Pub Date : 2019-12-01DOI: 10.1109/ist48021.2019.9010232
Copyright
版权
{"title":"Copyright","authors":"","doi":"10.1109/ist48021.2019.9010232","DOIUrl":"https://doi.org/10.1109/ist48021.2019.9010232","url":null,"abstract":"Copyright","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117288278","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010217
M. Khalil, E. Fantino, P. Liatsis
In recent years, the number of resident space objects has increased dramatically. The chances of space objects colliding with each other are increasing, thus posing a threat to active satellites and future space missions. Identifying and detecting space debris is essential in ensuring the security of space assets. In this contribution, we investigate the effectiveness of several feature extraction and oversampling techniques by attempting classification of real-world light curves of space objects using eight machine learning methods. Three feature extraction tools are utilized to represent the light curves as sets of features, i.e., FATS (Feature Analysis for Time Series), feets (feATURE eXTRACTOR FOR tIME sERIES) and UPSILoN (AUtomated Classification for Periodic Variable Stars using MachIne LearNing) public tools. To address the problem of class imbalance, four oversampling techniques are applied, i.e., ADaptive SYNthetic Sampling Approach (ADASYN), Synthetic Minority Oversampling TEchnique (SMOTE), and two modifications of SMOTE, specifically, Borderline-SMOTE and Support Vector Machine (SVM)-SMOTE. Results show that the features extracted using the FATS tool lead to a better performance, and therefore, they appear to represent light curves in a more informative manner, compared to feets and UPSILoN. Moreover, the use of SVM-SMOTE technique improves the performance of the utilized classifiers more than other oversampling techniques.
{"title":"Evaluation of Oversampling Strategies in Machine Learning for Space Debris Detection","authors":"M. Khalil, E. Fantino, P. Liatsis","doi":"10.1109/IST48021.2019.9010217","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010217","url":null,"abstract":"In recent years, the number of resident space objects has increased dramatically. The chances of space objects colliding with each other are increasing, thus posing a threat to active satellites and future space missions. Identifying and detecting space debris is essential in ensuring the security of space assets. In this contribution, we investigate the effectiveness of several feature extraction and oversampling techniques by attempting classification of real-world light curves of space objects using eight machine learning methods. Three feature extraction tools are utilized to represent the light curves as sets of features, i.e., FATS (Feature Analysis for Time Series), feets (feATURE eXTRACTOR FOR tIME sERIES) and UPSILoN (AUtomated Classification for Periodic Variable Stars using MachIne LearNing) public tools. To address the problem of class imbalance, four oversampling techniques are applied, i.e., ADaptive SYNthetic Sampling Approach (ADASYN), Synthetic Minority Oversampling TEchnique (SMOTE), and two modifications of SMOTE, specifically, Borderline-SMOTE and Support Vector Machine (SVM)-SMOTE. Results show that the features extracted using the FATS tool lead to a better performance, and therefore, they appear to represent light curves in a more informative manner, compared to feets and UPSILoN. Moreover, the use of SVM-SMOTE technique improves the performance of the utilized classifiers more than other oversampling techniques.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122904282","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010133
S. Hagagg, F. Khalifa, H. Abdeltawab, A. Elnakib, M. Abdelazim, M. Ghazal, H. Sandhu, A. El-Baz
Accurate segmentation of the vitreous region of retinal images is an essential step in any computer-aided diagnosis system for severity grading of vitreous inflammation. In this paper, we developed a framework to automatically segment the vitreous region from optical coherence tomography (OCT) images of uveitis eyes using fully convolutional neural network (CNN), U-net model. The CNN model consists of a contracting path to capture context and an expanding path for precise localization and utilizes the binary cross entropy (BCE) loss. The model has been tested on 200 OCT scans of eyes having different grades of uveitis severity (0–4). The developed CNN model demonstrated not only high accuracy of vitreous segmentation, documented by two evaluation metrics (Dice coefficient (DC) and Hausdorff distance (HD) are 0.94 ± 0.13 and 0.036 mm ± 0.086 mm, respectively), but also requires a small number of images for training. In addition, the training process of the model converges in few iterations, affording fast speed contrary to what is expected in such cases of deep learning problems. These preliminary results show the promise of the proposed CNN for accurate segmentation of the vitreous region from retinal OCT images.
