Pub Date : 2022-03-16DOI: 10.4015/s101623722250020x
Qaysar Mohi ud Din, A. Jayanthy
Children suffering from Autism Spectrum Disorder (ASD) have impaired social communication, interaction and restricted and repetitive behaviors. ASD is caused by abnormal brain developments which give rise to the behavioral characteristics associated with ASD. The clinical diagnosis of ASD is performed on the basis of behavioral assessment and it causes a time delay in early intervention, as there is a time gap between abnormal brain developments and associated behavioral characteristics. Electroencephalography (EEG) is a technique which measures the electrical activity produced by the brain and it has been used to detect several neurological disorders. Studies have shown that there is a variation in the EEG signals of a normal subject and EEG signals of ASD subjects. In this study, we obtained scalograms of EEG signals by using Continuous Wavelet Transform (CWT). Pre-trained deep Convolutional Neural Networks (CNNs) such as GoogLeNet, AlexNet, MobileNet and SqueezeNet were used for extracting the features from scalograms and classification of obtained scalograms from EEG signals of normal and ASD subjects. We also used Support Vector Machine (SVM) algorithm and Relevance Vector Machine (RVM) for classification of the features extracted by the deep CNNs. The GoogLeNet, AlexNet, MobileNet and SqueezeNet deep CNNs achieved a validation accuracy of 75%, 75.84%, 79.45% and 82.98% in classifying the scalograms generated from EEG signals. The SVM achieved an accuracy of 71.6%, 74.76%, 70.70% and 81.47% using GoogleNet, Mobilenet, AlexNet and SqueezeNet for scalogram feature extraction. The RVM achieved an accuracy of 65.5%, 69.9%, 65.3% and 72.59% when used for classification using the features generated from GoogLeNet, AlexNet, MobileNet and SqueezeNet.The SqueezeNet deep CNN performed better than GoogLeNet, AlexNet and MobileNet for classification of the EEG scalograms. The feature extraction using SqueezeNet also resulted in better classification accuracy obtained by SVM and RVM. The results indicate that pre-trained models can be used for classifying the ASD using scalograms of the EEG signals.
{"title":"AUTOMATED CLASSIFICATION OF AUTISM SPECTRUM DISORDER USING EEG SIGNALS AND CONVOLUTIONAL NEURAL NETWORKS","authors":"Qaysar Mohi ud Din, A. Jayanthy","doi":"10.4015/s101623722250020x","DOIUrl":"https://doi.org/10.4015/s101623722250020x","url":null,"abstract":"Children suffering from Autism Spectrum Disorder (ASD) have impaired social communication, interaction and restricted and repetitive behaviors. ASD is caused by abnormal brain developments which give rise to the behavioral characteristics associated with ASD. The clinical diagnosis of ASD is performed on the basis of behavioral assessment and it causes a time delay in early intervention, as there is a time gap between abnormal brain developments and associated behavioral characteristics. Electroencephalography (EEG) is a technique which measures the electrical activity produced by the brain and it has been used to detect several neurological disorders. Studies have shown that there is a variation in the EEG signals of a normal subject and EEG signals of ASD subjects. In this study, we obtained scalograms of EEG signals by using Continuous Wavelet Transform (CWT). Pre-trained deep Convolutional Neural Networks (CNNs) such as GoogLeNet, AlexNet, MobileNet and SqueezeNet were used for extracting the features from scalograms and classification of obtained scalograms from EEG signals of normal and ASD subjects. We also used Support Vector Machine (SVM) algorithm and Relevance Vector Machine (RVM) for classification of the features extracted by the deep CNNs. The GoogLeNet, AlexNet, MobileNet and SqueezeNet deep CNNs achieved a validation accuracy of 75%, 75.84%, 79.45% and 82.98% in classifying the scalograms generated from EEG signals. The SVM achieved an accuracy of 71.6%, 74.76%, 70.70% and 81.47% using GoogleNet, Mobilenet, AlexNet and SqueezeNet for scalogram feature extraction. The RVM achieved an accuracy of 65.5%, 69.9%, 65.3% and 72.59% when used for classification using the features generated from GoogLeNet, AlexNet, MobileNet and SqueezeNet.The SqueezeNet deep CNN performed better than GoogLeNet, AlexNet and MobileNet for classification of the EEG scalograms. The feature extraction using SqueezeNet also resulted in better classification accuracy obtained by SVM and RVM. The results indicate that pre-trained models can be used for classifying the ASD using scalograms of the EEG signals.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"9 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75293897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-11DOI: 10.4015/s1016237222500235
