Pub Date : 2020-11-26DOI: 10.1109/ICBME51989.2020.9319430
N. Soltani, Z. Rezasoltani, N. Jamshidi
The knee as a vital organ in the human body skeleton is one of the largest joints. In recent years, there have been a variety of therapies offered to improve the efficiency and performance of an implanted prosthetic knee joint. Knee replacement is considered as one of the most common and effective treatments which is technically known as knee arthroplasty. Various factors could affect the mechanical behavior of knee arthroplasty, including the patients’ sex, physical, and bone characteristics as well as prosthesis type, structure, and geometry. The very recent advances in arthroplasty have enabled the orthopedists to achieve more desirable results by following the standards offered for prosthesis considering the anatomical geometry and material structure. Knee prosthetic implants with and without stem are the two prevalent types that orthopedists utilize for the joint replacement. In this case study, a real knee joint geometry is reconstructed using the CT images and MIMICS software. The knee arthroplasty model was then imported to the ABAQUS to perform FE analysis on the two aforementioned types of prosthesis. According to the results, the prosthesis with stem causes more stress on the joint components in the vicinity of the implantation region but will allow the knee joint to have a greater angular displacement with lower stress.
{"title":"The Effect of Stem on The Knee Joint Prosthesis Flexion Considering Natural Gait Forces","authors":"N. Soltani, Z. Rezasoltani, N. Jamshidi","doi":"10.1109/ICBME51989.2020.9319430","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319430","url":null,"abstract":"The knee as a vital organ in the human body skeleton is one of the largest joints. In recent years, there have been a variety of therapies offered to improve the efficiency and performance of an implanted prosthetic knee joint. Knee replacement is considered as one of the most common and effective treatments which is technically known as knee arthroplasty. Various factors could affect the mechanical behavior of knee arthroplasty, including the patients’ sex, physical, and bone characteristics as well as prosthesis type, structure, and geometry. The very recent advances in arthroplasty have enabled the orthopedists to achieve more desirable results by following the standards offered for prosthesis considering the anatomical geometry and material structure. Knee prosthetic implants with and without stem are the two prevalent types that orthopedists utilize for the joint replacement. In this case study, a real knee joint geometry is reconstructed using the CT images and MIMICS software. The knee arthroplasty model was then imported to the ABAQUS to perform FE analysis on the two aforementioned types of prosthesis. According to the results, the prosthesis with stem causes more stress on the joint components in the vicinity of the implantation region but will allow the knee joint to have a greater angular displacement with lower stress.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"132 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":"116346089","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/ICBME51989.2020.9319433
Tina Sadat Hashemi, M. Iravani, F. Farahmand
It is generally accepted that the high tibial osteotomy (HTO) improves the stress distribution on the articular cartilage of varus knees in the standing posture. The effects of HTO during dynamic activities, e.g., gait, however, is unclear considering the fact that it also affects the tensions of the knee ligaments and hence the knee configuration under external load and knee flexion. In this study, the HTO was simulated on a detailed 3D model of the knee consisting of femur, tibia, cartilage layer, menisci, and four ligaments. The geometry of the model was acquired from the CT and MRI data of a volunteer and the mechanical properties of the model components were obtained from the literature. In total, 42 simulations were conducted in ABAQUS to observe the effects of the correction angle and the posterior tibial slope on the tensions of the ligaments. Results indicated that the ACL tension is highly affected by both the correction angle and the posterior slope. The ACL force was minimal with the optimal wedge-angle and a small slope. LCL force decreased significantly following HTO, but showed a slight increase for smaller slopes. The PCL force, on the other hand, increased slightly following HTO and with smaller posterior slopes. It was concluded that the most important effect of the HTO and posterior slope on the knee ligaments is that of the ACL. Care should be taken to perform the surgery with optimum correction angle, to pass the mechanical axis through the center of the knee joint, and at the same time keep the posterior slope sufficiently small, beyond 10 degrees.
