Pub Date : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319444
Saman Sotoudeh Paima, Navid Hasanzadeh, Ata Jodeiri, H. Soltanian-Zadeh
The coronavirus disease (COVID-19), which has been declared as a pandemic by the World Health Organization (WHO), is an infectious disease killing more than 660,000 people worldwide. During this challenge, Deep learning, a subset of artificial intelligence, could be used as an effective tool for assisting radiologists in detecting COVID-19 cases, as well as reducing the burden on healthcare systems. Correct detection of COVID-19 cases using X-ray images could help quarantine high-risk patients until a thorough examination is followed. In this study, we aim to compare four state-of-the-art deep learning models (VGG-16, VGG-19, EfficientNetB0, and ResNet50) using 464 chest X-ray images of COVID-19 and normal cases. A classification head is added to all these models in order to achieve the best performance. The VGG-19 model achieved the best performance in terms of AUROC among all the tested models with a value of 0.91. Also, the heatmaps of X-ray images are provided, which could be used to specify the disease's area within the lung.
{"title":"Detection of COVID-19 from Chest Radiographs: Comparison of Four End-to-End Trained Deep Learning Models","authors":"Saman Sotoudeh Paima, Navid Hasanzadeh, Ata Jodeiri, H. Soltanian-Zadeh","doi":"10.1109/ICBME51989.2020.9319444","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319444","url":null,"abstract":"The coronavirus disease (COVID-19), which has been declared as a pandemic by the World Health Organization (WHO), is an infectious disease killing more than 660,000 people worldwide. During this challenge, Deep learning, a subset of artificial intelligence, could be used as an effective tool for assisting radiologists in detecting COVID-19 cases, as well as reducing the burden on healthcare systems. Correct detection of COVID-19 cases using X-ray images could help quarantine high-risk patients until a thorough examination is followed. In this study, we aim to compare four state-of-the-art deep learning models (VGG-16, VGG-19, EfficientNetB0, and ResNet50) using 464 chest X-ray images of COVID-19 and normal cases. A classification head is added to all these models in order to achieve the best performance. The VGG-19 model achieved the best performance in terms of AUROC among all the tested models with a value of 0.91. Also, the heatmaps of X-ray images are provided, which could be used to specify the disease's area within the lung.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123259295","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319417
Fariborz Rahimi, N. Salahshour, Reza Eyvazpour, M. Azghani
Spasticity is one of the common motor disorders that occurs due to upper motor neuron defects in patients such as stroke, spinal cord injury, cerebral palsy, and multiple sclerosis. Its measurement is often done using standardized clinical scales. One of the salient problems associated with this symptom is poor objectivity in its assessment. Several methods have been proposed in the past two decades from which passive joint movement and the Wartenberg pendulum test are the most practical, promising, and sensitive to changes. The purpose of this study was to investigate the capability of accelerometer-based outcome measures in assessment of spasticity through pendulum test. We also aimed at evaluation of sensitivity to choice of sensor on outcome measures’ strength in discriminating levels of spasticity. In this study we have simulated oscillating movement of dropped limb in various levels of spasticity by a simple pendulum and adjustable friction level. Our results show that acceleration-based outcome measures are as strong as angle-based counterparts and can reliably discriminate levels of spasticity in the whole range of severity (87% discrimination index). We also found that choice of accelerometer does not have noticeable effect on the performance of this objective method of spasticity assessment
{"title":"An accelerometer-based objective assessment of spasticity: A simple pendulum model to evaluate outcome measures","authors":"Fariborz Rahimi, N. Salahshour, Reza Eyvazpour, M. Azghani","doi":"10.1109/ICBME51989.2020.9319417","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319417","url":null,"abstract":"Spasticity is one of the common motor disorders that occurs due to upper motor neuron defects in patients such as stroke, spinal cord injury, cerebral palsy, and multiple sclerosis. Its measurement is often done using standardized clinical scales. One of the salient problems associated with this symptom is poor objectivity in its assessment. Several methods have been proposed in the past two decades from which passive joint movement and the Wartenberg pendulum test are the most practical, promising, and sensitive to changes. The purpose of this study was to investigate the