Pub Date : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604841
Freddy Al-Hazzouri, Farah Bazzi, Ahmad Diab
This study investigates the use of textural features and texture maps in building a brain age prediction model using two publicly available datasets (IXI and OASIS), also the usage of texture maps to calculate the brain age delta and use it as a biomarker of dementia and investigate accelerated aging for demented subjects.
{"title":"Texture Analysis of Brain MR Images for Age Detection","authors":"Freddy Al-Hazzouri, Farah Bazzi, Ahmad Diab","doi":"10.1109/ICABME53305.2021.9604841","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604841","url":null,"abstract":"This study investigates the use of textural features and texture maps in building a brain age prediction model using two publicly available datasets (IXI and OASIS), also the usage of texture maps to calculate the brain age delta and use it as a biomarker of dementia and investigate accelerated aging for demented subjects.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122758110","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604856
Jumana Eyadeh, T. Salameh, Areej Alshurman, Roa'a Alakkish, A. Al-Zaben
In general, many of the in vivo measurements taken inside the body have direct contact with body fluids and most importantly, blood. Biocompatibility is required to prevent any adverse effects that may result from this interaction. On the other hand, optimal performance of the medical device is also a concern. For Example, the performance of invasive solid-state blood pressure sensors may be affected by the packaging materials used to achieve biocompatibility.This paper investigates the effect of different packaging biomaterials with different thicknesses on the solid-state blood pressure sensor response under dynamic measurement. Using fluid-structure interaction formulism, finite element analysis is used to explore the effect of the packaging material on the sensor’s response. In addition, a comparison of the different biomaterials effects is presented to enable designers to select the optimal configuration.
{"title":"FSI Model to Investigate Effects of Covering Material on Invasive Blood Pressure Sensor Performance","authors":"Jumana Eyadeh, T. Salameh, Areej Alshurman, Roa'a Alakkish, A. Al-Zaben","doi":"10.1109/ICABME53305.2021.9604856","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604856","url":null,"abstract":"In general, many of the in vivo measurements taken inside the body have direct contact with body fluids and most importantly, blood. Biocompatibility is required to prevent any adverse effects that may result from this interaction. On the other hand, optimal performance of the medical device is also a concern. For Example, the performance of invasive solid-state blood pressure sensors may be affected by the packaging materials used to achieve biocompatibility.This paper investigates the effect of different packaging biomaterials with different thicknesses on the solid-state blood pressure sensor response under dynamic measurement. Using fluid-structure interaction formulism, finite element analysis is used to explore the effect of the packaging material on the sensor’s response. In addition, a comparison of the different biomaterials effects is presented to enable designers to select the optimal configuration.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128741353","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604879
Israa Alnazer, O. Falou, T. Urruty, P. Bourdon, C. Guillevin, Mathieu Naudin, Mohamad Khalil, Ahmad Shahin, C. Fernandez-Maloigne
Non-invasive assessment of kidney function and structure remains of clinical importance in the diagnosis and prognosis of chronic kidney disease. This work aims to evaluate the role of textures extracted from functional magnetic resonance imaging in renal dysfunction detection by differentiating healthy and chronic kidney disease patients. Textural descriptors are extracted from apparent diffusion coefficient, blood oxygenation level dependent images and T2 maps. Synthetic resampling technique is performed to account for imbalanced classes and increase the variety of sample domain. Principal component analysis projection is applied to eliminate irrelevant features and compact the dataset. The performance of linear discriminant analysis, logistic regression and Naïve Bayes classifiers in terms of discriminating healthy and affected kidney is evaluated. The results of this preliminary study support the fact that chronic kidney disease affects texture parameters significantly. Textures-based predictive models have shown promise in accurate and safe renal function evaluation (accuracy, sensitivity and AUC up to 98%, 98% and 1 respectively).