{"title":"Effects of high tibia osteotomy on knee ligamentous forces during gait: A finite element study","authors":"Tina Sadat Hashemi, M. Iravani, F. Farahmand","doi":"10.1109/ICBME51989.2020.9319433","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319433","url":null,"abstract":"It is generally accepted that the high tibial osteotomy (HTO) improves the stress distribution on the articular cartilage of varus knees in the standing posture. The effects of HTO during dynamic activities, e.g., gait, however, is unclear considering the fact that it also affects the tensions of the knee ligaments and hence the knee configuration under external load and knee flexion. In this study, the HTO was simulated on a detailed 3D model of the knee consisting of femur, tibia, cartilage layer, menisci, and four ligaments. The geometry of the model was acquired from the CT and MRI data of a volunteer and the mechanical properties of the model components were obtained from the literature. In total, 42 simulations were conducted in ABAQUS to observe the effects of the correction angle and the posterior tibial slope on the tensions of the ligaments. Results indicated that the ACL tension is highly affected by both the correction angle and the posterior slope. The ACL force was minimal with the optimal wedge-angle and a small slope. LCL force decreased significantly following HTO, but showed a slight increase for smaller slopes. The PCL force, on the other hand, increased slightly following HTO and with smaller posterior slopes. It was concluded that the most important effect of the HTO and posterior slope on the knee ligaments is that of the ACL. Care should be taken to perform the surgery with optimum correction angle, to pass the mechanical axis through the center of the knee joint, and at the same time keep the posterior slope sufficiently small, beyond 10 degrees.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"459 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":"116410919","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/ICBME51989.2020.9319423
A. Khalvandi, M. M. Aghdam, S. Saber-Samandari
In this study, Finite elements (FE) based micromechanical procedures were implemented for predicting the mechanical properties of Gelatin/Akermanite two-phased porous bio-nano composite scaffolds having bone substitute applications with different w.t. % and porosity distributions. At the first, 3-D representative volume elements (RVEs) with different sizes generated via developing the random algorithms considering the random distribution of inclusions and porosities in PYTHON to predict the overall mechanical behavior and to calculate the homogenized or effective Young's modulus of the porous nanocomposite scaffolds employing finite elements analyzes (FEA). The optimum size for the RVEs has been obtained. Afterward, such analyses' accuracy was validated by comparing it to data from the experimental compression test. An acceptable range of agreement between FEA predictions for various generated RVEs and experimental data from compression tests is observed, having discrepancy intervals from 6.68 % up to approximately 11%.
{"title":"Micromechanical Modeling of Gelatin-Based Nano-Composite Bone Scaffolds","authors":"A. Khalvandi, M. M. Aghdam, S. Saber-Samandari","doi":"10.1109/ICBME51989.2020.9319423","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319423","url":null,"abstract":"In this study, Finite elements (FE) based micromechanical procedures were implemented for predicting the mechanical properties of Gelatin/Akermanite two-phased porous bio-nano composite scaffolds having bone substitute applications with different w.t. % and porosity distributions. At the first, 3-D representative volume elements (RVEs) with different sizes generated via developing the random algorithms considering the random distribution of inclusions and porosities in PYTHON to predict the overall mechanical behavior and to calculate the homogenized or effective Young's modulus of the porous nanocomposite scaffolds employing finite elements analyzes (FEA). The optimum size for the RVEs has been obtained. Afterward, such analyses' accuracy was validated by comparing it to data from the experimental compression test. An acceptable range of agreement between FEA predictions for various generated RVEs and experimental data from compression tests is observed, having discrepancy intervals from 6.68 % up to approximately 11%.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"122 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":"120908982","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/ICBME51989.2020.9319440
M. Rezaei-Dastjerdehei, A. Mijani, E. Fatemizadeh
Training a model and network on an imbalanced dataset always has been a challenging problem in the machine learning field that has been discussed by researchers. In fact, available machine learning algorithms are designed moderately imbalanced datasets and mainly do not consider the dataset's imbalanced problem. In the machine learning algorithm, the imbalance problem appears when the number of one class samples are significantly minor than another class. In order to solve the imbalance problem of a dataset, multiple algorithms are proposed in the field of machine learning and especially in deep learning. In this study, we have benefited from weighted binary cross-entropy in the learning process as a loss function instead of ordinary cross-entropy (binary cross-entropy). This model allocates more penalty to minority class samples during the learning process, and it makes that minority class samples are detected more accurately. Finally, we could improve Recall with preserving Accuracy. In fact, results show that using weighted binary cross-entropy recall increases about 10%, and precision does not decrease more than 3% in comparison to binary cross-entropy.
