Pub Date : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079315
Siti Munirah Muhammad Ali, W. El-Bouri, M. Mokhtarudin
Age is a major risk for heart failure, which is associated with the reduction in ventricular compliance, increase in arterial stiffening, and increase in systemic vascular resistance. In this study, a lumped-parameter model is used to investigate the effect of aging on the possibility of heart failure occurrence. Model parameters including the systemic and pulmonary arterial compliance and resistance, and the left ventricular elastance are calculated for different ages using a ratio-based method. These parameters are then used in the lumped-parameter model. Our findings show that as age increases, there is a leftward and a rightward shift in the left ventricle and right ventricle pressure-volume loops, respectively. For the left ventricle, there is a decrease in stroke volume and an increase in ventricular pressure as the age increases. This correlates with the occurrence of arterial hypertension in the older population. Meanwhile, the right ventricular pressure is maintained as the population gets older, despite the increase in the stroke volume. This is possibly due to the shift in intraventricular septum that causes an enlargement of the right ventricle as the age increases. This study provides understanding on the effect of age on the occurrence of heart failure.This study demonstrates the relationship of aging with cardiac hemodynamics, which provides the potential risk of heart failure occurrence. Although there are many risk factors that can cause heart failure, aging has been strongly associated with its occurrence. Understanding how age affects heart failure can help to differentiate them from other effects such as dietary, gender, and early cardiovascular diseases including arrhythmia and myocardial infarction.
{"title":"Age-Based Sensitivity Analysis on Cardiac Hemodynamics using Lumped-Parameter Modelling","authors":"Siti Munirah Muhammad Ali, W. El-Bouri, M. Mokhtarudin","doi":"10.1109/IECBES54088.2022.10079315","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079315","url":null,"abstract":"Age is a major risk for heart failure, which is associated with the reduction in ventricular compliance, increase in arterial stiffening, and increase in systemic vascular resistance. In this study, a lumped-parameter model is used to investigate the effect of aging on the possibility of heart failure occurrence. Model parameters including the systemic and pulmonary arterial compliance and resistance, and the left ventricular elastance are calculated for different ages using a ratio-based method. These parameters are then used in the lumped-parameter model. Our findings show that as age increases, there is a leftward and a rightward shift in the left ventricle and right ventricle pressure-volume loops, respectively. For the left ventricle, there is a decrease in stroke volume and an increase in ventricular pressure as the age increases. This correlates with the occurrence of arterial hypertension in the older population. Meanwhile, the right ventricular pressure is maintained as the population gets older, despite the increase in the stroke volume. This is possibly due to the shift in intraventricular septum that causes an enlargement of the right ventricle as the age increases. This study provides understanding on the effect of age on the occurrence of heart failure.This study demonstrates the relationship of aging with cardiac hemodynamics, which provides the potential risk of heart failure occurrence. Although there are many risk factors that can cause heart failure, aging has been strongly associated with its occurrence. Understanding how age affects heart failure can help to differentiate them from other effects such as dietary, gender, and early cardiovascular diseases including arrhythmia and myocardial infarction.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125382837","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}
Early and accurate detection of epileptic seizures is an extremely important therapeutic goal due to the severity of complications it can prevent. To this end, a low-power machine learning-based seizure detection implemented on an FPGA is proposed in this paper. Feature extraction is performed using time domain features which exhibit low hardware implementation complexity as well as high classification performance. A comparison between a Random Forest and a linear Support Vector Machine classifier has been conducted leading to the superior performance of the Random Forest. In addition, the hyperparameters of the Random Forest classifier are optimized to reach the best classification performance as well as to maintain the hardware implementation complexity sufficiently low for medical devices implants. The proposed seizure detector is implemented on a Cyclone V FPGA of the ALTERA DE10-standard board and tested on iEEG signals of six patients from the Bern University Hospital. FPGA implementation results demonstrate 100% seizure detection sensitivity as well as better specificity and faster seizure detection compared to recently published works using random forest classification. The FPGA dynamic power consumption is 0.59 mW which is acceptable for low-power implantable devices.