Hala S. Abuelmakarem, S. Fawzi, A. Quriba, Ahmed Elbialy, A. Kandil
Objectives: This study aims to develop a computer-aided therapy (CAT) application to help children who suffer from delayed language development (DLD) improve their language, especially during the COVID-19 pandemic. Methods: The implemented system teaches the children their body parts using the Egyptian dialect. Two datasets were collected from healthy children (2800 words) and unhealthy children (236 words) who have DLD at the clinic. The model is implemented using a speaker-independent isolated word recognizer based on a discrete-observation hidden Markov model (DHMM) classifier. After the speech signal preprocessing step, K-means algorithm generated a codebook to cluster the speech segments. This task was completed under the MATLAB environment. The graphical user interface was implemented successfully under the C# umbrella to complete the CAT application task. The system was tested on healthy and DLD children. Also, in a small clinical trial, five children who have DLD tested the program in an actual trial to monitor their pronunciation progress during therapeutic sessions. Results: The max recognition rate was 95.25% for the healthy children dataset, while 93.82% for the DLD dataset. Conclusion: DHMM was implemented successfully using nine and five states based on different codebook sizes (160, 200). The implemented system achieved a high recognition rate using both datasets. The children enjoyed using the application because it was interactive. Children who have DLD can use speech recognition applications.
{"title":"COMPUTER-AIDED THERAPY USING AUTOMATIC SPEECH RECOGNITION TECHNIQUE FOR DELAYED LANGUAGE DEVELOPMENT CHILDREN","authors":"Hala S. Abuelmakarem, S. Fawzi, A. Quriba, Ahmed Elbialy, A. Kandil","doi":"10.4015/s1016237222500235","DOIUrl":"https://doi.org/10.4015/s1016237222500235","url":null,"abstract":"Objectives: This study aims to develop a computer-aided therapy (CAT) application to help children who suffer from delayed language development (DLD) improve their language, especially during the COVID-19 pandemic. Methods: The implemented system teaches the children their body parts using the Egyptian dialect. Two datasets were collected from healthy children (2800 words) and unhealthy children (236 words) who have DLD at the clinic. The model is implemented using a speaker-independent isolated word recognizer based on a discrete-observation hidden Markov model (DHMM) classifier. After the speech signal preprocessing step, K-means algorithm generated a codebook to cluster the speech segments. This task was completed under the MATLAB environment. The graphical user interface was implemented successfully under the C# umbrella to complete the CAT application task. The system was tested on healthy and DLD children. Also, in a small clinical trial, five children who have DLD tested the program in an actual trial to monitor their pronunciation progress during therapeutic sessions. Results: The max recognition rate was 95.25% for the healthy children dataset, while 93.82% for the DLD dataset. Conclusion: DHMM was implemented successfully using nine and five states based on different codebook sizes (160, 200). The implemented system achieved a high recognition rate using both datasets. The children enjoyed using the application because it was interactive. Children who have DLD can use speech recognition applications.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"397 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80299744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-08DOI: 10.4015/s1016237222500181
Jinbao He, Zaifei Luo, Qinbo Hu
In order to correctly identify the motor unit action potential trains (MUAPTs) in estimated discharges from dynamic surface electromyogram (EMG), an approach for accurate classification of motor unit (MU) discharges is presented. First, the estimated discharges are obtained manually, then the estimated discharges are classified as MUAPTs based on the MU location, which combines the MU depth with the MU plane position. During verification in dynamic muscle contractions, the advanced tripole model is introduced. At SNRs of 10, 20 and 30[Formula: see text]dB, the MUAPTs were identified with true positive rate (TPR) of 91.1[Formula: see text]5.5%, 95.2[Formula: see text]3.7% and 96.1[Formula: see text]2.9%. The results also show that the MU location can be used as a simple method for identifying MUAPT from estimated discharges and selecting reliably decomposed discharges. The newly introduced method is a robust and reliable indicator of MUAPT identification accuracy.
