Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703537
M. Ebad, B. Vahidi
Bone is a living tissue which constantly adapts its internal structure to fit the needs of the mechanical environment and strain caused by the fluid flow. Mechanical forces such as tension and compression can be responsible for bone regeneration. In this study, the computational method of fluid-structure interaction was used for analyzing the nature of the mechanical stimulus in an osteoblast cell under the fluid flow inside a parallel plate system, for determining the change of strain, pressure and wall shear rate of the fluid. These changes were done by the outlet pressures of 100, 200 and 300 Pa and inlet velocities of 40, 80 and 120 mm/s. By increasing the outlet pressure from 100 to 200 Pa, the cell pressure increased by 90% and in the pressure of 300 Pa, 185%. By increasing the velocity from 40 to 80 mm/s cell pressure increased by 11% and in the velocity of 120 mm/s, 22%. Additionally, that cell membrane’s strain was relatively low, while it was significant in the contact region of the layer and cell. Also, the lower wall’s shearing rate has the most value. Conclusively, by controlling the applied mechanical forces, the growth and differentiation of osteoblast cell can be adjusted.
{"title":"Simulation of mechanical modulation of an osteoblast cell due to fluid flow","authors":"M. Ebad, B. Vahidi","doi":"10.1109/ICBME.2018.8703537","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703537","url":null,"abstract":"Bone is a living tissue which constantly adapts its internal structure to fit the needs of the mechanical environment and strain caused by the fluid flow. Mechanical forces such as tension and compression can be responsible for bone regeneration. In this study, the computational method of fluid-structure interaction was used for analyzing the nature of the mechanical stimulus in an osteoblast cell under the fluid flow inside a parallel plate system, for determining the change of strain, pressure and wall shear rate of the fluid. These changes were done by the outlet pressures of 100, 200 and 300 Pa and inlet velocities of 40, 80 and 120 mm/s. By increasing the outlet pressure from 100 to 200 Pa, the cell pressure increased by 90% and in the pressure of 300 Pa, 185%. By increasing the velocity from 40 to 80 mm/s cell pressure increased by 11% and in the velocity of 120 mm/s, 22%. Additionally, that cell membrane’s strain was relatively low, while it was significant in the contact region of the layer and cell. Also, the lower wall’s shearing rate has the most value. Conclusively, by controlling the applied mechanical forces, the growth and differentiation of osteoblast cell can be adjusted.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128106191","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703583
Elahe Parham, Mohamad Feshki, H. Soltanian-Zadeh
In this article, the relation between structural connectivity and processing speed of the brain is studied. Structural connectivity is calculated by using diffusion tensor imaging (DTI) data and tractography methods for 116 nodes of AAL atlas template. Then by employing the fractional anisotropy (FA) and processing speed task scores, correlation analysis is done to find important connections. The results show that connections in frontal, temporal, hippocampus, insula, cerebellum, and vermis regions are correlated with the processing speed of the brain. Also, connections with positive correlations have higher effects on the processing speed than connections with negative correlations. Predominantly, the higher the FA of the selected connection, the higher the processing speed.
{"title":"Relation between Brain Structural Connectivity and Processing Speed","authors":"Elahe Parham, Mohamad Feshki, H. Soltanian-Zadeh","doi":"10.1109/ICBME.2018.8703583","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703583","url":null,"abstract":"In this article, the relation between structural connectivity and processing speed of the brain is studied. Structural connectivity is calculated by using diffusion tensor imaging (DTI) data and tractography methods for 116 nodes of AAL atlas template. Then by employing the fractional anisotropy (FA) and processing speed task scores, correlation analysis is done to find important connections. The results show that connections in frontal, temporal, hippocampus, insula, cerebellum, and vermis regions are correlated with the processing speed of the brain. Also, connections with positive correlations have higher effects on the processing speed than connections with negative correlations. Predominantly, the higher the FA of the selected connection, the higher the processing speed.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123200266","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703592
Manizhe Rahchamani, Muhammad Ismail Soboute, N. Samadzadehaghdam, Bahador Makki Abadi
Camera pose estimation is an important problem in many applications that need localization of cameras, devices, or instruments in robotics, surgical operations, and augmented-reality. It is important to provide a cost-effective, real-time, accurate, and easy to use system for pose estimation. There are two kinds of optical tracking methods employed by camera pose estimation algorithms, model-based versus feature based methods. Here, we developed a feature-based camera pose estimationmethodutilizing justonesingle camera and a large marker. The keypoint features from the scene image and the marker are detected by Speeded Up Robust Features (SURF) detector. Then, their descriptors are extracted by Scale Invariant Feature Transform (SIFT) and they are matched using Brute Force matching (BF). A perspective transform is supposed to map the coordinates of the image keypoints to the coordinates of the corresponding 3D points in the marker.This problem is solved by OpenCV functionsand the final camera pose matrix is obtained. To evaluate the proposed method, we developed a 3D printed calibrator with known placeholder positions. The proposed system can be realized usinga smartphone camera (in webcam mode) and a large marker on the wall. As results show, the proposed method achieves acceptable accuracy namely an average error of approximately 1.4 cm for position and 0.02 radianfor orientation.