{"title":"Addressing Imbalance in Multi-Label Classification Using Weighted Cross Entropy Loss Function","authors":"M. Rezaei-Dastjerdehei, A. Mijani, E. Fatemizadeh","doi":"10.1109/ICBME51989.2020.9319440","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319440","url":null,"abstract":"Training a model and network on an imbalanced dataset always has been a challenging problem in the machine learning field that has been discussed by researchers. In fact, available machine learning algorithms are designed moderately imbalanced datasets and mainly do not consider the dataset's imbalanced problem. In the machine learning algorithm, the imbalance problem appears when the number of one class samples are significantly minor than another class. In order to solve the imbalance problem of a dataset, multiple algorithms are proposed in the field of machine learning and especially in deep learning. In this study, we have benefited from weighted binary cross-entropy in the learning process as a loss function instead of ordinary cross-entropy (binary cross-entropy). This model allocates more penalty to minority class samples during the learning process, and it makes that minority class samples are detected more accurately. Finally, we could improve Recall with preserving Accuracy. In fact, results show that using weighted binary cross-entropy recall increases about 10%, and precision does not decrease more than 3% in comparison to binary cross-entropy.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"34 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":"127003304","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/ICBME51989.2020.9319448
Kosar Rahimi, Maryam Alizadeh, M. Abdekhodaie
Collagen type I, as a biomimetic material, has wide applications in tissue engineering and drug delivery. Still, there are limited comparative studies between different methods of constructing scaffolds or carriers based on different collagen sources. In situ gel through the enzymatic method in the presence of horseradish peroxidase (HRP) as the enzyme and hydrogen peroxide (H2O2) is one of the appealing noninvasive methods due to rapid gelation in a mild condition. In this study, a comparison was made between two in situ gels constructed by HRP/ H2O2 method based on bovine Achilles tendon collagen (Bovine Coll) and rat tail tendon collagen (Rat Coll). After collagen extractions, tyramine was incorporated on the collagen backbones. The extent of modification was 39.95 µg/mg (tyramine per collagen) and 26.94 µg/mg (tyramine per collagen) for Bovine Coll and Rat Coll, respectively. The evaluations of morphology, rheology, and degradation were performed to compare the hydrogels formed. Bovine Coll based hydrogel (BC-hyd) showed smaller average pore size, higher mechanical strength, and longer degradation time in comparison to Rat Coll based hydrogel (RT-hyd).
{"title":"Comparative study of physical properties of enzymatic in situ hydrogels based on bovine Achilles tendon collagen and rat tail collagen","authors":"Kosar Rahimi, Maryam Alizadeh, M. Abdekhodaie","doi":"10.1109/ICBME51989.2020.9319448","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319448","url":null,"abstract":"Collagen type I, as a biomimetic material, has wide applications in tissue engineering and drug delivery. Still, there are limited comparative studies between different methods of constructing scaffolds or carriers based on different collagen sources. In situ gel through the enzymatic method in the presence of horseradish peroxidase (HRP) as the enzyme and hydrogen peroxide (H2O2) is one of the appealing noninvasive methods due to rapid gelation in a mild condition. In this study, a comparison was made between two in situ gels constructed by HRP/ H2O2 method based on bovine Achilles tendon collagen (Bovine Coll) and rat tail tendon collagen (Rat Coll). After collagen extractions, tyramine was incorporated on the collagen backbones. The extent of modification was 39.95 µg/mg (tyramine per collagen) and 26.94 µg/mg (tyramine per collagen) for Bovine Coll and Rat Coll, respectively. The evaluations of morphology, rheology, and degradation were performed to compare the hydrogels formed. Bovine Coll based hydrogel (BC-hyd) showed smaller average pore size, higher mechanical strength, and longer degradation time in comparison to Rat Coll based hydrogel (RT-hyd).","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"6 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":"127429447","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/ICBME51989.2020.9319452
R. Abazari, Hamed Akbari, M. Rostami
The purpose of the study was to evaluate the influence of Wing Chun basic stance on postural control of the Kung Fu athletes. Thirteen male practitioners were participated in the experiment. The center of pressure (COP) excursions in parallel and Wing Chun basic stances were recorded for 30 s. COP path area and mean velocities in the anterior-posterior (AP) and medial-lateral (ML) directions as well as sample entropy values were computed. Sway area for Wing Chun basic stance was significantly smaller than parallel stance (p < 0.005, ES = 0.91). Instead, COP velocity in AP (p < 0.0001, ES = 1.77) and ML (p < 0.0001, ES = 2.41) directions in Wing Chun basic stance were greater than parallel stance. Moreover, in AP (p < 0.00001, ES = 1.73) and ML (p < 0.00001, ES = 2.13) directions the sample entropy values for Wing Chun basic stance were greater than parallel stance. The results showed COP excursion during Wing Chun basic stance was smaller, faster and more random compared to the parallel stance. Furthermore, due to the greater values of sample entropy in AP and ML directions, Wing Chun basic stance represented more irregular COP fluctuations that indicate lower attentional involvement in postural control rather than the parallel stance.