{"title":"ACCURATE CLASSIFICATION OF MOTOR UNIT DISCHARGES FROM DYNAMIC SURFACE EMG SIGNALS","authors":"Jinbao He, Zaifei Luo, Qinbo Hu","doi":"10.4015/s1016237222500181","DOIUrl":"https://doi.org/10.4015/s1016237222500181","url":null,"abstract":"In order to correctly identify the motor unit action potential trains (MUAPTs) in estimated discharges from dynamic surface electromyogram (EMG), an approach for accurate classification of motor unit (MU) discharges is presented. First, the estimated discharges are obtained manually, then the estimated discharges are classified as MUAPTs based on the MU location, which combines the MU depth with the MU plane position. During verification in dynamic muscle contractions, the advanced tripole model is introduced. At SNRs of 10, 20 and 30[Formula: see text]dB, the MUAPTs were identified with true positive rate (TPR) of 91.1[Formula: see text]5.5%, 95.2[Formula: see text]3.7% and 96.1[Formula: see text]2.9%. The results also show that the MU location can be used as a simple method for identifying MUAPT from estimated discharges and selecting reliably decomposed discharges. The newly introduced method is a robust and reliable indicator of MUAPT identification accuracy.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"306 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73161879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-08DOI: 10.4015/s101623722250017x
Chi-Chih Wu, C. Chiu, Su-Yi Fu
Falls are a multi-factor problem that poses a serious risk to the elderly. Approximately, 60% of falls are caused by a number of known factors, including the environment, which accounts for approximately 25–45% of falling risk. Most of the remainder results from a lack of personal balance control. Falling can cause long-term disabilities in the elderly, sometimes resulting in lower quality of life, and is also associated with increased medical expenses and personal care costs. In this study, we developed a falling assessment system to evaluate and classify individuals into four graded falling risk groups. During the test, all subjects were required to wear a self-developed dynamic measurement system and to perform two balance tests: a “Timed Up and Go Test” and a “30-Second Chair Stand Test.” We obtained 29 characteristic parameters from the data recorded during these tests. Next, we performed group classification. Eigenvalues were normalized, and a principal component analysis (PCA) was performed. After identifying informative characteristic parameters, support vector machine (SVM) was used to classify individuals as members of one of the four falling risk groups. These included low-, moderate-, high-, and extreme-risk groups. Using unreduced data of the 29 characteristic parameters extracted from the two balance tests, the accuracy of the SVM classification in allocating individuals to the correct group was 97.5%. After PCA, the 29 characteristic parameters were reduced to eight principal components, and the SVM classification method using these eight principal components was 93.25%.