早期和准确的检测癫痫发作是一个极其重要的治疗目标，因为它可以预防并发症的严重性。为此，本文提出了一种基于FPGA的低功耗机器学习的癫痫检测方法。使用时域特征进行特征提取，具有较低的硬件实现复杂度和较高的分类性能。将随机森林与线性支持向量机分类器进行了比较，结果表明随机森林的性能更优。此外，对随机森林分类器的超参数进行了优化，以达到最佳的分类性能，并使医疗器械植入物的硬件实现复杂性保持在足够低的水平。提出的癫痫检测器在ALTERA de10标准板的Cyclone V FPGA上实现，并在伯尔尼大学医院的6名患者的iEEG信号上进行了测试。与最近发表的使用随机森林分类的作品相比，FPGA实现结果显示了100%的癫痫检测灵敏度，以及更好的特异性和更快的癫痫检测。FPGA动态功耗为0.59 mW，对于低功耗可植入器件是可以接受的。
{"title":"Hardware-Friendly Random Forest Classification of iEEG Signals for Implantable Seizure Detection","authors":"Keyvan Farhang Razi, Raquel Ramos Garcia, Alexandre Schmid","doi":"10.1109/IECBES54088.2022.10079382","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079382","url":null,"abstract":"Early and accurate detection of epileptic seizures is an extremely important therapeutic goal due to the severity of complications it can prevent. To this end, a low-power machine learning-based seizure detection implemented on an FPGA is proposed in this paper. Feature extraction is performed using time domain features which exhibit low hardware implementation complexity as well as high classification performance. A comparison between a Random Forest and a linear Support Vector Machine classifier has been conducted leading to the superior performance of the Random Forest. In addition, the hyperparameters of the Random Forest classifier are optimized to reach the best classification performance as well as to maintain the hardware implementation complexity sufficiently low for medical devices implants. The proposed seizure detector is implemented on a Cyclone V FPGA of the ALTERA DE10-standard board and tested on iEEG signals of six patients from the Bern University Hospital. FPGA implementation results demonstrate 100% seizure detection sensitivity as well as better specificity and faster seizure detection compared to recently published works using random forest classification. The FPGA dynamic power consumption is 0.59 mW which is acceptable for low-power implantable devices.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116130120","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079301
Maximus Liu, M. Shalaginov, Rory Liao, TingyingHelen Zeng
Alzheimer’s disease is a neurologic disorder that hinders many elderly people from being able to live fulfilling lives. There is no cure for this disease, but patients can get medication to improve cognitive function. In order for patients to get more effective treatment, they need to be accurately diagnosed with the disease before it gets worse. In this research, a deep convolutional neural network was developed to predict the severity of early-stage Alzheimer’s disease based on brain MRI images. We compared several of the most commonly used pre-trained convolutional neural network architectures, such as VGG16, VGG19, InceptionV3, ResNet50, Xception, and DenseNet201. Our new finding is that VGG16 can make predictions with the highest accuracy. The neural network has been fine-tuned by varying hyperparameters to maximize the performance of the model. By connecting the output of the VGG16 model to a batch normalization layer followed by four layers of 1000 neurons with a dropout rate of 0.6 between each layer, this model achieved an accuracy of 99.68% on the testing set. While other models can distinguish between no Alzheimer’s disease and severe Alzheimer’s disease, our model can differentiate the more subtle cases of no, very mild, and mild Alzheimer’s disease. Therefore, our approach may promptly and accurately diagnose the early stages of Alzheimer’s disease and help patients to get the necessary treatment before the noticeable symptoms appear.Clinical Relevance–The proposed neural network architecture, combined with the application of the MAGMA colormap to the brain MRI images, could be used to diagnose early-stage Alzheimer’s.