{"title":"Usefulness of Functional MRI Textures in the Evaluation of Renal Function","authors":"Israa Alnazer, O. Falou, T. Urruty, P. Bourdon, C. Guillevin, Mathieu Naudin, Mohamad Khalil, Ahmad Shahin, C. Fernandez-Maloigne","doi":"10.1109/ICABME53305.2021.9604879","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604879","url":null,"abstract":"Non-invasive assessment of kidney function and structure remains of clinical importance in the diagnosis and prognosis of chronic kidney disease. This work aims to evaluate the role of textures extracted from functional magnetic resonance imaging in renal dysfunction detection by differentiating healthy and chronic kidney disease patients. Textural descriptors are extracted from apparent diffusion coefficient, blood oxygenation level dependent images and T2 maps. Synthetic resampling technique is performed to account for imbalanced classes and increase the variety of sample domain. Principal component analysis projection is applied to eliminate irrelevant features and compact the dataset. The performance of linear discriminant analysis, logistic regression and Naïve Bayes classifiers in terms of discriminating healthy and affected kidney is evaluated. The results of this preliminary study support the fact that chronic kidney disease affects texture parameters significantly. Textures-based predictive models have shown promise in accurate and safe renal function evaluation (accuracy, sensitivity and AUC up to 98%, 98% and 1 respectively).","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114117711","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604830
Khouloud Lobnan Issa, Abbas Rammal, Ahmad Rammal, M. Ayache
Premature Ventricular Contractions (PVCs), a common type of cardiac arrhythmia, can be identified by analyzing electrocardiogram (ECG) signals. If not treated on time, PVCs become life-threatening. In this paper, a high-performance approach is proposed for detecting PVCs in an unsupervised manner. The main objective is to perform an automatic PVCs detection in ECG without prior knowledge. Ten different statistical features are extracted to represent various characteristics of the signal. Thereafter, the proposed approach explores PVCs detection by two different strategies. Performance evaluation results over the MIT-BIH Arrhythmia Database (MIT-BIH-AD) show that the strategy based on Agglomerative Hierarchical Clustering (AHC) Method outperforms K-means Clustering Method with an average Accuracy (ACC), Specificity (SPE), Sensitivity (SEN), and Positive Predictive Value (PPV) of 98.43%, 99.23%, 94.47%, and 96.67%, respectively. With less complexity and computation load, AHC can be an accurate candidate for PVCs detection to be used in clinical applications.
{"title":"Fully Automatic Detection of Premature Ventricular Contractions: A New Approach Based On Unsupervised Learning","authors":"Khouloud Lobnan Issa, Abbas Rammal, Ahmad Rammal, M. Ayache","doi":"10.1109/ICABME53305.2021.9604830","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604830","url":null,"abstract":"Premature Ventricular Contractions (PVCs), a common type of cardiac arrhythmia, can be identified by analyzing electrocardiogram (ECG) signals. If not treated on time, PVCs become life-threatening. In this paper, a high-performance approach is proposed for detecting PVCs in an unsupervised manner. The main objective is to perform an automatic PVCs detection in ECG without prior knowledge. Ten different statistical features are extracted to represent various characteristics of the signal. Thereafter, the proposed approach explores PVCs detection by two different strategies. Performance evaluation results over the MIT-BIH Arrhythmia Database (MIT-BIH-AD) show that the strategy based on Agglomerative Hierarchical Clustering (AHC) Method outperforms K-means Clustering Method with an average Accuracy (ACC), Specificity (SPE), Sensitivity (SEN), and Positive Predictive Value (PPV) of 98.43%, 99.23%, 94.47%, and 96.67%, respectively. With less complexity and computation load, AHC can be an accurate candidate for PVCs detection to be used in clinical applications.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123425907","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604818
Sepaldeep Singh Dhaliwal, A. Belarouci, Mario Sanz Lopez, Fabien Verbrugghe, Othman Lakhal, G. Dherbomez, T. Chettibi, R. Merzouki
This paper presents a novel concept for robotized adaptive prostate Brachytherapy (BT) under Magnetic Resonance Imaging (MRI). The Cooperative Brachytherapy (CoBra) concept with compact modular design robot-guide is capable of serving mount of Low Dose Rate (LDR-BT), High Dose Rate (HDR-BT), and Biopsy modules and operate in-bore 3 Tesla MRI. CoBra integrates the multi-components - radiotherapy, imaging, needle, robot-guide as one global system. CoBra MR-robot is a 5 degrees-of-freedom, actuated using non-magnetic piezo-ultrasonic motors. CoBra Robot intends to place BT seeds to the patient positioned in-bore in lithotomy under MRI-feedback control for the purpose of adaptive brachytherapy. The robot is capable of posing biopsy and BT needle modules for both straight and oblique orientation. It is controlled with an absolute sensor for position sensing. The paper presents recent advances in designing a robotic system for adaptive tumor-targeting in-bore intraoperatively under real-time MRI.