{"title":"A RISK CLASSIFICATION SYSTEM FOR ELDERLY FALLS USING SUPPORT VECTOR MACHINE","authors":"Chi-Chih Wu, C. Chiu, Su-Yi Fu","doi":"10.4015/s101623722250017x","DOIUrl":"https://doi.org/10.4015/s101623722250017x","url":null,"abstract":"Falls are a multi-factor problem that poses a serious risk to the elderly. Approximately, 60% of falls are caused by a number of known factors, including the environment, which accounts for approximately 25–45% of falling risk. Most of the remainder results from a lack of personal balance control. Falling can cause long-term disabilities in the elderly, sometimes resulting in lower quality of life, and is also associated with increased medical expenses and personal care costs. In this study, we developed a falling assessment system to evaluate and classify individuals into four graded falling risk groups. During the test, all subjects were required to wear a self-developed dynamic measurement system and to perform two balance tests: a “Timed Up and Go Test” and a “30-Second Chair Stand Test.” We obtained 29 characteristic parameters from the data recorded during these tests. Next, we performed group classification. Eigenvalues were normalized, and a principal component analysis (PCA) was performed. After identifying informative characteristic parameters, support vector machine (SVM) was used to classify individuals as members of one of the four falling risk groups. These included low-, moderate-, high-, and extreme-risk groups. Using unreduced data of the 29 characteristic parameters extracted from the two balance tests, the accuracy of the SVM classification in allocating individuals to the correct group was 97.5%. After PCA, the 29 characteristic parameters were reduced to eight principal components, and the SVM classification method using these eight principal components was 93.25%.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"39 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83626341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-08DOI: 10.4015/s1016237222500223
H. Tsai, Chia-Shin Wei, Ya-Chu Hsieh, I-Miao Chen, Pin-Yu Yeh, Darren Shih, Chiun-Li Chin
Today, radiologists observe a mammogram to determine whether breast tissue is normal. However, calcifications on the mammogram are so small that sometimes radiologists cannot locate them without a magnified observation to make a judgment. If clusters formed by malignant calcifications are found, the patient should undergo a needle localization surgical biopsy to determine whether the calcification cluster is benign or malignant. However, a needle localization surgical biopsy is an invasive examination. This invasive examination leaves scars, causes pain, and makes the patient feel uncomfortable and unwilling to receive an immediate biopsy, resulting in a delay in treatment time. The researcher cooperated with a medical radiologist to analyze calcification clusters and lesions, employing a mammogram using a multi-architecture deep learning algorithm to solve these problems. The features of the location of the cluster and its benign or malignant status are collected from the needle localization surgical biopsy images and medical order and are used as the target training data in this study. This study adopts the steps of a radiologist examination. First, VGG16 is used to locate calcification clusters on the mammogram, and then the Mask R-CNN model is used to find micro-calcifications in the cluster to remove background interference. Finally, an Inception V3 model is used to analyze whether the calcification cluster is benign or malignant. The prediction precision rates of VGG16, Mask R-CNN, and Inception V3 in this study are 93.63%, 99.76%, and 88.89%, respectively, proving that they can effectively assist radiologists and help patients avoid undergoing a needle localization surgical biopsy.
{"title":"CALCIFICATION CLUSTERS AND LESIONS ANALYSIS IN MAMMOGRAM USING MULTI-ARCHITECTURE DEEP LEARNING ALGORITHMS","authors":"H. Tsai, Chia-Shin Wei, Ya-Chu Hsieh, I-Miao Chen, Pin-Yu Yeh, Darren Shih, Chiun-Li Chin","doi":"10.4015/s1016237222500223","DOIUrl":"https://doi.org/10.4015/s1016237222500223","url":null,"abstract":"Today, radiologists observe a mammogram to determine whether breast tissue is normal. However, calcifications on the mammogram are so small that sometimes radiologists cannot locate them without a magnified observation to make a judgment. If clusters formed by malignant calcifications are found, the patient should undergo a needle localization surgical biopsy to determine whether the calcification cluster is benign or malignant. However, a needle localization surgical biopsy is an invasive examination. This invasive examination leaves scars, causes pain, and makes the patient feel uncomfortable and unwilling to receive an immediate biopsy, resulting in a delay in treatment time. The researcher cooperated with a medical radiologist to analyze calcification clusters and lesions, employing a mammogram using a multi-architecture deep learning algorithm to solve these problems. The features of the location of the cluster and its benign or malignant status are collected from the needle localization surgical biopsy images and medical order and are used as the target training data in this study. This study adopts the steps of a radiologist examination. First, VGG16 is used to locate calcification clusters on the mammogram, and then the Mask R-CNN model is used to find micro-calcifications in the cluster to remove background interference. Finally, an Inception V3 model is used to analyze whether the calcification cluster is benign or malignant. The prediction precision rates of VGG16, Mask R-CNN, and Inception V3 in this study are 93.63%, 99.76%, and 88.89%, respectively, proving that they can effectively assist radiologists and help patients avoid undergoing a needle localization surgical biopsy.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"127 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85716361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-02DOI: 10.4015/s1016237222500156