{"title":"A CNN-Based Framework for Automatic Vitreous Segemntation from OCT Images","authors":"S. Hagagg, F. Khalifa, H. Abdeltawab, A. Elnakib, M. Abdelazim, M. Ghazal, H. Sandhu, A. El-Baz","doi":"10.1109/IST48021.2019.9010133","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010133","url":null,"abstract":"Accurate segmentation of the vitreous region of retinal images is an essential step in any computer-aided diagnosis system for severity grading of vitreous inflammation. In this paper, we developed a framework to automatically segment the vitreous region from optical coherence tomography (OCT) images of uveitis eyes using fully convolutional neural network (CNN), U-net model. The CNN model consists of a contracting path to capture context and an expanding path for precise localization and utilizes the binary cross entropy (BCE) loss. The model has been tested on 200 OCT scans of eyes having different grades of uveitis severity (0–4). The developed CNN model demonstrated not only high accuracy of vitreous segmentation, documented by two evaluation metrics (Dice coefficient (DC) and Hausdorff distance (HD) are 0.94 ± 0.13 and 0.036 mm ± 0.086 mm, respectively), but also requires a small number of images for training. In addition, the training process of the model converges in few iterations, affording fast speed contrary to what is expected in such cases of deep learning problems. These preliminary results show the promise of the proposed CNN for accurate segmentation of the vitreous region from retinal OCT images.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133282483","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010237
C. Spanakis, E. Mathioudakis, N. Kampanis, M. Tsiknakis, K. Marias
The successful application and reported robustness of Mutual Information both in rigid and nonrigid image registration over the last decades gave rise to an ongoing research on other information based similarity metrics emanating from Renyi Divergence. To the best of our knowledge however, this is the first paper studying the effects of Renyi parameter in combination with a subsampling factor in image registration accuracy. To this end, a series of experiments are presented with respect to the effect of Renyi's parameter and the subsampling factor in registration accuracy. Our results show that the increase of the Renyi parameter and the percentage of the pixels used leads, on average, to the reduction of the registration error.
{"title":"Renyi divergence and non-deterministic subsampling in Rigid Image Registration","authors":"C. Spanakis, E. Mathioudakis, N. Kampanis, M. Tsiknakis, K. Marias","doi":"10.1109/IST48021.2019.9010237","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010237","url":null,"abstract":"The successful application and reported robustness of Mutual Information both in rigid and nonrigid image registration over the last decades gave rise to an ongoing research on other information based similarity metrics emanating from Renyi Divergence. To the best of our knowledge however, this is the first paper studying the effects of Renyi parameter in combination with a subsampling factor in image registration accuracy. To this end, a series of experiments are presented with respect to the effect of Renyi's parameter and the subsampling factor in registration accuracy. Our results show that the increase of the Renyi parameter and the percentage of the pixels used leads, on average, to the reduction of the registration error.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488518","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010204
Yuan Chen, Zhigang Li, Yunjie Yang, J. Jia, Chang Liu, M. Lucquiaud
Packed column flooding is caused by an excessive liquid enters a packed column, leading to a significant increase in pressure drop, liquid hold-up, and loss in separation efficiency. In this simulation study, electrical capacitance tomography (ECT) is used to monitor the flooding phenomenon in a packed column by inferring the liquid hold-up from the reconstructed images. A simulation study is implemented to reconstruct the liquid phase distributions across the structured packed column by using ECT during the flooding process. The flooding phenomenon is simulated by adding a different amount of water droplets from the bottom of the packed column to above. The capacitances measured using the ECT sensor are then used to reconstruct the images of the liquid phase distributions. A significant difference in the liquid phase distributions and the liquid hold-up can be observed during the flooding region. Simulation results demonstrate that ECT is capable of monitoring and further predicting the flooding phenomenon with high-fidelity liquid phase distribution image and the calculated liquid hold-up.
{"title":"Simulation of Flooding Phenomenon in Packed Column using Electrical Capacitance Tomography","authors":"Yuan Chen, Zhigang Li, Yunjie Yang, J. Jia, Chang Liu, M. Lucquiaud","doi":"10.1109/IST48021.2019.9010204","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010204","url":null,"abstract":"Packed column flooding is caused by an excessive liquid enters a packed column, leading to a significant increase in pressure drop, liquid hold-up, and loss in separation efficiency. In this simulation study, electrical capacitance tomography (ECT) is used to monitor the flooding phenomenon in a packed column by inferring the liquid hold-up from the reconstructed images. A simulation study is implemented to reconstruct the liquid phase distributions across the structured packed column by using ECT during the flooding process. The flooding phenomenon is simulated by adding a different amount of water droplets from the bottom of the packed column to above. The capacitances measured using the ECT sensor are then used to reconstruct the images of the liquid phase distributions. A significant difference in the liquid phase distributions and the liquid hold-up can be observed during the flooding region. Simulation results demonstrate that ECT is capable of monitoring and further predicting the flooding phenomenon with high-fidelity liquid phase distribution image and the calculated liquid hold-up.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114808588","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010333
Omar Dekhil, A. Naglah, M. Shaban, M. Ghazal, F. Taher, A. Elbaz
Diabetic retinopathy (DR) is a retinal disease caused by the high blood sugar levels that may damage and block the blood vessels feeding the retina. In the early stages of DR, the disease is asymptomatic; however, as the disease advances, a possible sudden loss of vision and blindness may occur. Therefore, an early diagnosis and staging of the disease is required to possibly slow down the progression of the disease and improve control of the symptoms. In response to the previous challenge, we introduce a computer aided diagnosis tool based on convolutional neural networks (CNN) to classify fundus images into one of the five stages of DR. The proposed CNN consists of a preprocessing stage, five stage convolutional, rectified linear and pooling layers followed by three fully connected layers. Transfer learning was adopted to minimize overfitting by training the model on a larger dataset of 3.2 million images (i.e. ImageNet) prior to the use of the model on the APTOS 2019 Kaggle DR dataset. The proposed approach has achieved a testing accuracy of 77% and a quadratic weighted kappa score of 78%, offering a promising solution for a successful early diagnose and staging of DR in an automated fashion.