{"title":"CoBra: Towards Adaptive Robotized Prostate Brachytherapy under MRI Guidance","authors":"Sepaldeep Singh Dhaliwal, A. Belarouci, Mario Sanz Lopez, Fabien Verbrugghe, Othman Lakhal, G. Dherbomez, T. Chettibi, R. Merzouki","doi":"10.1109/ICABME53305.2021.9604818","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604818","url":null,"abstract":"This paper presents a novel concept for robotized adaptive prostate Brachytherapy (BT) under Magnetic Resonance Imaging (MRI). The Cooperative Brachytherapy (CoBra) concept with compact modular design robot-guide is capable of serving mount of Low Dose Rate (LDR-BT), High Dose Rate (HDR-BT), and Biopsy modules and operate in-bore 3 Tesla MRI. CoBra integrates the multi-components - radiotherapy, imaging, needle, robot-guide as one global system. CoBra MR-robot is a 5 degrees-of-freedom, actuated using non-magnetic piezo-ultrasonic motors. CoBra Robot intends to place BT seeds to the patient positioned in-bore in lithotomy under MRI-feedback control for the purpose of adaptive brachytherapy. The robot is capable of posing biopsy and BT needle modules for both straight and oblique orientation. It is controlled with an absolute sensor for position sensing. The paper presents recent advances in designing a robotic system for adaptive tumor-targeting in-bore intraoperatively under real-time MRI.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123344454","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604862
M. Ayache, Hussien Kanaan, Kawthar Kassir, Yasser Kassir
Speech Recognition Software is a computer program that is trained to take the input of human speech, interpret it, and transcribe it into text. Most recently, the field has benefited from advances in deep learning and big data. The advances are evidenced not only by the surge of academic papers published in the field, but more importantly by the worldwide industry adoption of a variety of deep learning methods in designing and deploying speech recognition systems. The objective of this paper is to propose an advanced and accurate end-user software system that is able to recognize specific commands to control a robot to perform specified tasks in a hospital. This model will be based on Deep Learning since it is effective in models having huge data as for the two versions of Google TensorFlow and AIY datasets used in our model. Convolutional neural network will be used since it is able to extract features from the dataset instead of traditional methods of feature extraction, thus saving training time and reducing the complexity of the system. With addition to that, NVIDIA CUDA will be also used to train the model with GPU to decrease the training time. During training, some experiments have been done to see the effect of some parameters on the results of the system, and to make sure that the chosen parameters in our model are the best. The results indicate that the training, validation, and testing accuracies of the proposed approach were high, the training duration reached very low values due to the innovation used (CUDA Toolkit) and the commands were successfully recognized by the model. These results outcome the results of the papers that developed similar work which will be presented in the coming sections.
