Pub Date : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00064
L. Zhiming, Miao Sheng
The classification of heart sounds plays an important role in the detection of congenital heart disease. In recent years, the classification of heart sounds has made some progress, but it is mainly based on traditional acoustic features, which may be insufficient for heart sounds and easily influenced by complex and changeable environmental factors. In this paper, aiming at the traditional Mel cepstrum coefficient (MFCC), an improvement of heart sound signal characteristics is proposed, and a new window function expression is proposed in the windowing link of the extraction process. The data source of our 2016 Heart Sound Challenge serves as the data set. Finally, the new MFCC is used for feature learning and classification tasks, and compared with the traditional MFCC. A variety of recognition algorithms show that the average accuracy of the improved MFCC classification and recognition reaches 93.52%.
{"title":"Heart sound recognition method of congenital heart disease based on improved cepstrum coefficient features","authors":"L. Zhiming, Miao Sheng","doi":"10.1109/ICCEAI52939.2021.00064","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00064","url":null,"abstract":"The classification of heart sounds plays an important role in the detection of congenital heart disease. In recent years, the classification of heart sounds has made some progress, but it is mainly based on traditional acoustic features, which may be insufficient for heart sounds and easily influenced by complex and changeable environmental factors. In this paper, aiming at the traditional Mel cepstrum coefficient (MFCC), an improvement of heart sound signal characteristics is proposed, and a new window function expression is proposed in the windowing link of the extraction process. The data source of our 2016 Heart Sound Challenge serves as the data set. Finally, the new MFCC is used for feature learning and classification tasks, and compared with the traditional MFCC. A variety of recognition algorithms show that the average accuracy of the improved MFCC classification and recognition reaches 93.52%.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114355216","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00060
Kai Yao, Shanna Zhuang, Yale Zhao, Zhengyou Wang
Falls would cause harm to the fall-prone group, including the elderly, children and the disabled people. Fall behavior recognition is important to protect them from being injured. In order to improve the accurancy of the fall behavior recognition, a two-stream neural network model based on MobileNetV2, a lightweight deep neural network, is proposed in this paper. Experiments are conducted on the following three datasets, UR fall detection dataset, Multiple cameras fall dataset and Le2i fall detection dataset. The performances of the presented model are compared with those of single-stream model, 3D-CNN, and two-stream model combining CNN and optical stream. The effectiveness of the proposed method is indicated.
{"title":"Fall Recognition in Open Scenes","authors":"Kai Yao, Shanna Zhuang, Yale Zhao, Zhengyou Wang","doi":"10.1109/ICCEAI52939.2021.00060","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00060","url":null,"abstract":"Falls would cause harm to the fall-prone group, including the elderly, children and the disabled people. Fall behavior recognition is important to protect them from being injured. In order to improve the accurancy of the fall behavior recognition, a two-stream neural network model based on MobileNetV2, a lightweight deep neural network, is proposed in this paper. Experiments are conducted on the following three datasets, UR fall detection dataset, Multiple cameras fall dataset and Le2i fall detection dataset. The performances of the presented model are compared with those of single-stream model, 3D-CNN, and two-stream model combining CNN and optical stream. The effectiveness of the proposed method is indicated.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125175514","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00080
Zhang Yujie, Cai Lecai, Zhiming Wu, Kui Cheng, Di Wu, Keyuan Tang
The accuracy of gait recognition method would be affected by the occlusion of clothing object being carried. To overcome the problem, this paper adopted the method based on CNN(Convolutional neural network) and LSTM(Long and short term memory network) to build gait recognition models. Specifically, CNN is used to extract the spatial features of pedestrians in training videos, and the LSTM network is used to extract the temporal and spatial features of gait video sequences. We optimize the LSTM network structure and parameters of the gait recognition models and compare the establish models with the models built in other research. The results show that the models establish in our research perform better that the models in other research.
{"title":"Research on gait recognition algorithm based on deep learning","authors":"Zhang Yujie, Cai Lecai, Zhiming Wu, Kui Cheng, Di Wu, Keyuan Tang","doi":"10.1109/ICCEAI52939.2021.00080","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00080","url":null,"abstract":"The accuracy of gait recognition method would be affected by the occlusion of clothing object being carried. To overcome the problem, this paper adopted the method based on CNN(Convolutional neural network) and LSTM(Long and short term memory network) to build gait recognition models. Specifically, CNN is used to extract the spatial features of pedestrians in training videos, and the LSTM network is used to extract the temporal and spatial features of gait video sequences. We optimize the LSTM network structure and parameters of the gait recognition models and compare the establish models with the models built in other research. The results show that the models establish in our research perform better that the models in other research.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121774465","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00021
Yunfei Han, Yi Wang, Yupeng Ma
Image quality usually refers to the degree of error of the distorted image relative to the reference image in the human visual perception system. Image quality assessment is to score the image quality objectively. No-reference image quality assessment is limited to distorted image information, which is more challenging in the field of computer vision. In this paper, we proposed an approach based on difference image generation to address this problem. First, by removing the up-sampling layer and batch normalization layer in the Super-Resolution Generative Adversarial Network (SRGAN) to build a difference image generation model, and applying the content loss function to optimize the model. Then, the regression network is constructed based on the convolutional neural network (CNN). The regression network contains 4 convolutional layers and 2 fully connected layers and learns the correlation between the generated difference image and the image quality score to predict the distorted image quality. Finally, comparative experiments were evaluated on three public datasets. Compared with the previous state-of-the-art methods, our method obtains similar results on the LIVE dataset and achieves significant improvement on the TID2013 and CSIQ datasets. The results demonstrate that our proposed approach achieves state-of-the-art image quality prediction.