{"title":"Deep Learning Based Method for Computer Aided Diagnosis of Diabetic Retinopathy","authors":"Omar Dekhil, A. Naglah, M. Shaban, M. Ghazal, F. Taher, A. Elbaz","doi":"10.1109/IST48021.2019.9010333","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010333","url":null,"abstract":"Diabetic retinopathy (DR) is a retinal disease caused by the high blood sugar levels that may damage and block the blood vessels feeding the retina. In the early stages of DR, the disease is asymptomatic; however, as the disease advances, a possible sudden loss of vision and blindness may occur. Therefore, an early diagnosis and staging of the disease is required to possibly slow down the progression of the disease and improve control of the symptoms. In response to the previous challenge, we introduce a computer aided diagnosis tool based on convolutional neural networks (CNN) to classify fundus images into one of the five stages of DR. The proposed CNN consists of a preprocessing stage, five stage convolutional, rectified linear and pooling layers followed by three fully connected layers. Transfer learning was adopted to minimize overfitting by training the model on a larger dataset of 3.2 million images (i.e. ImageNet) prior to the use of the model on the APTOS 2019 Kaggle DR dataset. The proposed approach has achieved a testing accuracy of 77% and a quadratic weighted kappa score of 78%, offering a promising solution for a successful early diagnose and staging of DR in an automated fashion.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126754927","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010510
R. Hamoudi, M. Bettayeb, Areej Alsaafin, M. Hachim, Q. Nasir, A. B. Nassif
Deploying machine learning to improve medical diagnosis is a promising area. The purpose of this study is to identify and analyze unique genetic signatures for breast cancer grades using publicly available gene expression microarray data. The classification of cancer types is based on unsupervised feature learning. Unsupervised clustering use matrix algebra based on similarity measures which made it suitable for analyzing gene expression. The main advantage of the proposed approach is the ability to use gene expression data from different grades of breast cancer to generate features that automatically identify and enhance the cancer diagnosis. In this paper, we tested different similarity measures in order to find the best way that identifies the sets of genes with a common function using expression microarray data.
{"title":"Identifying Patterns of Breast Cancer Genetic Signatures using Unsupervised Machine Learning","authors":"R. Hamoudi, M. Bettayeb, Areej Alsaafin, M. Hachim, Q. Nasir, A. B. Nassif","doi":"10.1109/IST48021.2019.9010510","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010510","url":null,"abstract":"Deploying machine learning to improve medical diagnosis is a promising area. The purpose of this study is to identify and analyze unique genetic signatures for breast cancer grades using publicly available gene expression microarray data. The classification of cancer types is based on unsupervised feature learning. Unsupervised clustering use matrix algebra based on similarity measures which made it suitable for analyzing gene expression. The main advantage of the proposed approach is the ability to use gene expression data from different grades of breast cancer to generate features that automatically identify and enhance the cancer diagnosis. In this paper, we tested different similarity measures in order to find the best way that identifies the sets of genes with a common function using expression microarray data.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129215940","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010531
Haokun Wang, Maomao Zhang, Yunjie Yang
Complex-valued Electrical Capacitance Tomography (CVECT) system with multi-frequency excitation scheme has been implemented in recent studies for imaging both conductivity and permittivity components, where time-difference (TD) imaging method was employed. This paper explores the feasibility of performing frequency-difference (FD) imaging of CVECT using Multiple Measurement Vector (MMV) model. Experiments based on simulation data were performed to evaluate the proposed framework. Comparison with conventional Tikhonov regularization algorithm was presented. The results confirm that it is feasible to perform FD imaging with multifrequency CVECT system, and MMV outperforms conventional image reconstruction algorithms in terms of image quality and efficiency.