{"title":"Developing and Evaluating a Low-Cost Tracking Method based on a Single Camera and a Large Marker","authors":"Manizhe Rahchamani, Muhammad Ismail Soboute, N. Samadzadehaghdam, Bahador Makki Abadi","doi":"10.1109/ICBME.2018.8703592","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703592","url":null,"abstract":"Camera pose estimation is an important problem in many applications that need localization of cameras, devices, or instruments in robotics, surgical operations, and augmented-reality. It is important to provide a cost-effective, real-time, accurate, and easy to use system for pose estimation. There are two kinds of optical tracking methods employed by camera pose estimation algorithms, model-based versus feature based methods. Here, we developed a feature-based camera pose estimationmethodutilizing justonesingle camera and a large marker. The keypoint features from the scene image and the marker are detected by Speeded Up Robust Features (SURF) detector. Then, their descriptors are extracted by Scale Invariant Feature Transform (SIFT) and they are matched using Brute Force matching (BF). A perspective transform is supposed to map the coordinates of the image keypoints to the coordinates of the corresponding 3D points in the marker.This problem is solved by OpenCV functionsand the final camera pose matrix is obtained. To evaluate the proposed method, we developed a 3D printed calibrator with known placeholder positions. The proposed system can be realized usinga smartphone camera (in webcam mode) and a large marker on the wall. As results show, the proposed method achieves acceptable accuracy namely an average error of approximately 1.4 cm for position and 0.02 radianfor orientation.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134183947","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703529
F. Abdolali, R. Zoroofi, A. Biniaz
Automatic detection of mandibular canal in cone beam CT data is an essential step for planning and guiding implant surgery. In this work, we present a new detection method based on combining statistical shape models and Lie group. The proposed methodology consists of three steps. Firstly, a method based on multi-scale low rank matrix decomposition is used for noise removal and image enhancement. Subsequently, a Lie group based statistical shape model is constructed to represent shape variation and fast marching is employed to localize the location of the mandibular canal more accurately. Quantitative results show that accurate and fully automatic detection of mandibular canal is feasible. Moreover, the proposed method based on Lie group based statistical shape model outperforms two previous methods based on statistical shape model in the literature, i.e. conventional and conditional statistical shape models. The average value of Dice similarity index and symmetric distance are 0.92 and 1.02 mm, respectively.
{"title":"Fully automated detection of the mandibular canal in cone beam CT images using Lie group based statistical shape models","authors":"F. Abdolali, R. Zoroofi, A. Biniaz","doi":"10.1109/ICBME.2018.8703529","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703529","url":null,"abstract":"Automatic detection of mandibular canal in cone beam CT data is an essential step for planning and guiding implant surgery. In this work, we present a new detection method based on combining statistical shape models and Lie group. The proposed methodology consists of three steps. Firstly, a method based on multi-scale low rank matrix decomposition is used for noise removal and image enhancement. Subsequently, a Lie group based statistical shape model is constructed to represent shape variation and fast marching is employed to localize the location of the mandibular canal more accurately. Quantitative results show that accurate and fully automatic detection of mandibular canal is feasible. Moreover, the proposed method based on Lie group based statistical shape model outperforms two previous methods based on statistical shape model in the literature, i.e. conventional and conditional statistical shape models. The average value of Dice similarity index and symmetric distance are 0.92 and 1.02 mm, respectively.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116042063","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703527
Ensieh Nouri, Masoume Rahimi, M. Moradi
The life of living beings from cell to society in the universe is controlled by complex processes to preserve life. Understanding the gene network and discovering interactions between genes in cells is an important goal in biological systems. Modeling the gene network is one of the important issues in signal processing at the gene level. After the development of microarray technology, it was possible to model this network using time series data. The main objective of this research is to model the gene network from microarray time-series data that uses Granger causality, and to improve Granger causality and to observe the vague nature of microarray data,The linear method in Granger causality is replaced by a fuzzy method which then was applied on artificial and the real HELA data.