{"title":"A Deep Convolutional Neural Network For Early Diagnosis of Alzheimer’s Disease","authors":"Maximus Liu, M. Shalaginov, Rory Liao, TingyingHelen Zeng","doi":"10.1109/IECBES54088.2022.10079301","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079301","url":null,"abstract":"Alzheimer’s disease is a neurologic disorder that hinders many elderly people from being able to live fulfilling lives. There is no cure for this disease, but patients can get medication to improve cognitive function. In order for patients to get more effective treatment, they need to be accurately diagnosed with the disease before it gets worse. In this research, a deep convolutional neural network was developed to predict the severity of early-stage Alzheimer’s disease based on brain MRI images. We compared several of the most commonly used pre-trained convolutional neural network architectures, such as VGG16, VGG19, InceptionV3, ResNet50, Xception, and DenseNet201. Our new finding is that VGG16 can make predictions with the highest accuracy. The neural network has been fine-tuned by varying hyperparameters to maximize the performance of the model. By connecting the output of the VGG16 model to a batch normalization layer followed by four layers of 1000 neurons with a dropout rate of 0.6 between each layer, this model achieved an accuracy of 99.68% on the testing set. While other models can distinguish between no Alzheimer’s disease and severe Alzheimer’s disease, our model can differentiate the more subtle cases of no, very mild, and mild Alzheimer’s disease. Therefore, our approach may promptly and accurately diagnose the early stages of Alzheimer’s disease and help patients to get the necessary treatment before the noticeable symptoms appear.Clinical Relevance–The proposed neural network architecture, combined with the application of the MAGMA colormap to the brain MRI images, could be used to diagnose early-stage Alzheimer’s.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129718858","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079296
W. Mansor, N. Jaafar, D. P. Morawakage, F. H. Kamaru Zaman, A. Z. Che Daud, N. F. Ahmad Roslan, Z. Hassan
Mirror therapy is a well-known method that can improve motor function after a stroke. Monitoring post-stroke patients’ conditions during mirror therapy is critical for improving rehabilitation oucomes. Electroencephalogram (EEG) based mirror therapy can provide an upper extremity evaluation during treatment. There has been minimal research studying the mu rhythm EEG signals of chronic post-stroke patients. This paper reveals the changes in mu rhythm of chronic post-stroke patients and their comparisons with the normal subjects’ mu rhythm obtained from fingers movements with and without using a mirror. The power spectral density and absolute power are the parameters used to observe the mu rhythm characteristics. It was discovered that post-stroke patients have the greatest mu rhythm suppression, while normal subjects who performed fingers movements without a mirror have the least suppression.
{"title":"Mu Rhythm EEG Signals Analysis during Fingers Movements in Mirror Therapy","authors":"W. Mansor, N. Jaafar, D. P. Morawakage, F. H. Kamaru Zaman, A. Z. Che Daud, N. F. Ahmad Roslan, Z. Hassan","doi":"10.1109/IECBES54088.2022.10079296","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079296","url":null,"abstract":"Mirror therapy is a well-known method that can improve motor function after a stroke. Monitoring post-stroke patients’ conditions during mirror therapy is critical for improving rehabilitation oucomes. Electroencephalogram (EEG) based mirror therapy can provide an upper extremity evaluation during treatment. There has been minimal research studying the mu rhythm EEG signals of chronic post-stroke patients. This paper reveals the changes in mu rhythm of chronic post-stroke patients and their comparisons with the normal subjects’ mu rhythm obtained from fingers movements with and without using a mirror. The power spectral density and absolute power are the parameters used to observe the mu rhythm characteristics. It was discovered that post-stroke patients have the greatest mu rhythm suppression, while normal subjects who performed fingers movements without a mirror have the least suppression.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129697019","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079290
A. Yousif, Z. Omar, Harith Hamoodat, Neibal Younis Al Morad
A brain tumor is an extreme danger to the patient in the current era, leading to confirmed death. Furthermore, the precise classification of brain tumor image is one of the significant issues in clinical analysis fields. Therefore, enhancing tumor classification is required in the medical area. Moreover, brain tumor classification using machine learning (ML) for Magnetic Resonance Imaging scan (MRI) plays a huge vital role in different treatments applications. However, unfortunately, the previous schemes have recorded insufficient accuracy in the classification of brain tumors. The introduced technique contains feature extraction, feature reduction, and classification-based machine learning. Firstly, the low-frequency features of images using Discrete wavelet Transformation (DWT) have been obtained. Secondly, the reduced features have been provided using Principal Component Analysis (PCA). Lastly, The Random Forest (RF) classifier has been used to classify seven tumor classes. RF has obtained classification with a success of accuracy-based-metric with 96.83%. This result explores that the introduced DWT-PCA is more effective than other recent schemes.Clinical Relevance–Tumor Diseases.