J. Nisha, V. Gopi, P. Palanisamy
Colonoscopy allows doctors to check the abnormalities in the intestinal tract without any surgical operations. The major problem in the Computer-Aided Diagnosis (CAD) of colonoscopy images is the low illumination condition of the images. This study aims to provide an image enhancement method and feature extraction and classification techniques for detecting polyps in colonoscopy images. We propose a novel image enhancement method with a Pyramid Histogram of Oriented Gradients (PHOG) feature extractor to detect polyps in the colonoscopy images. The approach is evaluated across different classifiers, such as Multi-Layer Perceptron (MLP), Adaboost, Support Vector Machine (SVM), and Random Forest. The proposed method has been trained using the publicly available databases CVC ClinicDB and tested in ETIS Larib and CVC ColonDB. The proposed approach outperformed the existing state-of-the-art methods on both databases. The reliability of the classifiers performance was examined by comparing their F1 score, precision, F2 score, recall, and accuracy. PHOG with Random Forest classifier outperformed the existing methods in terms of recall of 97.95%, precision 98.46%, F1 score 98.20%, F2 score of 98.00%, and accuracy of 98.21% in the CVC-ColonDB. In the ETIS-LARIB dataset it attained a recall value of 96.83%, precision 98.65%, F1 score 97.73%, F2 score 98.59%, and accuracy of 97.75%. We observed that the proposed image enhancement method with PHOG feature extraction and the Random Forest classifier will help doctors to evaluate and analyze anomalies from colonoscopy data and make decisions quickly.
{"title":"CLASSIFICATION OF INFORMATIVE FRAMES IN COLONOSCOPY VIDEO BASED ON IMAGE ENHANCEMENT AND PHOG FEATURE EXTRACTION","authors":"J. Nisha, V. Gopi, P. Palanisamy","doi":"10.4015/s1016237222500156","DOIUrl":"https://doi.org/10.4015/s1016237222500156","url":null,"abstract":"Colonoscopy allows doctors to check the abnormalities in the intestinal tract without any surgical operations. The major problem in the Computer-Aided Diagnosis (CAD) of colonoscopy images is the low illumination condition of the images. This study aims to provide an image enhancement method and feature extraction and classification techniques for detecting polyps in colonoscopy images. We propose a novel image enhancement method with a Pyramid Histogram of Oriented Gradients (PHOG) feature extractor to detect polyps in the colonoscopy images. The approach is evaluated across different classifiers, such as Multi-Layer Perceptron (MLP), Adaboost, Support Vector Machine (SVM), and Random Forest. The proposed method has been trained using the publicly available databases CVC ClinicDB and tested in ETIS Larib and CVC ColonDB. The proposed approach outperformed the existing state-of-the-art methods on both databases. The reliability of the classifiers performance was examined by comparing their F1 score, precision, F2 score, recall, and accuracy. PHOG with Random Forest classifier outperformed the existing methods in terms of recall of 97.95%, precision 98.46%, F1 score 98.20%, F2 score of 98.00%, and accuracy of 98.21% in the CVC-ColonDB. In the ETIS-LARIB dataset it attained a recall value of 96.83%, precision 98.65%, F1 score 97.73%, F2 score 98.59%, and accuracy of 97.75%. We observed that the proposed image enhancement method with PHOG feature extraction and the Random Forest classifier will help doctors to evaluate and analyze anomalies from colonoscopy data and make decisions quickly.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"22 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78845815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-28DOI: 10.4015/s1016237222500211
Shimaa M. Khder, Eman A. H. Mohamed, I. Yassine
Microscopic digital image processing paves the way for study and evaluation of blastomere identification and localization as a preprocessing step for the embryos selection for the In VitroFertilization (IVF) transfer. Computer vision aims at developing automated image system to localize and grade blastomeres before injection. In this paper, we propose a clustering-based system that supports the localization and counting of blastomeres. The dataset, employed in this study, is formed of 50 Images collected at Assisted Reproduction Technology (ART) Unit, International Islamic Center for Population Studies and Research, Al-Azhar University, Egypt. The proposed system is formed of 2 modules named preprocessing and segmentation modules, where different algorithms were investigated for each module. The preprocessing module includes Image denoising and enhancement tasks. Whereas the edge enhancement investigates the performance of Ostu’s thresholding, Canny and Sobel edge detection techniques, while employing Circular Hough Transform (CHT) for the segmentation task. A fusion-based algorithm was then employed to merge the segmented Blastomeres of the previously defined systems to boost the performance through integrated blastomeres, as well the confidence in localization. The fusion-based algorithm showed very promising results reaching an average Precision, sensitivity, and Overall Quality of 87.9%, 92.9%, and 82.3%, respectively.