{"title":"Speech Command Recognition Using Deep Learning","authors":"M. Ayache, Hussien Kanaan, Kawthar Kassir, Yasser Kassir","doi":"10.1109/ICABME53305.2021.9604862","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604862","url":null,"abstract":"Speech Recognition Software is a computer program that is trained to take the input of human speech, interpret it, and transcribe it into text. Most recently, the field has benefited from advances in deep learning and big data. The advances are evidenced not only by the surge of academic papers published in the field, but more importantly by the worldwide industry adoption of a variety of deep learning methods in designing and deploying speech recognition systems. The objective of this paper is to propose an advanced and accurate end-user software system that is able to recognize specific commands to control a robot to perform specified tasks in a hospital. This model will be based on Deep Learning since it is effective in models having huge data as for the two versions of Google TensorFlow and AIY datasets used in our model. Convolutional neural network will be used since it is able to extract features from the dataset instead of traditional methods of feature extraction, thus saving training time and reducing the complexity of the system. With addition to that, NVIDIA CUDA will be also used to train the model with GPU to decrease the training time. During training, some experiments have been done to see the effect of some parameters on the results of the system, and to make sure that the chosen parameters in our model are the best. The results indicate that the training, validation, and testing accuracies of the proposed approach were high, the training duration reached very low values due to the innovation used (CUDA Toolkit) and the commands were successfully recognized by the model. These results outcome the results of the papers that developed similar work which will be presented in the coming sections.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130048596","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604859
A. Fenneteau, P. Bourdon, D. Helbert, C. Fernandez-Maloigne, C. Habas, R. Guillevin
In this study we propose to improve an existing artificial neural network architecture, the MPU-net, which is designed for having very few parameters for multiple sclerosis lesion segmentation on magnetic resonance images. With this improved architecture we conducted a study to assess the influence of the number of training examples on the model performance and generalization. The question behind this study is: "With an appropriate architecture, how many patients do we need?". We evaluated 9 different adaptations of the MPU-net architecture. Then, after the selection of the best architecture we learned the model multiple times with different numbers of patients and assessed its performances. The addition of deep supervision, the reduction of number of convolutional layers and the addition of regularization layers produced a more stable and performant architecture. Learnings of selected model with only 10 exams delivered performances equivalent to learnings with 23 exams. So, in our experimental setup, it is possible to learn a performant model with only 10 fully annotated examples.
{"title":"CNN for multiple sclerosis lesion segmentation: How many patients for a fully supervised method?","authors":"A. Fenneteau, P. Bourdon, D. Helbert, C. Fernandez-Maloigne, C. Habas, R. Guillevin","doi":"10.1109/ICABME53305.2021.9604859","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604859","url":null,"abstract":"In this study we propose to improve an existing artificial neural network architecture, the MPU-net, which is designed for having very few parameters for multiple sclerosis lesion segmentation on magnetic resonance images. With this improved architecture we conducted a study to assess the influence of the number of training examples on the model performance and generalization. The question behind this study is: \"With an appropriate architecture, how many patients do we need?\". We evaluated 9 different adaptations of the MPU-net architecture. Then, after the selection of the best architecture we learned the model multiple times with different numbers of patients and assessed its performances. The addition of deep supervision, the reduction of number of convolutional layers and the addition of regularization layers produced a more stable and performant architecture. Learnings of selected model with only 10 exams delivered performances equivalent to learnings with 23 exams. So, in our experimental setup, it is possible to learn a performant model with only 10 fully annotated examples.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133303235","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604855
C. Lipps, Lea Bergkemper, H. Schotten
Though biometrics are moving into a recent focus, they are actually the oldest form of identification. Humans, and even some animals, recognize each other by their voice, body shape and face. But with the emergence of sensors close to the body combined with the possibilities of Artificial Intelligence (AI), other factors such as the gait and behaviorals are also becoming of increasingly interest.Therefore, this paper illustrates how individuals, supported by Machine Learning (ML) methods, can be distinguished based on their Electrocardiogram (ECG) signals. ECG values recorded with an Microcontroller Unit (MCU) are used and the applicability of three different ML methods -K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Gaussian Naive Bayes (GNB)- are compared. The results also indicate the potential of ML in terms of applications in (tele)medicine and disease prevention.