{"title":"Multi-Class Tumor Diseases Classification Using Discrete Wavelet Transform and Principal Component Analysis","authors":"A. Yousif, Z. Omar, Harith Hamoodat, Neibal Younis Al Morad","doi":"10.1109/IECBES54088.2022.10079290","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079290","url":null,"abstract":"A brain tumor is an extreme danger to the patient in the current era, leading to confirmed death. Furthermore, the precise classification of brain tumor image is one of the significant issues in clinical analysis fields. Therefore, enhancing tumor classification is required in the medical area. Moreover, brain tumor classification using machine learning (ML) for Magnetic Resonance Imaging scan (MRI) plays a huge vital role in different treatments applications. However, unfortunately, the previous schemes have recorded insufficient accuracy in the classification of brain tumors. The introduced technique contains feature extraction, feature reduction, and classification-based machine learning. Firstly, the low-frequency features of images using Discrete wavelet Transformation (DWT) have been obtained. Secondly, the reduced features have been provided using Principal Component Analysis (PCA). Lastly, The Random Forest (RF) classifier has been used to classify seven tumor classes. RF has obtained classification with a success of accuracy-based-metric with 96.83%. This result explores that the introduced DWT-PCA is more effective than other recent schemes.Clinical Relevance–Tumor Diseases.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125990060","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079597
N. F. Amlee, N. Nazmi, M. K. Shabdin, I. Bahiuddin, S. Mazlan, N. A. Nordin
The higher demand for sensors and actuators devices is a result of machines and robotic devices incorporating electronics devices in its system. Intelligent material like hydrogel-based magnetorheological plastomer (HMRP) can be considered for its potential to be used in such system, particularly in a low force sensing system. However, the studies on HMRP’s potential to be used in a low force detecting system has not been further explored. In this paper, HMRP with 0 wt. % to 15 wt.% of graphite were fabricated and their resistance was tested under applied force ranging from 0 N - 5 N. The resistance was also measured in the absence and presence of magnetic field. With 15 wt.% of graphite, the resistance in the HMRP samples could reach as low as ~3000 Ω while applying load up to 5 N resulted in resistance as low as ~600 Ω in the absence of magnetic field. In the presence of 0.141 mT of magnetic field, the resistance of HRMP sample with 15 wt.% of graphite could reach as low as ~2500 Ω. The establishment of this relationship indicates that HMRP has the potential to be used in a sensing system.Clinical Relevance– This research can be used as a base to help in improving methods for physiology or therapy.