{"title":"Gene networks modeling of microarray time series using Fuzzy Granger causality","authors":"Ensieh Nouri, Masoume Rahimi, M. Moradi","doi":"10.1109/ICBME.2018.8703527","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703527","url":null,"abstract":"The life of living beings from cell to society in the universe is controlled by complex processes to preserve life. Understanding the gene network and discovering interactions between genes in cells is an important goal in biological systems. Modeling the gene network is one of the important issues in signal processing at the gene level. After the development of microarray technology, it was possible to model this network using time series data. The main objective of this research is to model the gene network from microarray time-series data that uses Granger causality, and to improve Granger causality and to observe the vague nature of microarray data,The linear method in Granger causality is replaced by a fuzzy method which then was applied on artificial and the real HELA data.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116304842","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703538
Mehdi Jalili AhmadAbad, Mohammad Bakhshi Beris, N. Kiaie
composites have a wide range of applications in biomedical engineering as drug delivery templates and cell scaffolds. In this study, a composite scaffold of Chitosan-Gelatin-TCP was fabricated through freeze drying method and effect of gelatin concentration on porosity and swelling of scaffolds was investigated. Morphology and porosity of scaffolds was assessed by SEM. Binding of elements in composite was shown by FTIR and swelling test was performed in PBS. The results showed there exist a direct relationship between amount of gelatin in scaffold, pore size, porosity, and swelling ratio.
{"title":"Effect of gelatin concentration on pores and swelling behaviour of a composite bone scaffold","authors":"Mehdi Jalili AhmadAbad, Mohammad Bakhshi Beris, N. Kiaie","doi":"10.1109/ICBME.2018.8703538","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703538","url":null,"abstract":"composites have a wide range of applications in biomedical engineering as drug delivery templates and cell scaffolds. In this study, a composite scaffold of Chitosan-Gelatin-TCP was fabricated through freeze drying method and effect of gelatin concentration on porosity and swelling of scaffolds was investigated. Morphology and porosity of scaffolds was assessed by SEM. Binding of elements in composite was shown by FTIR and swelling test was performed in PBS. The results showed there exist a direct relationship between amount of gelatin in scaffold, pore size, porosity, and swelling ratio.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123465002","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703541
Sharifi Fatemeh, B. Firoozabadi, K. Firoozbakhsh
Finding optimized conditions in analyzing in vitro drug hepatotoxicity especially during preliminary stages of drug development is highly appreciated. Recently, liver-on-chip platforms have been widely used in drug toxicity researches. Although perfusion in the bioreactor will enhance oxygen and nutrition delivery to the hepatocytes and decrease hypoxic zone in the bioreactor, high perfusion rate impose high shear stress on liver cells which may be detrimental or effect on their liver specific functions. Here, a three-dimensional bioreactor containing hepatic spheroids is developed numerically and velocity distribution, shear stress sensed by cells was calculated. Based on the rate of oxygen delivery and oxygen metabolic activities of the hepatocytes, the level of oxygen for each spheroid was analyzed. Also, albumin production of the hepatic cells was modeled as an example of modeling metabolic function capabilities. The computed albumin production was verified with the experimental results over 7 days of culture period which showed a good compatibility between the experimental results and numerical predictions. The results are of a great importance in finding an optimal design and working conditions of the bioreactors.
{"title":"Computational Modeling of 3D Printed Hepatic Spheroids Inside a Bioreactor","authors":"Sharifi Fatemeh, B. Firoozabadi, K. Firoozbakhsh","doi":"10.1109/ICBME.2018.8703541","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703541","url":null,"abstract":"Finding optimized conditions in analyzing in vitro drug hepatotoxicity especially during preliminary stages of drug development is highly appreciated. Recently, liver-on-chip platforms have been widely used in drug toxicity researches. Although perfusion in the bioreactor will enhance oxygen and nutrition delivery to the hepatocytes and decrease hypoxic zone in the bioreactor, high perfusion rate impose high shear stress on liver cells which may be detrimental or effect on their liver specific functions. Here, a three-dimensional bioreactor containing hepatic spheroids is developed numerically and velocity distribution, shear stress sensed by cells was calculated. Based on the rate of oxygen delivery and oxygen metabolic activities of the hepatocytes, the level of oxygen for each spheroid was analyzed. Also, albumin production of the hepatic cells was modeled as an example of modeling metabolic function capabilities. The computed albumin production was verified with the experimental results over 7 days of culture period which showed a good compatibility between the experimental results and numerical predictions. The results are of a great importance in finding an optimal design and working conditions of the bioreactors.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123835749","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703559
Omid Bazgir, Z. Mohammadi, S. Habibi
In this research, an emotion recognition system is developed based on valence/arousal model using electroencephalography (EEG) signals. EEG signals are decomposed into the gamma, beta, alpha and theta frequency bands using discrete wavelet transform (DWT), and spectral features are extracted from each frequency band. Principle component analysis (PCA) is applied to the extracted features by preserving the same dimensionality, as a transform, to make the features mutually uncorrelated. Support vector machine (SVM), K-nearest neighbor (KNN) and artificial neural network (ANN) are used to classify emotional states. The cross- validated SVM with radial basis function (RBF) kernel using extracted features of 10 EEG channels, performs with 91.3% accuracy for arousal and 91.1% accuracy for valence, both in the beta frequency band. Our approach shows better performance compared to existing algorithms applied to the "DEAP" dataset.