{"title":"Distinguishing Hearts: How Machine Learning identifies People based on their Heartbeat","authors":"C. Lipps, Lea Bergkemper, H. Schotten","doi":"10.1109/ICABME53305.2021.9604855","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604855","url":null,"abstract":"Though biometrics are moving into a recent focus, they are actually the oldest form of identification. Humans, and even some animals, recognize each other by their voice, body shape and face. But with the emergence of sensors close to the body combined with the possibilities of Artificial Intelligence (AI), other factors such as the gait and behaviorals are also becoming of increasingly interest.Therefore, this paper illustrates how individuals, supported by Machine Learning (ML) methods, can be distinguished based on their Electrocardiogram (ECG) signals. ECG values recorded with an Microcontroller Unit (MCU) are used and the applicability of three different ML methods -K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Gaussian Naive Bayes (GNB)- are compared. The results also indicate the potential of ML in terms of applications in (tele)medicine and disease prevention.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114948707","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604875
Mazen Kabbara, Joy Khayat, Saja Haj Hassan, F. Ayoubi, A. R. Sarraj
It is claimed that humans are particularly sensitive to biological motion. A biological motion is a pattern and class of articulated motion specific to animals and humans. The ability to perceive biological motion pattern over non-biological ones has been discussed in the research literature. Johansson et al. in 1973 has confirmed that human can perceive biological motion pattern from movements of little dots. Here, we investigate the difference between observing biological and non-biological task of squat vertical jump (SVJ). Action Observation has been proved also to improve motor performance of SVJ in several previous studies. Results of this study didn’t show any difference in observing both movements upon the performance of SVJ. We concluded that a kinogram may be internally represented from previous daily life experiences or scenes and therefore improvement of SVJ was confirmed with AO, but for both stimuli. Further research should stress the importance of the cognitive stimuli et its meaning for the observers.
据说人类对生物运动特别敏感。生物运动是动物和人类特有的关节运动的模式和类别。对非生物运动模式的感知能力已经在研究文献中进行了讨论。Johansson et al.在1973年证实了人类可以从小点的运动中感知生物的运动模式。在此，我们研究了蹲下垂直跳(SVJ)的生物和非生物任务的观察差异。在之前的一些研究中，动作观察也被证明可以改善上下颌关节的运动性能。本研究的结果显示，观察两种运动对SVJ的表现没有任何差异。我们得出的结论是，运动图可能是由以前的日常生活经历或场景内部表示的，因此，AO证实了SVJ的改善，但对于两种刺激。进一步的研究应强调认知刺激的重要性及其对观察者的意义。
{"title":"Observation of biological vs non-biological of squat vertical jump to improve the motor performance of a similar task","authors":"Mazen Kabbara, Joy Khayat, Saja Haj Hassan, F. Ayoubi, A. R. Sarraj","doi":"10.1109/ICABME53305.2021.9604875","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604875","url":null,"abstract":"It is claimed that humans are particularly sensitive to biological motion. A biological motion is a pattern and class of articulated motion specific to animals and humans. The ability to perceive biological motion pattern over non-biological ones has been discussed in the research literature. Johansson et al. in 1973 has confirmed that human can perceive biological motion pattern from movements of little dots. Here, we investigate the difference between observing biological and non-biological task of squat vertical jump (SVJ). Action Observation has been proved also to improve motor performance of SVJ in several previous studies. Results of this study didn’t show any difference in observing both movements upon the performance of SVJ. We concluded that a kinogram may be internally represented from previous daily life experiences or scenes and therefore improvement of SVJ was confirmed with AO, but for both stimuli. Further research should stress the importance of the cognitive stimuli et its meaning for the observers.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115421733","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 : 2021-10-07DOI: 10.1109/ICABME53305.2021.9604812
A. Zaylaa, Ghiwa I. Wehbe, AbdulJalil M. Ouahabi