{"title":"Force Sensing Performance of Hydrogel-based Magnetorheological Plastomers with Graphite","authors":"N. F. Amlee, N. Nazmi, M. K. Shabdin, I. Bahiuddin, S. Mazlan, N. A. Nordin","doi":"10.1109/IECBES54088.2022.10079597","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079597","url":null,"abstract":"The higher demand for sensors and actuators devices is a result of machines and robotic devices incorporating electronics devices in its system. Intelligent material like hydrogel-based magnetorheological plastomer (HMRP) can be considered for its potential to be used in such system, particularly in a low force sensing system. However, the studies on HMRP’s potential to be used in a low force detecting system has not been further explored. In this paper, HMRP with 0 wt. % to 15 wt.% of graphite were fabricated and their resistance was tested under applied force ranging from 0 N - 5 N. The resistance was also measured in the absence and presence of magnetic field. With 15 wt.% of graphite, the resistance in the HMRP samples could reach as low as ~3000 Ω while applying load up to 5 N resulted in resistance as low as ~600 Ω in the absence of magnetic field. In the presence of 0.141 mT of magnetic field, the resistance of HRMP sample with 15 wt.% of graphite could reach as low as ~2500 Ω. The establishment of this relationship indicates that HMRP has the potential to be used in a sensing system.Clinical Relevance– This research can be used as a base to help in improving methods for physiology or therapy.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128911113","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079316
M. Khant, Daniel Ts Lee, D. Gouwanda, A. Gopalai, K. Lim, Chee Choong Foong
Gait analysis is the study of human locomotion. It plays an essential role in the diagnosis and rehabilitation of gait abnormalities, the study of physiological changes associated with ageing, and the treatment of injuries. Muscle activity is an important gait parameter that controls joint function during walking and provides valuable information about the gait quality. However, current techniques to measure muscle activity, such as electromyogram (EMG) and musculoskeletal modelling tools, have drawbacks. This study develops an artificial neural network (ANN) method to estimate eight lower extremity muscle activities using pelvis, hip, knee and ankle joint angles. It uses an online gait database that contains kinematic and kinetic gait parameters and lower limb EMG. Four training algorithms were explored and investigated. Despite the noticeable differences between the actual and the estimated muscle activities, e.g. gluteus maximus and bicep femoris, the results demonstrate the feasibility of the proposed method in determining the muscle behaviour during walking. The study also shows the potentials of machine learning to compensate for the lack of modality and to provide an insight on the dynamics of muscles in gait. Clinical Relevance- Gait analysis is important in clinical and rehabilitation settings. The proposed method has the potential in reducing the dependency on EMGs and can be an alternative to the musculoskeletal modelling tools in diagnosing, treating, and rehabilitating gait abnormalities.
{"title":"A Neural Network Approach to Estimate Lower Extremity Muscle Activity during Walking","authors":"M. Khant, Daniel Ts Lee, D. Gouwanda, A. Gopalai, K. Lim, Chee Choong Foong","doi":"10.1109/IECBES54088.2022.10079316","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079316","url":null,"abstract":"Gait analysis is the study of human locomotion. It plays an essential role in the diagnosis and rehabilitation of gait abnormalities, the study of physiological changes associated with ageing, and the treatment of injuries. Muscle activity is an important gait parameter that controls joint function during walking and provides valuable information about the gait quality. However, current techniques to measure muscle activity, such as electromyogram (EMG) and musculoskeletal modelling tools, have drawbacks. This study develops an artificial neural network (ANN) method to estimate eight lower extremity muscle activities using pelvis, hip, knee and ankle joint angles. It uses an online gait database that contains kinematic and kinetic gait parameters and lower limb EMG. Four training algorithms were explored and investigated. Despite the noticeable differences between the actual and the estimated muscle activities, e.g. gluteus maximus and bicep femoris, the results demonstrate the feasibility of the proposed method in determining the muscle behaviour during walking. The study also shows the potentials of machine learning to compensate for the lack of modality and to provide an insight on the dynamics of muscles in gait. Clinical Relevance- Gait analysis is important in clinical and rehabilitation settings. The proposed method has the potential in reducing the dependency on EMGs and can be an alternative to the musculoskeletal modelling tools in diagnosing, treating, and rehabilitating gait abnormalities.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122227243","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079507
T. R. Shivaraja, K. Chellappan, N. Kamal, R. Remli
Personalized remote monitoring healthcare devices have begun emerging in the industry over the years, slowly setting a new standard for long term monitoring services. In this study, the researchers are addressing epilepsy. This neurological disorder hinders mobility freedom and may affect humans of any age, often starting in childhood or people over 60 years old. Diagnosing epileptic patients still stands as a challenge due to similar symptoms shown by other medical conditions such as migraines, fainting and panic attacks, often unable to be ruled as epilepsy without detecting seizure. Electroencephalogram (EEG) has proven to be the most helpful procedure for diagnosis of epilepsy. Interictal epileptiform discharges (IED), detected in EEG aids in differentiating epileptic and other nonepileptic episodes. Currently, available EEG devices are often bulky and restricted to be in use of clinical environments, limiting treatment process among epilepsy patients. The aim of this research is to present a personalized mobile EEG device for epilepsy monitoring and management. A customizable dry electrode EEG headset with 16-channel was assembled and configured. A server and an Android based mobile application were also developed to aid in remote monitoring regardless of location and available network. The device was tested and validated for signal reliability by a neurologist at the Neurology Lab of Canselor Tuanku Muhriz Hospital. The proposed device has potential to be solution for numerous limitations in current epilepsy treatment decision and may even be vital in addressing the drawback of recent pandemic. The outcome of the study is expected to boost and improve neurological research and clinical diagnosis in patient monitoring.