{"title":"A CLUSTERING-BASED FUSION SYSTEM FOR BLASTOMERE LOCALIZATION","authors":"Shimaa M. Khder, Eman A. H. Mohamed, I. Yassine","doi":"10.4015/s1016237222500211","DOIUrl":"https://doi.org/10.4015/s1016237222500211","url":null,"abstract":"Microscopic digital image processing paves the way for study and evaluation of blastomere identification and localization as a preprocessing step for the embryos selection for the In VitroFertilization (IVF) transfer. Computer vision aims at developing automated image system to localize and grade blastomeres before injection. In this paper, we propose a clustering-based system that supports the localization and counting of blastomeres. The dataset, employed in this study, is formed of 50 Images collected at Assisted Reproduction Technology (ART) Unit, International Islamic Center for Population Studies and Research, Al-Azhar University, Egypt. The proposed system is formed of 2 modules named preprocessing and segmentation modules, where different algorithms were investigated for each module. The preprocessing module includes Image denoising and enhancement tasks. Whereas the edge enhancement investigates the performance of Ostu’s thresholding, Canny and Sobel edge detection techniques, while employing Circular Hough Transform (CHT) for the segmentation task. A fusion-based algorithm was then employed to merge the segmented Blastomeres of the previously defined systems to boost the performance through integrated blastomeres, as well the confidence in localization. The fusion-based algorithm showed very promising results reaching an average Precision, sensitivity, and Overall Quality of 87.9%, 92.9%, and 82.3%, respectively.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"36 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89044928","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}
The femoral prostheses experience versatile loading during the activities of daily living (ADL) and subsequently encounter a variety of stresses. This paper presents a detailed finite element analysis (FEA) of the femoral implant under transient loading. The distinct loading patterns corresponding to the most commonly occurring ADL are utilized for simulating the different scenarios. The CT reconstructed CAD model of the human femur bone assembled with a femoral implant is utilized for this study. The loading scenarios for walking, stair ascent, stair descent, standing up, sitting down, standing on one leg and knee bending are simulated by using the joint reaction forces and moments, corresponding to a body weight of 750 N, for the FEA. The results of this study are validated using a preliminary in-house built experimental setup comprising a fixture for a stainless steel femoral implant with sensors attached at three locations on the implant. The results indicate that the highest stresses are generated in case of the stair descent, stair ascent and standing on a single leg type of activities. These activities that generate high stresses on the implant surfaces are not suitable for the longevity of the implant and are therefore not advisable for post-operative patients.