本研究旨在探讨咏春基本站位对功夫运动员体位控制的影响。13名男性从业人员参加了实验。在平行和咏春基本姿势的压力中心(COP)漂移记录30秒。计算COP路径面积、前后(AP)和中外侧(ML)方向的平均速度以及样本熵值。咏春基本站姿的摇摆面积明显小于平行站姿(p < 0.005, ES = 0.91)。相反，咏春基本立姿AP方向(p < 0.0001, ES = 1.77)和ML方向(p < 0.0001, ES = 2.41)的COP速度大于平行立姿。在AP (p < 0.00001, ES = 1.73)和ML (p < 0.00001, ES = 2.13)方向上，咏春基本站姿的样本熵值大于平行站姿。结果表明，咏春基本立姿的COP偏移比平行立姿更小、更快、更随机。此外，由于AP和ML方向的样本熵值更大，咏春基本站姿比平行站姿表现出更多不规则的COP波动，这表明姿势控制的注意参与程度更低。
{"title":"Influence of Wing Chun Kung Fu basic stance on postural control of amateur practitioners","authors":"R. Abazari, Hamed Akbari, M. Rostami","doi":"10.1109/ICBME51989.2020.9319452","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319452","url":null,"abstract":"The purpose of the study was to evaluate the influence of Wing Chun basic stance on postural control of the Kung Fu athletes. Thirteen male practitioners were participated in the experiment. The center of pressure (COP) excursions in parallel and Wing Chun basic stances were recorded for 30 s. COP path area and mean velocities in the anterior-posterior (AP) and medial-lateral (ML) directions as well as sample entropy values were computed. Sway area for Wing Chun basic stance was significantly smaller than parallel stance (p < 0.005, ES = 0.91). Instead, COP velocity in AP (p < 0.0001, ES = 1.77) and ML (p < 0.0001, ES = 2.41) directions in Wing Chun basic stance were greater than parallel stance. Moreover, in AP (p < 0.00001, ES = 1.73) and ML (p < 0.00001, ES = 2.13) directions the sample entropy values for Wing Chun basic stance were greater than parallel stance. The results showed COP excursion during Wing Chun basic stance was smaller, faster and more random compared to the parallel stance. Furthermore, due to the greater values of sample entropy in AP and ML directions, Wing Chun basic stance represented more irregular COP fluctuations that indicate lower attentional involvement in postural control rather than the parallel stance.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"217 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":"128919354","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/ICBME51989.2020.9319419
Mohammadreza Freidouny, Seyyed Mahdi Torabi, Ali Aliyari, Mahdi Mohammadbeigi, N. Arjmand
Low back pain and spinal disorders caused by whole-body vibration (WBV) are almost common in industrial machine operators’ society, especially forklift operators. In this study, WBV was studied while operators were performing their assigned tasks. Moreover, the effect of awkward static posture was separately investigated. Results revealed that the risk of injury caused by WBV at higher speeds and heavier loads is extremely high and some actions should be taken in order to guard against probable disorders in the operators. Accordingly, several interventions were proposed; for instance, reducing the speed of the forklifts and using air cushions on the seats can reduce the injury risk remarkably.
