopathalogical images. Classification models of each feature vectors are obtained by employing CNN, support vector machines (SVM) and random forest (RF) methods. For comparison purposes, the classification accuracy results obtained from supervised learning methods are presented in the experimental results section.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"123 6 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":"129568742","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/TIPTEKNO50054.2020.9299307
T. Artug
In this study, 300 signal records were acquired in each session using surface electrode under submaximal stimulation. Data set were formed from 10 ALS and Polio patients with 10 normal individuals. The muscle group under study was abductor pollisis brevis and abductor digiti minimi muscles which were interconnected to median and ulnar nerves. Parameters were calculated by doing F-response analysis to the acquired recordings. The most prominent parameters among the calculated ones are mean sMUP amplitude and MUNE value. Mean sMUP amplitude value can differentiate patients from normal individuals in both muscles. Moreover, the MUNE value that are calculated from abductor pollisis brevis muscle can differentiate all groups from each other significantly (p<0.05).
{"title":"The Effect of F-response Parameters in ALS and Polio Patients","authors":"T. Artug","doi":"10.1109/TIPTEKNO50054.2020.9299307","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299307","url":null,"abstract":"In this study, 300 signal records were acquired in each session using surface electrode under submaximal stimulation. Data set were formed from 10 ALS and Polio patients with 10 normal individuals. The muscle group under study was abductor pollisis brevis and abductor digiti minimi muscles which were interconnected to median and ulnar nerves. Parameters were calculated by doing F-response analysis to the acquired recordings. The most prominent parameters among the calculated ones are mean sMUP amplitude and MUNE value. Mean sMUP amplitude value can differentiate patients from normal individuals in both muscles. Moreover, the MUNE value that are calculated from abductor pollisis brevis muscle can differentiate all groups from each other significantly (p<0.05).","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":"130092960","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/TIPTEKNO50054.2020.9299296
Ö. B. Mercan, ve Volkan Kılıç
Glucose is an extremely important molecule as an energy source and human body function. Diabetes, which ranks among the diseases of the age, is detected based on the glucose level in the human body. Therefore, quantification of glucose is important to develop research and applications of diabetes, which is an important health problem. This study aims to classify glucose concentration with deep learning based colorimetric analysis using a smartphone. The color changes obtained as a result of the reaction of Au-Ag nanoparticles with different concentrations of glucose were captured using a smartphone camera to create a dataset. The proposed deep learning model was trained with this dataset and glucose concentration was classified with 95.93% accuracy. The deep learning model was integrated into our custom-designed Android application, DeepGlucose, to enable glucose classification via a smartphone.
{"title":"Deep Learning based Colorimetric Classification of Glucose with Au-Ag nanoparticles using Smartphone","authors":"Ö. B. Mercan, ve Volkan Kılıç","doi":"10.1109/TIPTEKNO50054.2020.9299296","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299296","url":null,"abstract":"Glucose is an extremely important molecule as an energy source and human body function. Diabetes, which ranks among the diseases of the age, is detected based on the glucose level in the human body. Therefore, quantification of glucose is important to develop research and applications of diabetes, which is an important health problem. This study aims to classify glucose concentration with deep learning based colorimetric analysis using a smartphone. The color changes obtained as a result of the reaction of Au-Ag nanoparticles with different concentrations of glucose were captured using a smartphone camera to create a dataset. The proposed deep learning model was trained with this dataset and glucose concentration was classified with 95.93% accuracy. The deep learning model was integrated into our custom-designed Android application, DeepGlucose, to enable glucose classification via a smartphone.","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":"128697208","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/TIPTEKNO50054.2020.9299277
Z. Karhan, F. Akal
The automatic evaluation is essential for the diagnosis and treatment of the disease of pathological images. Computer-aided systems are becoming more common day by day in this area. In this study, multi-class (8 different classes) tissue types were studied in colon cancer histopathological images. Data mining algorithms are used in the diagnosis phase in the health field. As a conventional method, first of all, the properties of the images are extracted and then the texture classification process is performed with data mining algorithms. The Gray Level Co-occurrence Matrix (GLCM), Discrete Cosine Transform (DCT), Local Binary Pattern (LBP) are used in textural feature extraction. Along with these attributes, machine learning algorithms, such as k-nearest neighbors (KNN), support vector machines (SVM), random forests (RF), logistic regression (LR) were used for classification. As another method, to remove the attributes and perform classification at the same time, tissue classification was performed using deep learning (convolutional neural network) on histopathological images. Tissue classification was automated using transfer learning based on ResNet-18 architecture, one of the convolutional neural network architectures. According to the determined feature and classification algorithm, the performance rates are also given comparatively. Our experiments showed that RF classifier with LBP and GLCM features provided 82% accuracy, while the deep learning method based on ResNet-18 architecture achieved 88.5% accuracy.