capability of accelerometer-based outcome measures in assessment of spasticity through pendulum test. We also aimed at evaluation of sensitivity to choice of sensor on outcome measures’ strength in discriminating levels of spasticity. In this study we have simulated oscillating movement of dropped limb in various levels of spasticity by a simple pendulum and adjustable friction level. Our results show that acceleration-based outcome measures are as strong as angle-based counterparts and can reliably discriminate levels of spasticity in the whole range of severity (87% discrimination index). We also found that choice of accelerometer does not have noticeable effect on the performance of this objective method of spasticity assessment","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"32 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116931359","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319434
Fatemeh Maadi, N. Faraji, Mohammadreza Hassannejad Bibalan
In this paper, the optic disc and optic cup are segmented for a cup to disc ratio (CDR) based glaucoma diagnosis. For this purpose, segmentation is implemented by a modified U-Net architecture employing the pre-trained SE-ResNet50 as its downsampling layers. Finally, due to cup and disc areas obtained from the proposed segmentation step, CDR is evaluated. This model is trained on Drishti-GS1 and RIM-ONE v3 databases and is tested on test images of the Drishti-GS1 database. Additionally, to demonstrate the robustness of the proposed method across different datasets the test phase is performed on validation images of the REFUGE database. In terms of F1-score criteria, segmentation results of the optic cup and optic disc are respectively 0.926 and 0.977 for the Drishti-GS1 database and 0.79 and 0.91 for the REFUGE database. Also, the correlation coefficient between the proposed method CDR and the ground truth CDR is 0.94 for the Drishti-GS1 database and is 0.81 for the REFUGE database. Finally, the AUC value is obtained 0.94 and 0.939 for Drishti-GS1 and REFUGE databases, respectively, where the latter result shows the robustness of the proposed diagnosis model.
{"title":"A Robust Glaucoma Screening Method for Fundus Images Using Deep Learning Technique","authors":"Fatemeh Maadi, N. Faraji, Mohammadreza Hassannejad Bibalan","doi":"10.1109/ICBME51989.2020.9319434","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319434","url":null,"abstract":"In this paper, the optic disc and optic cup are segmented for a cup to disc ratio (CDR) based glaucoma diagnosis. For this purpose, segmentation is implemented by a modified U-Net architecture employing the pre-trained SE-ResNet50 as its downsampling layers. Finally, due to cup and disc areas obtained from the proposed segmentation step, CDR is evaluated. This model is trained on Drishti-GS1 and RIM-ONE v3 databases and is tested on test images of the Drishti-GS1 database. Additionally, to demonstrate the robustness of the proposed method across different datasets the test phase is performed on validation images of the REFUGE database. In terms of F1-score criteria, segmentation results of the optic cup and optic disc are respectively 0.926 and 0.977 for the Drishti-GS1 database and 0.79 and 0.91 for the REFUGE database. Also, the correlation coefficient between the proposed method CDR and the ground truth CDR is 0.94 for the Drishti-GS1 database and is 0.81 for the REFUGE database. Finally, the AUC value is obtained 0.94 and 0.939 for Drishti-GS1 and REFUGE databases, respectively, where the latter result shows the robustness of the proposed diagnosis model.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127534514","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319466
V. Nafisi, R. Ghods, Mahnaz Mardi
In Persian Medicine (PM), measuring the wrist pulse is one of the main method for determining a person's health status and temperament. One problem that can arise is the dependence of the diagnosis on the physician's interpretation of pulse wave features. Perhaps this is one reason why this method has yet to be combined with modern medical methods. This paper addresses this concern and outlines a system for measuring pulse signals based on PM. A system that uses data from a customized device that logs the pulse wave on the wrist was designed and clinically implemented based on PM. Seven Convolutional Neural Networks (CNN) have been used for classification. The pulse wave features of 34 participants was assessed by a specialist based on PM principles. Pulse taking was done on the wrist in the supine position (named Malmas in PM) under the supervision of the physician. Seven CNNs were implemented for participants’ classification based on seven PM classes. It appears that the design and construction of a customized device that can measure the pulse waves features according to PM, is possible and can increase the reliability of the diagnostic results based on PM.