{"title":"An investigation into the occupational risk in forklift drivers","authors":"Mohammadreza Freidouny, Seyyed Mahdi Torabi, Ali Aliyari, Mahdi Mohammadbeigi, N. Arjmand","doi":"10.1109/ICBME51989.2020.9319419","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319419","url":null,"abstract":"Low back pain and spinal disorders caused by whole-body vibration (WBV) are almost common in industrial machine operators’ society, especially forklift operators. In this study, WBV was studied while operators were performing their assigned tasks. Moreover, the effect of awkward static posture was separately investigated. Results revealed that the risk of injury caused by WBV at higher speeds and heavier loads is extremely high and some actions should be taken in order to guard against probable disorders in the operators. Accordingly, several interventions were proposed; for instance, reducing the speed of the forklifts and using air cushions on the seats can reduce the injury risk remarkably.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"100 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":"131570696","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/ICBME51989.2020.9319436
Shaghayegh Reza, S. Seyyedsalehi, Seyyedeh Zohreh Seyyedsalehi
Acoustic landmarks are defined as more informative parts of the speech signal and are proofed to be beneficial in designing more robust speech recognition systems. This work aims to present a Persian phone recognition system based on acoustic landmarks to achieve a quality phone recognition system. For this, appropriate acoustic landmarks for the Persian language was selected and trained to an artificial neural network. Then to boost the performance of our landmark recognition system, the model's structure and the training method were modified. The goal of these modifications is to filter variations of acoustic landmarks as much as possible. For this, we utilized neural network structures to map landmarks to their corresponding gold ones nonlinearly. These gold landmarks are the ones that could be recognized without any error in our landmark recognition system. The experiments were implemented on a Persian database named Farsdat. The best landmark recognition model is a five-hidden layer feedforward neural network with 21.74 phone error rate. We also attained 0.56 percent PER improvement using our best variation filtering method.
{"title":"Persian Language Phone Recognition Based on Robust Extraction of Acoustic Landmarks","authors":"Shaghayegh Reza, S. Seyyedsalehi, Seyyedeh Zohreh Seyyedsalehi","doi":"10.1109/ICBME51989.2020.9319436","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319436","url":null,"abstract":"Acoustic landmarks are defined as more informative parts of the speech signal and are proofed to be beneficial in designing more robust speech recognition systems. This work aims to present a Persian phone recognition system based on acoustic landmarks to achieve a quality phone recognition system. For this, appropriate acoustic landmarks for the Persian language was selected and trained to an artificial neural network. Then to boost the performance of our landmark recognition system, the model's structure and the training method were modified. The goal of these modifications is to filter variations of acoustic landmarks as much as possible. For this, we utilized neural network structures to map landmarks to their corresponding gold ones nonlinearly. These gold landmarks are the ones that could be recognized without any error in our landmark recognition system. The experiments were implemented on a Persian database named Farsdat. The best landmark recognition model is a five-hidden layer feedforward neural network with 21.74 phone error rate. We also attained 0.56 percent PER improvement using our best variation filtering method.","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":"130772068","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/ICBME51989.2020.9319412
Navid Hasanzadeh, Saman Sotoudeh Paima, Ali Bashirgonbadi, M. Naghibi, H. Soltanian-Zadeh
Diagnosis and staging of COVID-19 are crucial for optimal management of the disease. To this end, novel image analysis methods need to be developed to assist radiologists with the detection and quantification of the COVID-19-related lung infections. In this work, we develop and evaluate four Artificial intelligence (AI) based lesion segmentation and quantification methods from chest CT, using U-Net, Attention U-Net, R2U-Net, and Attention R2U-Net models. These models are trained and evaluated using a dataset consisting of 8739 CT images of the lungs from 147 healthy subjects and 150 patients infected by COVID-19. The results show that the Attention R2U-Net model is superior to the others with a Dice value of 0.79. The lesion volumes estimated by the Attention R2U-Net model are highly correlated with those of the manual segmentations by an expert, with a correlation coefficient of 0.96.