{"title":"FINITE ELEMENT ANALYSIS OF FEMORAL PROSTHESIS UNDER TRANSIENT LOADING FOR MULTIPLE ACTIVITIES OF DAILY LIVING","authors":"Rabiteja Patra, Shreeshan Jena, Harish Chandra Das, Asita Kumar Rath","doi":"10.4015/s1016237222500168","DOIUrl":"https://doi.org/10.4015/s1016237222500168","url":null,"abstract":"The femoral prostheses experience versatile loading during the activities of daily living (ADL) and subsequently encounter a variety of stresses. This paper presents a detailed finite element analysis (FEA) of the femoral implant under transient loading. The distinct loading patterns corresponding to the most commonly occurring ADL are utilized for simulating the different scenarios. The CT reconstructed CAD model of the human femur bone assembled with a femoral implant is utilized for this study. The loading scenarios for walking, stair ascent, stair descent, standing up, sitting down, standing on one leg and knee bending are simulated by using the joint reaction forces and moments, corresponding to a body weight of 750 N, for the FEA. The results of this study are validated using a preliminary in-house built experimental setup comprising a fixture for a stainless steel femoral implant with sensors attached at three locations on the implant. The results indicate that the highest stresses are generated in case of the stair descent, stair ascent and standing on a single leg type of activities. These activities that generate high stresses on the implant surfaces are not suitable for the longevity of the implant and are therefore not advisable for post-operative patients.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"249 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85044111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-17DOI: 10.4015/s1016237222500193
Anita Desiani, Erwin, B. Suprihatin, Sinta Bella Agustina
The retina is the most important part of the eye. Early detection of retinal disease can be done through the passage of the blood vessels of the retina. Enhancement of the quality of retinal images that have both noise and noise is the first step in image processing to help improve the accuracy of the results for image segmentation and extraction. Images store a lot of information, but often there is a decrease in quality or image defects. So that images that have experienced interference or noise are easily interpreted, then the image can be manipulated into other images of better quality using image processing techniques or methods. The neural network-based method that is currently popular is deep learning. The segmentation process is currently a widely used method of deep learning that has grown rapidly used in various studies. One of the popular methods is Convolutional Neural Network (CNN). CNN can handle large-dimensional data such as images because the input to CNN is in the form of a matrix. Since the findings of retinal blood vessel segmentation are often inaccurate and there is always noise, this study will look at how to segment retinal images in blood vessels using CNN U-Net and LadderNet methods. Proper segmentation of retinal blood vessels can be the first step to detecting a disease. Segmentation and analysis of retinal blood vessels can assist medical personnel in detecting the severity of a disease. The stages of image enhancement used are Histogram Equalization and Clahe. Segmentation of blood vessels is done using CNN U-Net and LadderNet Methods. The results of the application of the enhancement and segmentation using the U-Net and LadderNet methods on training and on testing data were tested on the DRIVE dataset. The results of measurement of accuracy, specificity, sensitivity and F1 Score of blood vessel segmentation using the U-Net CNN method were 95.46%, 98.56%, 74.20%, and 80.63%, respectively. While the results of the CNN LadderNet method were 95.47%, 98.42%, 75.19%, and 80.86%, respectively. Based on the results of blood vessel segmentation from two proposed methods, the result of the CNN LaddetNet method is greater than the CNN U-Net method in accuracy, sensitivity, and F1 Score. The proposed approach will be further developed in the future, with the aim of increasing the value of the blood vessel segmentation process evaluation outcomes.