{"title":"Comparison of Tissue Classification Performance by Deep Learning and Conventional Methods on Colorectal Histopathological Images","authors":"Z. Karhan, F. Akal","doi":"10.1109/TIPTEKNO50054.2020.9299277","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299277","url":null,"abstract":"The automatic evaluation is essential for the diagnosis and treatment of the disease of pathological images. Computer-aided systems are becoming more common day by day in this area. In this study, multi-class (8 different classes) tissue types were studied in colon cancer histopathological images. Data mining algorithms are used in the diagnosis phase in the health field. As a conventional method, first of all, the properties of the images are extracted and then the texture classification process is performed with data mining algorithms. The Gray Level Co-occurrence Matrix (GLCM), Discrete Cosine Transform (DCT), Local Binary Pattern (LBP) are used in textural feature extraction. Along with these attributes, machine learning algorithms, such as k-nearest neighbors (KNN), support vector machines (SVM), random forests (RF), logistic regression (LR) were used for classification. As another method, to remove the attributes and perform classification at the same time, tissue classification was performed using deep learning (convolutional neural network) on histopathological images. Tissue classification was automated using transfer learning based on ResNet-18 architecture, one of the convolutional neural network architectures. According to the determined feature and classification algorithm, the performance rates are also given comparatively. Our experiments showed that RF classifier with LBP and GLCM features provided 82% accuracy, while the deep learning method based on ResNet-18 architecture achieved 88.5% accuracy.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"128 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":"122578883","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/TIPTEKNO50054.2020.9299291
Fikri Seven, ve Mustafa Şen
The main purpose of this study is the fabrication of an ultra-small size, simple and inexpensive metal oxide semiconductor field effect transistor-based (MOSFET) probe type pH sensor that allows fast and precise local pH measurement. First, the surface of a Pt ultra micro-electrode was coated electrochemically with polypyrrole, a semiconductor polymer, and then the probe was integrated into the gate of a MOSFET. Using the developed system, measurements were taken in PBS at different pH values. The results showed that the developed pH microsensor is sensitive to pH change. It is predicted that the micro pH sensor will allow local pH analysis in biological samples or corrosion studies.