{"title":"A pulse taking device for Persian medicine based on Convolutional Neural Network","authors":"V. Nafisi, R. Ghods, Mahnaz Mardi","doi":"10.1109/ICBME51989.2020.9319466","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319466","url":null,"abstract":"In Persian Medicine (PM), measuring the wrist pulse is one of the main method for determining a person's health status and temperament. One problem that can arise is the dependence of the diagnosis on the physician's interpretation of pulse wave features. Perhaps this is one reason why this method has yet to be combined with modern medical methods. This paper addresses this concern and outlines a system for measuring pulse signals based on PM. A system that uses data from a customized device that logs the pulse wave on the wrist was designed and clinically implemented based on PM. Seven Convolutional Neural Networks (CNN) have been used for classification. The pulse wave features of 34 participants was assessed by a specialist based on PM principles. Pulse taking was done on the wrist in the supine position (named Malmas in PM) under the supervision of the physician. Seven CNNs were implemented for participants’ classification based on seven PM classes. It appears that the design and construction of a customized device that can measure the pulse waves features according to PM, is possible and can increase the reliability of the diagnostic results based on PM.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116730192","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 : 2020-11-26DOI: 10.1109/icbme51989.2020.9319441
{"title":"ICBME 2020 Committees","authors":"","doi":"10.1109/icbme51989.2020.9319441","DOIUrl":"https://doi.org/10.1109/icbme51989.2020.9319441","url":null,"abstract":"","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126045663","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319438
S. Hashemikamangar, F. Bakouie, S. Gharibzadeh
In this study, we aim to investigate how children’s language develops. To do so, we apply the network model of language and examine the graph-theoretic properties of Word2Vec semantic networks of children through development. The networks are made of words children learn prior to the age of 30 months as the nodes. The links in the word-embedding networks are built from the cosine vector similarity of words normatively acquired by children prior to 2 ½ years of age. By exploiting some graph measures such as the clustering coefficient and path length, the growth pattern of these semantic networks will be revealed. The small-world property allows for high amounts of local structure combined with global access. Within these semantic networks, there is a considerable local structure in the form of clusters of words. For global structure, some nodes act like bridges. They are actually the hubs of the network and connect the clusters which are semantically far-away. We explore the small-world property of these semantic networks and their changes through language development. The results demonstrate that the Word2Vec semantic networks of children show the small-world property from the early age of several months.
{"title":"Children Semantic Network Growth: A Graph Theory Analysis","authors":"S. Hashemikamangar, F. Bakouie, S. Gharibzadeh","doi":"10.1109/ICBME51989.2020.9319438","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319438","url":null,"abstract":"In this study, we aim to investigate how children’s language develops. To do so, we apply the network model of language and examine the graph-theoretic properties of Word2Vec semantic networks of children through development. The networks are made of words children learn prior to the age of 30 months as the nodes. The links in the word-embedding networks are built from the cosine vector similarity of words normatively acquired by children prior to 2 ½ years of age. By exploiting some graph measures such as the clustering coefficient and path length, the growth pattern of these semantic networks will be revealed. The small-world property allows for high amounts of local structure combined with global access. Within these semantic networks, there is a considerable local structure in the form of clusters of words. For global structure, some nodes act like bridges. They are actually the hubs of the network and connect the clusters which are semantically far-away. We explore the small-world property of these semantic networks and their changes through language development. The results demonstrate that the Word2Vec semantic networks of children show the small-world property from the early age of several months.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"84 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113954790","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319326
Abolfazl Karimiyan Abdar, S. M. Sadjadi, H. Soltanian-Zadeh, Ali Bashirgonbadi, M. Naghibi
In recent months, coronavirus disease 2019 (COVID-19) has infected millions of people worldwide. In addition to the clinical tests like reverse transcription-polymerase chain reaction (RT-PCR), medical imaging techniques such as computed tomography (CT) can be used as a rapid technique to detect and evaluate patients infected by COVID-19. Conventionally, CT-based COVID-19 classification is done by a radiology expert. In this paper, we present a deep learning-based Convolutional Neural Network (CNN) model we developed for the classification of COVID-19 positive patients from healthy subjects using chest CT. We used 10979 chest CT images of 131 patients with COVID-19 and 150 healthy subjects for training, validating, and testing of the proposed model. Evaluation of the results showed the precision of 92%, sensitivity of 90%, specificity of 91%, F1-Score of 0.91, and accuracy of 90%. We have used the regions of infection segmented by a radiologist to increase the generalization and reliability of the results. The plotted heatmaps show that the developed model has focused only on the infected regions of the lungs by COVID-19 to make decisions.