{"title":"Frequency-difference imaging for multi-frequency complex-valued ECT","authors":"Haokun Wang, Maomao Zhang, Yunjie Yang","doi":"10.1109/IST48021.2019.9010531","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010531","url":null,"abstract":"Complex-valued Electrical Capacitance Tomography (CVECT) system with multi-frequency excitation scheme has been implemented in recent studies for imaging both conductivity and permittivity components, where time-difference (TD) imaging method was employed. This paper explores the feasibility of performing frequency-difference (FD) imaging of CVECT using Multiple Measurement Vector (MMV) model. Experiments based on simulation data were performed to evaluate the proposed framework. Comparison with conventional Tikhonov regularization algorithm was presented. The results confirm that it is feasible to perform FD imaging with multifrequency CVECT system, and MMV outperforms conventional image reconstruction algorithms in terms of image quality and efficiency.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122815932","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010231
K. K. Singh, M. Bajpai
Mammogram enhancement plays vital role in detection of abnormality present in low contrast mammogram images. This paper explores a new application of Fractional Order Savitzky-Golay(SG) Differentiator for mammogram enhancement. It encompasses a new approach for low contrast mammogram image enhancement based on the concept of convolution. The enhancement is performed by three different test cases. The performance of proposed approaches is validated with quantitative as well as visual results. The result shows that the proposed algorithm produces better results. The effect of size of differentiator and order of derivative has also been analyzed.
{"title":"Fractional Order Savitzky-Golay Differentiator based Approach for Mammogram Enhancement","authors":"K. K. Singh, M. Bajpai","doi":"10.1109/IST48021.2019.9010231","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010231","url":null,"abstract":"Mammogram enhancement plays vital role in detection of abnormality present in low contrast mammogram images. This paper explores a new application of Fractional Order Savitzky-Golay(SG) Differentiator for mammogram enhancement. It encompasses a new approach for low contrast mammogram image enhancement based on the concept of convolution. The enhancement is performed by three different test cases. The performance of proposed approaches is validated with quantitative as well as visual results. The result shows that the proposed algorithm produces better results. The effect of size of differentiator and order of derivative has also been analyzed.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133454328","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 : 2019-12-01DOI: 10.1109/IST48021.2019.9010335
Reem T. Haweel, Omar Dekhil, A. Shalaby, Ali H. Mahmoud, M. Ghazal, R. Keynton, G. Barnes, A. El-Baz
Autism is a developmental disorder associated with difficulties in communication and social interaction. Autism diagnostic observation schedule (ADOS) is considered the gold standard in autism diagnosis, which estimates a score explaining the severity level for each individual. Currently, brain image modalities are being investigated for the development of objective technologies to diagnose Autism spectrum disorder (ASD). Alterations in functional activity is believed to be important in explaining autism causative factors. This paper presents a machine learning approach for grading severity level of the autistic subjects using task-based functional MRI data. The local features related to the functional activity of the brain is obtained from a speech experiment. According to ADOS reports, the adopted dataset is classified to three groups: Mild, moderate and severe. Our analysis is divided into two parts: (i) individual subject analysis and (ii) higher level group analysis. We use the individual analysis to extract the features used in classification, while the higher level analysis is used to infer the statistical differences between groups. The obtained classification accuracy is 78% using the random forest classifier.
{"title":"A Machine Learning Approach for Grading Autism Severity Levels Using Task-based Functional MRI","authors":"Reem T. Haweel, Omar Dekhil, A. Shalaby, Ali H. Mahmoud, M. Ghazal, R. Keynton, G. Barnes, A. El-Baz","doi":"10.1109/IST48021.2019.9010335","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010335","url":null,"abstract":"Autism is a developmental disorder associated with difficulties in communication and social interaction. Autism diagnostic observation schedule (ADOS) is considered the gold standard in autism diagnosis, which estimates a score explaining the severity level for each individual. Currently, brain image modalities are being investigated for the development of objective technologies to diagnose Autism spectrum disorder (ASD). Alterations in functional activity is believed to be important in explaining autism causative factors. This paper presents a machine learning approach for grading severity level of the autistic subjects using task-based functional MRI data. The local features related to the functional activity of the brain is obtained from a speech experiment. According to ADOS reports, the adopted dataset is classified to three groups: Mild, moderate and severe. Our analysis is divided into two parts: (i) individual subject analysis and (ii) higher level group analysis. We use the individual analysis to extract the features used in classification, while the higher level analysis is used to infer the statistical differences between groups. The obtained classification accuracy is 78% using the random forest classifier.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134104073","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：