2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)最新文献_第2页

Speckle Noise Reduction Of Ultrasound Images Based On Neighbor Pixels Averaging 基于相邻像素平均的超声图像散斑降噪

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703576

Zahra Hosseini, Mohammadreza Hassannejad Bibalan

引用次数: 3

Automatic segmentation of prostate in MR images using deep learning and multi-atlas techniques 基于深度学习和多图谱技术的磁共振图像前列腺自动分割

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703532

H. Moradi, A. H. Foruzan, Yenwei Chen

引用次数: 1

Multi-Objective Optimal Strategies For HIV Drug Dosage Scheduling Using NSIWO 基于NSIWO的HIV药物剂量调度多目标优化策略

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703499

Arezoo Vafamand, Amirhossein Nikoofard

引用次数: 2

Classification of Emotion Aroused from Painting Using Correspondence Analysis Features of Trained Pictures 基于训练图像对应分析特征的绘画情感分类

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703579

Leila Nemati Mansour, F. Farokhi

{"title":"Classification of Emotion Aroused from Painting Using Correspondence Analysis Features of Trained Pictures","authors":"Leila Nemati Mansour, F. Farokhi","doi":"10.1109/ICBME.2018.8703579","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703579","url":null,"abstract":"Nowadays, psychologists have proven that many external factors and psychological damage affect the physical health of individuals. So this requires the attention of all members of a community. Children are more exposed to such injuries and disorders such as autism and ADHD, including those that mainly affect their quality of life. People with these disorders are having trouble handling their surroundings and cannot show their abilities. So over time, people become isolated, unable to flourish their talents. But people who are concerned about the reform and growth of the community are looking for a way to help these children. Among these people are art therapists which try to increase the quality of life for such patients with mentioned disorders by using art techniques. An important work of art is the visual representation of the treatment process. In this way, the person can express emotions, psychological stresses, emotions and stress by exerting an image or a drama. Therefore, we can imagine a refining role for art therapy, which promotes human communication.We have shown that there exist a meaningful relationship between paintings and Labeled images in a way that a meaningful intelligent system could be trained by extracting effective features based on UTA algorithm and selecting important instances using Fast Condensed Nearest Neighbor (FCNN). The results shown that using mentioned approach and Correspondence Analysis (CA) features can improve the classification accuracy to 66.5% in task1 and 64.4% in task2.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 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":"129486702","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}

引用次数: 0

A Novel Algorithm Based on Decision Trees in Multiclass Classification 一种基于决策树的多类分类新算法

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703580

Soroush Mirjalili, S. H. Sardouie, N. Samiee

{"title":"A Novel Algorithm Based on Decision Trees in Multiclass Classification","authors":"Soroush Mirjalili, S. H. Sardouie, N. Samiee","doi":"10.1109/ICBME.2018.8703580","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703580","url":null,"abstract":"Classification is the most important part in Brain-Computer Interface problems, where our task is to decipher the individual's (usually people with physical or verbal disorders) intention from several candidates. In our study, the MEG signals were recorded from an individual when he was shown S different types of video clips while our task was to process the MEG signals in each experiment to guess the type of the movie from 5 candidates. In this study, we applied various approaches to this multiclass classification problem and in the end, we proposed a novel algorithm which can also be applied to any multiclass classification problem. Suppose that we are using a decision tree and at each node, the classes are going to be divided into two groups of classes. In the proposed algorithm, we defined a criterion to find the best partitioning by using the results of only $left( begin{array}{c}n 2 end{array} right)$ classifications between each pair of classes using training data. As a result, the algorithm is polynomial and can be applied to any multiclass problem. Moreover, as a matter of accuracy, it led us to the best accuracy (61.4%) in comparison to other routine methods. Thus, this algorithm might be a powerful tool in any multiclass classification problem.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 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":"130647955","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}

引用次数: 2

A Mobile Application for Early Detection of Melanoma by Image Processing Algorithms 基于图像处理算法的黑色素瘤早期检测移动应用

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703575

Seyed Mohammad Alizadeh, A. Mahloojifar

{"title":"A Mobile Application for Early Detection of Melanoma by Image Processing Algorithms","authors":"Seyed Mohammad Alizadeh, A. Mahloojifar","doi":"10.1109/ICBME.2018.8703575","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703575","url":null,"abstract":"Melanoma is the most dangerous skin cancer which causes many deaths annually. However, early detection can help treat it. For accurate detection of melanoma, dermatologists use biopsy which is usually associated with pain, time and cost. With the advancement of technology and the development of smartphones, many mobile applications have been designed for early detection of melanoma. Although they are fast in the detection of melanoma and save time and money, they are not as accurate as the biopsy. In this paper, the authors proposed an application for early detection of melanoma using image processing methods and pattern recognition algorithms by Android Studio software, Java programming language, and the OpenCV library. All detection steps were carried out using the Android smartphone. For better performance in the classification step, in addition to the smartphone, a computer was also used. This application is user-friendly and the calculated Accuracy, Sensitivity, and Specificity are 95%, 98%, and 92.19% on average, respectively. It should be noted that these results are more reliable when the lesions are geometrically distinct.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"75 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":"134091084","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}

引用次数: 9

Design and fabrication of a new chitosan based wound dressing in combination with carboxylated Polyethylene glycol 壳聚糖与羧化聚乙二醇复合创面敷料的设计与制备