{"title":"Emotion Recognition with Machine Learning Using EEG Signals","authors":"Omid Bazgir, Z. Mohammadi, S. Habibi","doi":"10.1109/ICBME.2018.8703559","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703559","url":null,"abstract":"In this research, an emotion recognition system is developed based on valence/arousal model using electroencephalography (EEG) signals. EEG signals are decomposed into the gamma, beta, alpha and theta frequency bands using discrete wavelet transform (DWT), and spectral features are extracted from each frequency band. Principle component analysis (PCA) is applied to the extracted features by preserving the same dimensionality, as a transform, to make the features mutually uncorrelated. Support vector machine (SVM), K-nearest neighbor (KNN) and artificial neural network (ANN) are used to classify emotional states. The cross- validated SVM with radial basis function (RBF) kernel using extracted features of 10 EEG channels, performs with 91.3% accuracy for arousal and 91.1% accuracy for valence, both in the beta frequency band. Our approach shows better performance compared to existing algorithms applied to the \"DEAP\" dataset.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122507750","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 : 2018-11-01DOI: 10.1109/icbme.2018.8703526
{"title":"ICBME 2018 Organizing Committee","authors":"","doi":"10.1109/icbme.2018.8703526","DOIUrl":"https://doi.org/10.1109/icbme.2018.8703526","url":null,"abstract":"","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121641420","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703601
A. Amirkhani, Mojtaba Kolahdoozi, A. Naimi
Autoimmune hepatitis (AIH) is an inflammatory liver disease with an undiscovered cause that is attributed to the promiscuous humoral as well as cellular immune response against homologous self-antigens. If AIH is not diagnosed and treated in its early stages, it can result in cirrhosis or liver failure. In this regard, we propose a novel algorithm based on fuzzy cognitive maps (FCM) for paving the way for accurate diagnosis of it. For doing so, major and innate characteristics of AIH which play a significant role in diagnosing it, in addition to the data of 216 samples—suffering from AIH—have been gathered by the help of three pathologists. Then, we have applied our developed FCM solution on obtained data in order to classify them in one the definite AIH or improbable AIH classes. Our devised algorithm utilizes quantum inspired evolutionary algorithm (QEA) as a link reduction tool as well as particle swarm optimization algorithm as a link tuning mean. In the QEA, instead of coding the presence and absence of links between concepts with 1 and 0, respectively, the probability of their existence or inexistence is modeled with a Q-bit (the smallest information unit in the QEA) and, depending on the outcome of objective function, the quantum state of these Q-bits are updated. Using a probabilistic representation instead of 0 and 1, in addition to creating diversity in the solution space, can lead to escapes from many local optima; which is an issue of concern in the optimization of FCM structure. Experimental results show that not only does our developed algorithm make accurate diagnosis, but it outperforms other conventional methods as well.
{"title":"Quantum Learning of Fuzzy Cognitive Map: An Illustrative Study of Cirrhosis","authors":"A. Amirkhani, Mojtaba Kolahdoozi, A. Naimi","doi":"10.1109/ICBME.2018.8703601","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703601","url":null,"abstract":"Autoimmune hepatitis (AIH) is an inflammatory liver disease with an undiscovered cause that is attributed to the promiscuous humoral as well as cellular immune response against homologous self-antigens. If AIH is not diagnosed and treated in its early stages, it can result in cirrhosis or liver failure. In this regard, we propose a novel algorithm based on fuzzy cognitive maps (FCM) for paving the way for accurate diagnosis of it. For doing so, major and innate characteristics of AIH which play a significant role in diagnosing it, in addition to the data of 216 samples—suffering from AIH—have been gathered by the help of three pathologists. Then, we have applied our developed FCM solution on obtained data in order to classify them in one the definite AIH or improbable AIH classes. Our devised algorithm utilizes quantum inspired evolutionary algorithm (QEA) as a link reduction tool as well as particle swarm optimization algorithm as a link tuning mean. In the QEA, instead of coding the presence and absence of links between concepts with 1 and 0, respectively, the probability of their existence or inexistence is modeled with a Q-bit (the smallest information unit in the QEA) and, depending on the outcome of objective function, the quantum state of these Q-bits are updated. Using a probabilistic representation instead of 0 and 1, in addition to creating diversity in the solution space, can lead to escapes from many local optima; which is an issue of concern in the optimization of FCM structure. Experimental results show that not only does our developed algorithm make accurate diagnosis, but it outperforms other conventional methods as well.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122012981","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：