{"title":"Automatic Detection of Coronavirus (COVID-19) from Chest CT Images using VGG16-Based Deep-Learning","authors":"Abolfazl Karimiyan Abdar, S. M. Sadjadi, H. Soltanian-Zadeh, Ali Bashirgonbadi, M. Naghibi","doi":"10.1109/ICBME51989.2020.9319326","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319326","url":null,"abstract":"In recent months, coronavirus disease 2019 (COVID-19) has infected millions of people worldwide. In addition to the clinical tests like reverse transcription-polymerase chain reaction (RT-PCR), medical imaging techniques such as computed tomography (CT) can be used as a rapid technique to detect and evaluate patients infected by COVID-19. Conventionally, CT-based COVID-19 classification is done by a radiology expert. In this paper, we present a deep learning-based Convolutional Neural Network (CNN) model we developed for the classification of COVID-19 positive patients from healthy subjects using chest CT. We used 10979 chest CT images of 131 patients with COVID-19 and 150 healthy subjects for training, validating, and testing of the proposed model. Evaluation of the results showed the precision of 92%, sensitivity of 90%, specificity of 91%, F1-Score of 0.91, and accuracy of 90%. We have used the regions of infection segmented by a radiologist to increase the generalization and reliability of the results. The plotted heatmaps show that the developed model has focused only on the infected regions of the lungs by COVID-19 to make decisions.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123871356","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319461
A. Ghajarjazy, Kanaan Mousaie, S. Sabzpoushan
Neural oscillation occurs in many neural disorders such as Parkinson or epilepsy, that makes it important to study methods to suppress these oscillations. Stability analysis of different system behaviors can play a crucial role in understanding dynamical mechanisms in cell modelling. In this study, mathematical method is used to investigate the effect of potassium Nernst Voltage (VK) and temperature (T). In this regard, we analyze the stability and bifurcations of a modified version of Hodgkin-Huxley model by changing multi parameters. The (VK, T) plane is partitioned into two regions which indicates stable and unstable behaviors. Numerical simulations illustrate the validity of the analysis. The results could be helpful in studying temperature stimulation of diseased cells.
{"title":"Stability Analysis in a Temperature-Dependent Model of Neurons","authors":"A. Ghajarjazy, Kanaan Mousaie, S. Sabzpoushan","doi":"10.1109/ICBME51989.2020.9319461","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319461","url":null,"abstract":"Neural oscillation occurs in many neural disorders such as Parkinson or epilepsy, that makes it important to study methods to suppress these oscillations. Stability analysis of different system behaviors can play a crucial role in understanding dynamical mechanisms in cell modelling. In this study, mathematical method is used to investigate the effect of potassium Nernst Voltage (VK) and temperature (T). In this regard, we analyze the stability and bifurcations of a modified version of Hodgkin-Huxley model by changing multi parameters. The (VK, T) plane is partitioned into two regions which indicates stable and unstable behaviors. Numerical simulations illustrate the validity of the analysis. The results could be helpful in studying temperature stimulation of diseased cells.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852984","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319435
Pooya Tahmasebi, M. M. Dastjerdi, A. Fallah, S. Rashidi
Due to momentous clinical applications, modeling soft tissues and studying their mechanical properties such as elasticity and hyperelasticity were highly highlighted during the last decade. Because of differences between the mechanical properties of normal and cancerous tissues, precise modeling of mechanical behavior of soft tissues and distinguishing the types of tissues based on their responses to applied stimulations would facilitate the diagnosis of cancerous tissues. The present study sought to noninvasively recognize the mechanical behavior of prostate tissue and its cancerous masses. In this regard, the mechanical parameters of cancerous tissues were accurately estimated using the potent neural network method based on the displacement data. The displacement data related to various tissues and corresponding mechanical properties are required for developing and training neural network models. The finite element modeling using Abaqus software was implemented to simulate prostate tissue behavior and extract the required data for training neural networks. The nonlinear tissue behavior should be considered in soft tissue modeling. For representing the hyperelastic behavior of soft tissues, Ogden and Yeoh models are accurate, which were utilized in the study to prepare the finite element model of prostate tissue containing tumor. In addition, white noise was added into the displacement data obtained by the finite element model for simulating laboratory conditions during extracting tissue data from the model in order to achieve robust neural network models. The results indicate high accuracy and efficiency of the trained neural network models in estimating the mechanical parameters of cancerous prostate tissues based on the displacement data, which is promising outcome for the exact diagnosis of cancerous tissues.