{"title":"Fabrication and Characterization of a Metal Oxide Semiconductor Field Effect Transistor (MOSFET)-based Micro pH Sensor","authors":"Fikri Seven, ve Mustafa Şen","doi":"10.1109/TIPTEKNO50054.2020.9299291","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299291","url":null,"abstract":"The main purpose of this study is the fabrication of an ultra-small size, simple and inexpensive metal oxide semiconductor field effect transistor-based (MOSFET) probe type pH sensor that allows fast and precise local pH measurement. First, the surface of a Pt ultra micro-electrode was coated electrochemically with polypyrrole, a semiconductor polymer, and then the probe was integrated into the gate of a MOSFET. Using the developed system, measurements were taken in PBS at different pH values. The results showed that the developed pH microsensor is sensitive to pH change. It is predicted that the micro pH sensor will allow local pH analysis in biological samples or corrosion studies.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"80 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":"116199776","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/TIPTEKNO50054.2020.9299249
Egehan Dorum, Mazlum Unay, Onan Guren, A. Akan
Magnetic Resonance (MR) imaging has always followed a developmental path by incorporating new algorithms in terms of image quality and imaging duration. In MR imaging performed in hospitals and clinics, the duration of imaging is an important consideration in terms of both for the comfort of the patient and the number of patients who can be taken daily. One of the approaches to shorten the imaging time is the parallel imaging method. After parallel imaging algorithms started being used, imaging duration up to 1 hour with traditional methods has been reduced to minutes or even seconds depending on the number of receiving coils and the type of algorithm used. In this paper; comparison of the widely used parallel imaging algorithms such as Partially Parallel Imaging With Localized Sensitivities (PILS), and Sensitivity Encoding (SENSE) and evaluation of advantages and disadvantages of these algorithms over each other were performed utilizing the numerical calculation software named MATLAB.
磁共振成像在图像质量和成像时间方面一直遵循新的算法发展路径。在医院和诊所进行磁共振成像时，成像时间是一个重要的考虑因素，既考虑到患者的舒适度，也考虑到每天可以接受治疗的患者人数。缩短成像时间的方法之一是并行成像方法。在并行成像算法开始使用后，根据接收线圈的数量和使用的算法类型，传统方法长达1小时的成像时间已经缩短到几分钟甚至几秒钟。在本文中;利用MATLAB数值计算软件，对目前广泛应用的局部灵敏度部分并行成像(partial parallel imaging With localization sensitions, PILS)和灵敏度编码(Sensitivity Encoding, SENSE)等并行成像算法进行了比较，并对这些算法的优缺点进行了评价。
{"title":"Comparison of Parallel Magnetic Resonance Imaging Algorithms: PILS and SENSE","authors":"Egehan Dorum, Mazlum Unay, Onan Guren, A. Akan","doi":"10.1109/TIPTEKNO50054.2020.9299249","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299249","url":null,"abstract":"Magnetic Resonance (MR) imaging has always followed a developmental path by incorporating new algorithms in terms of image quality and imaging duration. In MR imaging performed in hospitals and clinics, the duration of imaging is an important consideration in terms of both for the comfort of the patient and the number of patients who can be taken daily. One of the approaches to shorten the imaging time is the parallel imaging method. After parallel imaging algorithms started being used, imaging duration up to 1 hour with traditional methods has been reduced to minutes or even seconds depending on the number of receiving coils and the type of algorithm used. In this paper; comparison of the widely used parallel imaging algorithms such as Partially Parallel Imaging With Localized Sensitivities (PILS), and Sensitivity Encoding (SENSE) and evaluation of advantages and disadvantages of these algorithms over each other were performed utilizing the numerical calculation software named MATLAB.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"69 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":"127405379","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/TIPTEKNO50054.2020.9299255
Gokturk Cinel, E. A. Tarim, H. Tekin
Sleep apnea is a disease that occurs during sleep, which affects the daily life of patients due to the obstruction of the upper respiratory tract and decreases oxygen level in blood and it may even lead to patient death in the later stage. Monitoring the patients regularly has absolute importance to prevent patient disorders caused by sleep apnea. Wearable sensor technologies and patient tracking systems provide diagnosis, treatment, and monitoring of patients, and procure better health services in medical fields. In addition to decreasing the workload of health institutions, remote patient monitoring systems can serve continuous monitoring and determine variable symptoms of the patients. In this paper, we propose a patient monitoring system, which will be used for diagnosis and monitoring of sleep apnea by tracking the respiratory rate of patients with wearable sensor technology. The respiratory rate is detected using either an accelerometer sensor to be placed on the patients' abdomen or a temperature sensor to be placed on their noses. The proposed system offers an increase in the versatility of patient monitoring systems and offers an alternative new technology in sleep apnea diagnosis.