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703556

A. Anousheh, M. Tafazzoli-Shadpour, Alireza Hassani-Najafabadi

{"title":"Design and fabrication of a new chitosan based wound dressing in combination with carboxylated Polyethylene glycol","authors":"A. Anousheh, M. Tafazzoli-Shadpour, Alireza Hassani-Najafabadi","doi":"10.1109/ICBME.2018.8703556","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703556","url":null,"abstract":"a successful wound dressing is required to show acceptable structural properties. Here we aimed in developing a new wound dressing using chitosan in combination with polyethylene glycol (PEG) for mechanical and structural properties enhancement the percentages of polymers and method of mixing were major parameters to obtain a proper porous structure with appropriate properties and economical advantage. Hence we used wide ranges of chitosan percentage and molecular weight of PEG, and two methods of fabrication through casting and freeze drying to obtain a novel wound dressing with enhanced properties. After synthesis, different material properties were examined including swelling, biodegradability. Furthermore, samples were mechanically characterized by elastic moduli parameters. Samples with 70% and 50% of chitosan and PEG molecular weight of 2000, synthesized by casting method were selected after meeting the adequate requirements as proper candidates for the wound dressing. Their porous structure with small size pores provided an appropriate environment to enable absorbance drainage and transmission of vapor. They showed superb antibacterial property with high reduction rates of bacterial colonies of E.coli and S.aureus. Moreover, they indicated non-toxicity for L929 fibroblast cells with over 98% viability in MTT assay. Considering appropriate physical, structural and biological properties, the selected samples were introduced as wound dressing candidates.","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":"134258931","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}

引用次数: 0

The effect of ethanol and temperature on the structural properties of mesoporous silica synthesized by the sol-gel method 研究了乙醇和温度对溶胶-凝胶法制备介孔二氧化硅结构性能的影响

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.22034/JTM.2018.67254

Pegah Khodaee, N. Najmoddin, Shima Shahrad

引用次数: 5

Using deep convolutional neural networks with adaptive activation functions for medical CT brain image Classification 基于自适应激活函数的深度卷积神经网络用于医学CT脑图像分类

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703546

Roxana ZahediNasab, H. Mohseni

{"title":"Using deep convolutional neural networks with adaptive activation functions for medical CT brain image Classification","authors":"Roxana ZahediNasab, H. Mohseni","doi":"10.1109/ICBME.2018.8703546","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703546","url":null,"abstract":"recently, imaging has become an essential component in many fields of medical research. Analysis of the diverse medical image types requires sophisticated visualization and processing tools. Deep neural networks have introduced themselves as one of the most important branches of machine learning and have been successfully used in many fields of pattern recognition and medical imaging applications. Among the different networks, convolutional neural networks which are biologically inspired variants of multilayer perceptions are widely used in the medical imaging field. In these networks, activation function plays a significant role especially when the data come in different scales. There is a hope to improve the performance of these networks by using adaptive activation functions which adapts their parameters to the input data. In this paper, we have used a modified version of a successful convolutional neural network tuned for medical image classification and investigated the effect of applying three types of adaptive activation functions on that. These activation functions combine basic activation functions in linear (mixed) and nonlinear (gated and hierarchical) ways. The effectiveness of using these adaptive functions is shown on a CT brain images dataset (as a complex medical dataset). The experiments show that the classification accuracy of the proposed network with adaptive activation functions is higher compared to the ones using basic activation functions.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"17 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":"133921759","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}

引用次数: 3

A Learning-Based Framework for the Automatic Segmentation of Human Sperm Head, Acrosome and Nucleus 基于学习的人类精子头、顶体和核自动分割框架

2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) Pub Date : 2018-11-01 DOI: 10.1109/ICBME.2018.8703544

R. Movahed, M. Orooji

{"title":"A Learning-Based Framework for the Automatic Segmentation of Human Sperm Head, Acrosome and Nucleus","authors":"R. Movahed, M. Orooji","doi":"10.1109/ICBME.2018.8703544","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703544","url":null,"abstract":"Evaluating the morphology of the human sperm is one of the most important steps in the human semen analysis, which is the controversial aspect of the treatment of male infertility. Manual assessment of the corresponding parameters of human sperm morphology is a time-consuming, reader subjective and error-prone process. Therefore, developing the automatic methods is necessary to achieve the more accurate diagnosis. In this paper, we presented a learning-based framework for the automatic segmentation of the human sperm head particles, i.e., Acrosome and Nucleus. First, the homomorphic filtering is employed to correct uneven illumination and highlight each sperm from the background of an image. In the second step, sperm's heads are segmented using an introduced deep convolutional neural network (CNN). Then, a filling holes operation and geometric constraints are utilized to improve head segments. A Support Vector Machine (SVM) is used to classify each pixel of segmented heads to nucleus and acrosome regions. Finally, segmented acrosomes and nucleus are modified using opening and closing operations followed by isolated objects removing. The proposed method is validated on the expert delineated dataset with 20 images of human semen smears and obtains 0.94, 0.87, and 0.88 of Dice Similarity Coefficient for the head, the acrosome, and the nucleus segments, respectively. Our results indicate that the proposed method has outperformed the segmentation systems based on classical learning methods, in the accuracy and the reliability.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"14 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":"127823129","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}

引用次数: 7