{"title":"Estimation of Linear and Nonlinear Elastic Parameters of Prostate Tumors Using Artificial Neural Networks : Estimation of Linear and Nonlinear Elastic Parameters of Tumors","authors":"Pooya Tahmasebi, M. M. Dastjerdi, A. Fallah, S. Rashidi","doi":"10.1109/ICBME51989.2020.9319435","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319435","url":null,"abstract":"Due to momentous clinical applications, modeling soft tissues and studying their mechanical properties such as elasticity and hyperelasticity were highly highlighted during the last decade. Because of differences between the mechanical properties of normal and cancerous tissues, precise modeling of mechanical behavior of soft tissues and distinguishing the types of tissues based on their responses to applied stimulations would facilitate the diagnosis of cancerous tissues. The present study sought to noninvasively recognize the mechanical behavior of prostate tissue and its cancerous masses. In this regard, the mechanical parameters of cancerous tissues were accurately estimated using the potent neural network method based on the displacement data. The displacement data related to various tissues and corresponding mechanical properties are required for developing and training neural network models. The finite element modeling using Abaqus software was implemented to simulate prostate tissue behavior and extract the required data for training neural networks. The nonlinear tissue behavior should be considered in soft tissue modeling. For representing the hyperelastic behavior of soft tissues, Ogden and Yeoh models are accurate, which were utilized in the study to prepare the finite element model of prostate tissue containing tumor. In addition, white noise was added into the displacement data obtained by the finite element model for simulating laboratory conditions during extracting tissue data from the model in order to achieve robust neural network models. The results indicate high accuracy and efficiency of the trained neural network models in estimating the mechanical parameters of cancerous prostate tissues based on the displacement data, which is promising outcome for the exact diagnosis of cancerous tissues.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128577276","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 : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319454
Maryam Sadat Fadav, Fatemeh Hasanzadeh, M. Mohebbi, Peyman Hassani Abharian
Currently, the detection of opioid addiction is done by biological tests, but these tests are time-consuming, and their result can be changed by applying some tricks. Using bio-signals such as EEG for detecting opioid abuse can be a good alternative to the current biological tests. In this study, we are aimed to employ EEG signal to detect opioid addiction. The dataset of this study consist of a 19-channel resting-state EEG signal recorded from 22 opioid addicts and 22 healthy normal individuals (without a history of substance abuse). Extracted features of EEG signal include phase-amplitude coupling (PAC) among delta, theta, alpha1, alpha 2, beta1, beta2, and gamma frequency bands. Informative features that can discriminate addicted groups from normal groups are selected by statistical tests and the Minimum Redundancy Maximum Relevance (mRMR) technique. Then selected features are fed to the k-nearest neighbors (KNN) classifier, which is evaluated by Leave-one-out cross-validation. The proposed algorithm classified the addicted and normal group with 93.18% accuracy, 100% sensitivity, and 86.36% specificity. Analyzing the results indicates that delta-beta1 coupling and FZ channel had the most participation in the selected features. The obtained results show that the proposed technique based on EEG signals PAC can be useful in addiction detection.
{"title":"A Machine Learning Approach for Addiction Detection Using Phase Amplitude Coupling of EEG Signals","authors":"Maryam Sadat Fadav, Fatemeh Hasanzadeh, M. Mohebbi, Peyman Hassani Abharian","doi":"10.1109/ICBME51989.2020.9319454","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319454","url":null,"abstract":"Currently, the detection of opioid addiction is done by biological tests, but these tests are time-consuming, and their result can be changed by applying some tricks. Using bio-signals such as EEG for detecting opioid abuse can be a good alternative to the current biological tests. In this study, we are aimed to employ EEG signal to detect opioid addiction. The dataset of this study consist of a 19-channel resting-state EEG signal recorded from 22 opioid addicts and 22 healthy normal individuals (without a history of substance abuse). Extracted features of EEG signal include phase-amplitude coupling (PAC) among delta, theta, alpha1, alpha 2, beta1, beta2, and gamma frequency bands. Informative features that can discriminate addicted groups from normal groups are selected by statistical tests and the Minimum Redundancy Maximum Relevance (mRMR) technique. Then selected features are fed to the k-nearest neighbors (KNN) classifier, which is evaluated by Leave-one-out cross-validation. The proposed algorithm classified the addicted and normal group with 93.18% accuracy, 100% sensitivity, and 86.36% specificity. Analyzing the results indicates that delta-beta1 coupling and FZ channel had the most participation in the selected features. The obtained results show that the proposed technique based on EEG signals PAC can be useful in addiction detection.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132272636","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：