{"title":"Personalization of a Mobile EEG for Remote Monitoring","authors":"T. R. Shivaraja, K. Chellappan, N. Kamal, R. Remli","doi":"10.1109/IECBES54088.2022.10079507","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079507","url":null,"abstract":"Personalized remote monitoring healthcare devices have begun emerging in the industry over the years, slowly setting a new standard for long term monitoring services. In this study, the researchers are addressing epilepsy. This neurological disorder hinders mobility freedom and may affect humans of any age, often starting in childhood or people over 60 years old. Diagnosing epileptic patients still stands as a challenge due to similar symptoms shown by other medical conditions such as migraines, fainting and panic attacks, often unable to be ruled as epilepsy without detecting seizure. Electroencephalogram (EEG) has proven to be the most helpful procedure for diagnosis of epilepsy. Interictal epileptiform discharges (IED), detected in EEG aids in differentiating epileptic and other nonepileptic episodes. Currently, available EEG devices are often bulky and restricted to be in use of clinical environments, limiting treatment process among epilepsy patients. The aim of this research is to present a personalized mobile EEG device for epilepsy monitoring and management. A customizable dry electrode EEG headset with 16-channel was assembled and configured. A server and an Android based mobile application were also developed to aid in remote monitoring regardless of location and available network. The device was tested and validated for signal reliability by a neurologist at the Neurology Lab of Canselor Tuanku Muhriz Hospital. The proposed device has potential to be solution for numerous limitations in current epilepsy treatment decision and may even be vital in addressing the drawback of recent pandemic. The outcome of the study is expected to boost and improve neurological research and clinical diagnosis in patient monitoring.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133006993","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079482
Hitesh Khunti, B. Rao, S. Obrzut
Low radiopharmaceutical dose and reduced scan time for molecular medical tomographic imaging are pursued for wider and safer medical applications. Towards this goal we propose an analytical approach to optimally reduce scanning duration or radiopharmaceutical dose for Single Photon Emission Computed Tomographic (SPECT) techniques, while not compromising on reconstructed image accuracy and reconstruction stability. In addition, we provide statistical guarantees to ensure generalization. This is achieved by: (a) utilizing the observation model and Fisher information driven scan strategy, (b) coordinating scanning with point spread function and prior of the reconstruction algorithm, and (c) providing statistical guarantees on reconstructed image variance through the Cramer-Rao bound. Our approach distributes the given total scanning duration optimally across scan angles to minimize Mean Square Error for a given image reconstruction algorithm. It coordinates the duration at each scan angle to ensure optimal information flow to the chosen reconstruction algorithm. For maximum likelihood (ML) estimators we derive a globally optimal closed form equation for angular sampling, and for maximum a posteriori (MAP) estimators we show the optimization problem is a difference of convex functions which can be efficiently optimized. The efficacy of the proposed scanning strategy is quantified through Monte Carlo simulations using real SPECT images and synthetic phantoms. The proposed algorithm achieves more than 2 dB PSNR improvement over conventional uniform scanning approach for real SPECT images. This improvement could be traded in to achieve more than 50% reduction in scan duration.