{"title":"Segmentation of COVID-19 Infections on CT: Comparison of Four UNet-Based Networks","authors":"Navid Hasanzadeh, Saman Sotoudeh Paima, Ali Bashirgonbadi, M. Naghibi, H. Soltanian-Zadeh","doi":"10.1109/ICBME51989.2020.9319412","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319412","url":null,"abstract":"Diagnosis and staging of COVID-19 are crucial for optimal management of the disease. To this end, novel image analysis methods need to be developed to assist radiologists with the detection and quantification of the COVID-19-related lung infections. In this work, we develop and evaluate four Artificial intelligence (AI) based lesion segmentation and quantification methods from chest CT, using U-Net, Attention U-Net, R2U-Net, and Attention R2U-Net models. These models are trained and evaluated using a dataset consisting of 8739 CT images of the lungs from 147 healthy subjects and 150 patients infected by COVID-19. The results show that the Attention R2U-Net model is superior to the others with a Dice value of 0.79. The lesion volumes estimated by the Attention R2U-Net model are highly correlated with those of the manual segmentations by an expert, with a correlation coefficient of 0.96.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"35 5 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":"132400841","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/ICBME51989.2020.9319409
M. Ebad, B. Vahidi
Heart failure is the leading cause of death in the world and there are still many flaws in its diagnosis. At present, surgical interventions for the treatment of cardiovascular disease are limited to the absence of organ donors for transplantation and the complications of immunosuppressive therapy. Researchers are looking for new ways to regenerate a damaged heart. Tissue engineering has emerged as a new technology using cells with regenerative capacity, scaffolds, and growth factors. Stem cells are optimal cell sources for cardiac tissue engineering due to their ability to self-repair and differentiation into cardiomyocytes. Since the cardiomyocytes inside the body are in a dynamic environment under cyclic strain and pulsatile flow due to the rhythmic heartbeat, these mechanical stimuli are important factors in differentiating stem cells, regulating cardiac tissue function, and homeostasis. This study aims to simulate the effect of pulsatile flow and cyclic strain exerted on a perfusion bioreactor on stem cells for cardiac tissue engineering applications (cardiomyocyte cells). Since shear stress activates transcription pathways, this parameter is very effective in the differentiation of stem cells to cardiomyocytes. The present study attempts to evaluate the effect of frequency on the maximum magnitude of shear stress created on the embryonic stem cell layer. By applying the fluid-solid interaction method to solve the problem by two-way coupling of the equations, the results show that all the obtained values of shear stress at frequencies of 0.33 and 1 Hz and with frequency difference in cyclic strain (0.33 Hz) and pulsatile flow (1 Hz) are in the suitable range for differentiation of the stem cells to cardiomyocytes. The corresponding shear stress values are 0.00562, 0.02 and 0.01 dyn/cm2, respectively.
{"title":"Finite element analysis of stem cells mechanical stimulations for differentiation into cardiomyocytes","authors":"M. Ebad, B. Vahidi","doi":"10.1109/ICBME51989.2020.9319409","DOIUrl":"https://doi.org/10.1109/ICBME51989.2020.9319409","url":null,"abstract":"Heart failure is the leading cause of death in the world and there are still many flaws in its diagnosis. At present, surgical interventions for the treatment of cardiovascular disease are limited to the absence of organ donors for transplantation and the complications of immunosuppressive therapy. Researchers are looking for new ways to regenerate a damaged heart. Tissue engineering has emerged as a new technology using cells with regenerative capacity, scaffolds, and growth factors. Stem cells are optimal cell sources for cardiac tissue engineering due to their ability to self-repair and differentiation into cardiomyocytes. Since the cardiomyocytes inside the body are in a dynamic environment under cyclic strain and pulsatile flow due to the rhythmic heartbeat, these mechanical stimuli are important factors in differentiating stem cells, regulating cardiac tissue function, and homeostasis. This study aims to simulate the effect of pulsatile flow and cyclic strain exerted on a perfusion bioreactor on stem cells for cardiac tissue engineering applications (cardiomyocyte cells). Since shear stress activates transcription pathways, this parameter is very effective in the differentiation of stem cells to cardiomyocytes. The present study attempts to evaluate the effect of frequency on the maximum magnitude of shear stress created on the embryonic stem cell layer. By applying the fluid-solid interaction method to solve the problem by two-way coupling of the equations, the results show that all the obtained values of shear stress at frequencies of 0.33 and 1 Hz and with frequency difference in cyclic strain (0.33 Hz) and pulsatile flow (1 Hz) are in the suitable range for differentiation of the stem cells to cardiomyocytes. The corresponding shear stress values are 0.00562, 0.02 and 0.01 dyn/cm2, respectively.","PeriodicalId":120969,"journal":{"name":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)","volume":"28 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":"126511690","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：