{"title":"Wearable respiratory rate sensor technology for diagnosis of sleep apnea","authors":"Gokturk Cinel, E. A. Tarim, H. Tekin","doi":"10.1109/TIPTEKNO50054.2020.9299255","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299255","url":null,"abstract":"Sleep apnea is a disease that occurs during sleep, which affects the daily life of patients due to the obstruction of the upper respiratory tract and decreases oxygen level in blood and it may even lead to patient death in the later stage. Monitoring the patients regularly has absolute importance to prevent patient disorders caused by sleep apnea. Wearable sensor technologies and patient tracking systems provide diagnosis, treatment, and monitoring of patients, and procure better health services in medical fields. In addition to decreasing the workload of health institutions, remote patient monitoring systems can serve continuous monitoring and determine variable symptoms of the patients. In this paper, we propose a patient monitoring system, which will be used for diagnosis and monitoring of sleep apnea by tracking the respiratory rate of patients with wearable sensor technology. The respiratory rate is detected using either an accelerometer sensor to be placed on the patients' abdomen or a temperature sensor to be placed on their noses. The proposed system offers an increase in the versatility of patient monitoring systems and offers an alternative new technology in sleep apnea diagnosis.","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":"127971947","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/TIPTEKNO50054.2020.9299257
Ç. Erdaş, E. Sümer
Studies conducted by the World Health Organization (WHO) show that more than a billion people worldwide suffer from neurological disorders and the lack of effective diagnostic procedures affects treatment. Characterizing specific motor symptoms to facilitate their diagnosis can be useful in monitoring disease progression and effective treatment planning. Classification of highly prevalent neurodegenerative diseases (NDD) such as Parkinson’s disease (PH), Amyotrophic Lateral Sclerosis (ALS), and Huntington’s disease (HH) is of clinical importance. One of the methods used in the literature to detect these neurodegenerative diseases is gait analysis-based classification. In this study, 12 different features fed a unidimensional Convolutional Neural Network (CNN) deep learning algorithm-based model, and aims to detect PD,HD, and ALS diseases was studied.The unidimensional CNN deep learning model fed with 12 features achieved 78,92%, 84,39% and 92,09% classification accuracy for control against HH, control against PH, and control detection problems against ALS. Again, the relevant classifier produced 84.75% accuracy with the approach developed to separate all neurodegenerative disease specimens (NDD) under a single label as a class, and to distinguish these diseases against the current control.
{"title":"A Deep Learning-Based Approach to Detect Neurodegenerative Diseases","authors":"Ç. Erdaş, E. Sümer","doi":"10.1109/TIPTEKNO50054.2020.9299257","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299257","url":null,"abstract":"Studies conducted by the World Health Organization (WHO) show that more than a billion people worldwide suffer from neurological disorders and the lack of effective diagnostic procedures affects treatment. Characterizing specific motor symptoms to facilitate their diagnosis can be useful in monitoring disease progression and effective treatment planning. Classification of highly prevalent neurodegenerative diseases (NDD) such as Parkinson’s disease (PH), Amyotrophic Lateral Sclerosis (ALS), and Huntington’s disease (HH) is of clinical importance. One of the methods used in the literature to detect these neurodegenerative diseases is gait analysis-based classification. In this study, 12 different features fed a unidimensional Convolutional Neural Network (CNN) deep learning algorithm-based model, and aims to detect PD,HD, and ALS diseases was studied.The unidimensional CNN deep learning model fed with 12 features achieved 78,92%, 84,39% and 92,09% classification accuracy for control against HH, control against PH, and control detection problems against ALS. Again, the relevant classifier produced 84.75% accuracy with the approach developed to separate all neurodegenerative disease specimens (NDD) under a single label as a class, and to distinguish these diseases against the current control.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"98 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":"132840790","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：