{"title":"Information Driven Angular Sampling for Reliable and Efficient SPECT Imaging","authors":"Hitesh Khunti, B. Rao, S. Obrzut","doi":"10.1109/IECBES54088.2022.10079482","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079482","url":null,"abstract":"Low radiopharmaceutical dose and reduced scan time for molecular medical tomographic imaging are pursued for wider and safer medical applications. Towards this goal we propose an analytical approach to optimally reduce scanning duration or radiopharmaceutical dose for Single Photon Emission Computed Tomographic (SPECT) techniques, while not compromising on reconstructed image accuracy and reconstruction stability. In addition, we provide statistical guarantees to ensure generalization. This is achieved by: (a) utilizing the observation model and Fisher information driven scan strategy, (b) coordinating scanning with point spread function and prior of the reconstruction algorithm, and (c) providing statistical guarantees on reconstructed image variance through the Cramer-Rao bound. Our approach distributes the given total scanning duration optimally across scan angles to minimize Mean Square Error for a given image reconstruction algorithm. It coordinates the duration at each scan angle to ensure optimal information flow to the chosen reconstruction algorithm. For maximum likelihood (ML) estimators we derive a globally optimal closed form equation for angular sampling, and for maximum a posteriori (MAP) estimators we show the optimization problem is a difference of convex functions which can be efficiently optimized. The efficacy of the proposed scanning strategy is quantified through Monte Carlo simulations using real SPECT images and synthetic phantoms. The proposed algorithm achieves more than 2 dB PSNR improvement over conventional uniform scanning approach for real SPECT images. This improvement could be traded in to achieve more than 50% reduction in scan duration.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132363399","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 : 2022-12-07DOI: 10.1109/IECBES54088.2022.10079580
Reem Brome, J. Nasreddine, F. Bonnardot, M. Mohamed el Badaoui, M. Diab
Falls prevention among the elderly community is regarded as one of the most critical public health topics in today’s aging society. Identifying the risk of falling in elderly individuals is considered the first step in prevention. In this study we present an alternative method of representing signal cyclostationarity as heat-map images and using convolutional neural network (CNN) with the ADAM optimization method to predict the risk of falling in 411 subjects over the age of 65. The study involved three different modes of walking: normal straight walking (MS), walking straight while calling out names of animals (MF), and walking straight while de-counting from the number 50 (MD). Data from the elderly participants were collected from wearable insole pressure sensors. Results obtained in this study showed improved prediction capability (increased accuracy by 6.8%) compared to traditional machine learning methods. In addition, the proposed method achieved improved results with reduced time in data collection as it requires the subject to perform one type of walking mode (MD) instead of three.
{"title":"Fall Risk Assessment Using Pressure Insole Sensors and Convolutional Neural Networks","authors":"Reem Brome, J. Nasreddine, F. Bonnardot, M. Mohamed el Badaoui, M. Diab","doi":"10.1109/IECBES54088.2022.10079580","DOIUrl":"https://doi.org/10.1109/IECBES54088.2022.10079580","url":null,"abstract":"Falls prevention among the elderly community is regarded as one of the most critical public health topics in today’s aging society. Identifying the risk of falling in elderly individuals is considered the first step in prevention. In this study we present an alternative method of representing signal cyclostationarity as heat-map images and using convolutional neural network (CNN) with the ADAM optimization method to predict the risk of falling in 411 subjects over the age of 65. The study involved three different modes of walking: normal straight walking (MS), walking straight while calling out names of animals (MF), and walking straight while de-counting from the number 50 (MD). Data from the elderly participants were collected from wearable insole pressure sensors. Results obtained in this study showed improved prediction capability (increased accuracy by 6.8%) compared to traditional machine learning methods. In addition, the proposed method achieved improved results with reduced time in data collection as it requires the subject to perform one type of walking mode (MD) instead of three.","PeriodicalId":146681,"journal":{"name":"2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129553767","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：