{"title":"A ROBUST TECHNIQUES OF ENHANCEMENT AND SEGMENTATION BLOOD VESSELS IN RETINAL IMAGE USING DEEP LEARNING","authors":"Anita Desiani, Erwin, B. Suprihatin, Sinta Bella Agustina","doi":"10.4015/s1016237222500193","DOIUrl":"https://doi.org/10.4015/s1016237222500193","url":null,"abstract":"The retina is the most important part of the eye. Early detection of retinal disease can be done through the passage of the blood vessels of the retina. Enhancement of the quality of retinal images that have both noise and noise is the first step in image processing to help improve the accuracy of the results for image segmentation and extraction. Images store a lot of information, but often there is a decrease in quality or image defects. So that images that have experienced interference or noise are easily interpreted, then the image can be manipulated into other images of better quality using image processing techniques or methods. The neural network-based method that is currently popular is deep learning. The segmentation process is currently a widely used method of deep learning that has grown rapidly used in various studies. One of the popular methods is Convolutional Neural Network (CNN). CNN can handle large-dimensional data such as images because the input to CNN is in the form of a matrix. Since the findings of retinal blood vessel segmentation are often inaccurate and there is always noise, this study will look at how to segment retinal images in blood vessels using CNN U-Net and LadderNet methods. Proper segmentation of retinal blood vessels can be the first step to detecting a disease. Segmentation and analysis of retinal blood vessels can assist medical personnel in detecting the severity of a disease. The stages of image enhancement used are Histogram Equalization and Clahe. Segmentation of blood vessels is done using CNN U-Net and LadderNet Methods. The results of the application of the enhancement and segmentation using the U-Net and LadderNet methods on training and on testing data were tested on the DRIVE dataset. The results of measurement of accuracy, specificity, sensitivity and F1 Score of blood vessel segmentation using the U-Net CNN method were 95.46%, 98.56%, 74.20%, and 80.63%, respectively. While the results of the CNN LadderNet method were 95.47%, 98.42%, 75.19%, and 80.86%, respectively. Based on the results of blood vessel segmentation from two proposed methods, the result of the CNN LaddetNet method is greater than the CNN U-Net method in accuracy, sensitivity, and F1 Score. The proposed approach will be further developed in the future, with the aim of increasing the value of the blood vessel segmentation process evaluation outcomes.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"55 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81336055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-14DOI: 10.4015/s1016237222500144
Pouya Nosratkhah, J. Frounchi
Detecting the QRS complex on an ECG signal leads to precious information about the signal under study. Different noises, arrhythmias, and diseases alter the shape and energy of the signal, making it harder to detect the QRS points. Several algorithms for QRS detection have been proposed and most of them merely focus on precision improvement, and therefore certain limitations have emerged with regard to deployment of these algorithms. As a result, while developing the new algorithm, not only efforts have been made to keep the precision at a high level, but also it has been tried to keep an eye on the generality of the algorithm, and to eliminate the end user limitations as much as possible. To this end, we have used an exclusive mother wavelet together with an artificial neural network to develop an algorithm which not only has superior precision, but also does not require changing the tuning parameters for each different signal. In other words, the algorithm extracts the required parameters automatically. In this method, first, an exclusive mother wavelet identical to the input signal is formed. Then, by using the mother wavelet, matrices containing sufficient data to be processed by the neural network are developed. Using these matrices, the existing QRSs will be detected with a sensitivity of 99.81[Formula: see text] on MIT-BIH and 99.49[Formula: see text] on physiozoo datasets.
{"title":"A COMPREHENSIVE QRS DETECTION METHOD BASED ON EXCLUSIVE MOTHER WAVELET AND ARTIFICIAL NEURAL NETWORK","authors":"Pouya Nosratkhah, J. Frounchi","doi":"10.4015/s1016237222500144","DOIUrl":"https://doi.org/10.4015/s1016237222500144","url":null,"abstract":"Detecting the QRS complex on an ECG signal leads to precious information about the signal under study. Different noises, arrhythmias, and diseases alter the shape and energy of the signal, making it harder to detect the QRS points. Several algorithms for QRS detection have been proposed and most of them merely focus on precision improvement, and therefore certain limitations have emerged with regard to deployment of these algorithms. As a result, while developing the new algorithm, not only efforts have been made to keep the precision at a high level, but also it has been tried to keep an eye on the generality of the algorithm, and to eliminate the end user limitations as much as possible. To this end, we have used an exclusive mother wavelet together with an artificial neural network to develop an algorithm which not only has superior precision, but also does not require changing the tuning parameters for each different signal. In other words, the algorithm extracts the required parameters automatically. In this method, first, an exclusive mother wavelet identical to the input signal is formed. Then, by using the mother wavelet, matrices containing sufficient data to be processed by the neural network are developed. Using these matrices, the existing QRSs will be detected with a sensitivity of 99.81[Formula: see text] on MIT-BIH and 99.49[Formula: see text] on physiozoo datasets.","PeriodicalId":8862,"journal":{"name":"Biomedical Engineering: Applications, Basis and Communications","volume":"41 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2022-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85214238","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：