Artificial Intelligence (AI) is significantly gaining interest in the field of Diagnostic and Functional Optical Imaging. As cutting-edge algorithms for decision-making are vast and medical imaging machines are diverse, the choice of the ultimate algorithm remains challenging. As a breakthrough in the field, our aim is to explore the adequate machine and deep learning algorithms that improve the classification of Optical Coherence Tomography Angiography (OCTA) Images, between normal and Diabetic Retinopathy (DR) images. The target was to provide an automatic paradigm for the medical staff to detect the presence of DR Lesions from OCTA images for diagnostic and monitoring purposes. Data were collected prospectively over a year from a comprehensive medical center in Lebanon. The mixed Convolution Neural Network (CNN)-Support Vector Machine Network (CNN, SVM) algorithm was utilized in the new paradigm and compared to the feed forward backpropagation NN, to the SVM and to the modified SVM. Results were evaluated independently for the presence or absence of DR using statistical metrics. Experimental results showcased promising association of deep learning to the early diagnosis of DR. Results manifested the high performance of the new paradigm, where the mixed algorithm applied to the functional OCTA surpassed the performance of the feed forward backpropagation NN. The sensitivity of the mixed (CNN, SVM) algorithm was 22.22% higher than that obtained by the feed forward backpropagation NN. Moreover, the specificity of classification of DR from OCTA images using mixed (CNN, SVM) algorithm was 24.44% higher than that obtained by the feed forward backpropagation NN. The precision was 25.47% higher in the new paradigm than that obtained by the feed forward backpropagation network, and the accuracy was 23.35% higher in the mixed (CNN, SVM) than that obtained by the feed forward backpropagation NN. This high performance plays a massive role in improving the diagnosis of DR, and thus Healthcare system and processing of information. As a future prospect, we aim to consider more algorithms and variables in the diagnosis of DR from OCTA images.
{"title":"Bringing AI to Automatic Diagnosis of Diabetic Retinopathy from Optical Coherence Tomography Angiography","authors":"A. Zaylaa, Ghiwa I. Wehbe, AbdulJalil M. Ouahabi","doi":"10.1109/ICABME53305.2021.9604812","DOIUrl":"https://doi.org/10.1109/ICABME53305.2021.9604812","url":null,"abstract":"Artificial Intelligence (AI) is significantly gaining interest in the field of Diagnostic and Functional Optical Imaging. As cutting-edge algorithms for decision-making are vast and medical imaging machines are diverse, the choice of the ultimate algorithm remains challenging. As a breakthrough in the field, our aim is to explore the adequate machine and deep learning algorithms that improve the classification of Optical Coherence Tomography Angiography (OCTA) Images, between normal and Diabetic Retinopathy (DR) images. The target was to provide an automatic paradigm for the medical staff to detect the presence of DR Lesions from OCTA images for diagnostic and monitoring purposes. Data were collected prospectively over a year from a comprehensive medical center in Lebanon. The mixed Convolution Neural Network (CNN)-Support Vector Machine Network (CNN, SVM) algorithm was utilized in the new paradigm and compared to the feed forward backpropagation NN, to the SVM and to the modified SVM. Results were evaluated independently for the presence or absence of DR using statistical metrics. Experimental results showcased promising association of deep learning to the early diagnosis of DR. Results manifested the high performance of the new paradigm, where the mixed algorithm applied to the functional OCTA surpassed the performance of the feed forward backpropagation NN. The sensitivity of the mixed (CNN, SVM) algorithm was 22.22% higher than that obtained by the feed forward backpropagation NN. Moreover, the specificity of classification of DR from OCTA images using mixed (CNN, SVM) algorithm was 24.44% higher than that obtained by the feed forward backpropagation NN. The precision was 25.47% higher in the new paradigm than that obtained by the feed forward backpropagation network, and the accuracy was 23.35% higher in the mixed (CNN, SVM) than that obtained by the feed forward backpropagation NN. This high performance plays a massive role in improving the diagnosis of DR, and thus Healthcare system and processing of information. As a future prospect, we aim to consider more algorithms and variables in the diagnosis of DR from OCTA images.","PeriodicalId":294393,"journal":{"name":"2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115520669","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：