{"title":"Generative Difference Image for Blind Image Quality Assessment","authors":"Yunfei Han, Yi Wang, Yupeng Ma","doi":"10.1109/ICCEAI52939.2021.00021","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00021","url":null,"abstract":"Image quality usually refers to the degree of error of the distorted image relative to the reference image in the human visual perception system. Image quality assessment is to score the image quality objectively. No-reference image quality assessment is limited to distorted image information, which is more challenging in the field of computer vision. In this paper, we proposed an approach based on difference image generation to address this problem. First, by removing the up-sampling layer and batch normalization layer in the Super-Resolution Generative Adversarial Network (SRGAN) to build a difference image generation model, and applying the content loss function to optimize the model. Then, the regression network is constructed based on the convolutional neural network (CNN). The regression network contains 4 convolutional layers and 2 fully connected layers and learns the correlation between the generated difference image and the image quality score to predict the distorted image quality. Finally, comparative experiments were evaluated on three public datasets. Compared with the previous state-of-the-art methods, our method obtains similar results on the LIVE dataset and achieves significant improvement on the TID2013 and CSIQ datasets. The results demonstrate that our proposed approach achieves state-of-the-art image quality prediction.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123815881","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00096
Li Ruiyu, Li Yue, L. Xing, L. Meng, Zhang Chenyu, L. Qingwen, Hou Jinjie
Objective: To investigate the changes of ankle-brachial index (ABI) and peak velocity of dorsal foot artery in patients with type 2 diabetes mellitus with lower extremity vascular disease treated with Yingweifang. Methods: 36 cases of type 2 diabetes mellitus with lower extremity vascular disease were observed, including 13 cases of Yin deficiency and hot, 9 cases of qi and Yin deficiency and 14 cases of Yin and Yang deficiency. Oral “Yingwei Fang” capsule, 5 capsules per time, 3 times a day, combined with the dialectical TCM dialectical theory of treatment, conventional treatment such as hypoglycemia. Changes in the ankle-brachial index (ABI) and peak flow rate of dorsal foot artery were measured after 150 days of treatment compared with before treatment. RESULTS: After treatment, ABI and peak flow rate of dorsal foot artery in diabetic lower extremity vascular disease patients were changed in different degrees (P < 0.05, P<0.01), and ABI was improved more obviously (P <0.01). Qi and Yin deficiency and Yin and Yang deficiency were also improved (P<0.05). The comparison of desiccation and heat between Qi and Yin deficiency and Yin deficiency after treatment (P<0.05); CONCLUSIONS: Yingwei Fang can significantly improve the ankle-brachial index (ABI) and peak velocity of dorsal foot artery in patients with lower extremity vascular disease of type 2 diabetes mellitus.
{"title":"Effect of “Yingwei Fang” on Lower Extremity Vascular Lesions in Patients with Different Syndromic Type 2 Diabetes","authors":"Li Ruiyu, Li Yue, L. Xing, L. Meng, Zhang Chenyu, L. Qingwen, Hou Jinjie","doi":"10.1109/ICCEAI52939.2021.00096","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00096","url":null,"abstract":"Objective: To investigate the changes of ankle-brachial index (ABI) and peak velocity of dorsal foot artery in patients with type 2 diabetes mellitus with lower extremity vascular disease treated with Yingweifang. Methods: 36 cases of type 2 diabetes mellitus with lower extremity vascular disease were observed, including 13 cases of Yin deficiency and hot, 9 cases of qi and Yin deficiency and 14 cases of Yin and Yang deficiency. Oral “Yingwei Fang” capsule, 5 capsules per time, 3 times a day, combined with the dialectical TCM dialectical theory of treatment, conventional treatment such as hypoglycemia. Changes in the ankle-brachial index (ABI) and peak flow rate of dorsal foot artery were measured after 150 days of treatment compared with before treatment. RESULTS: After treatment, ABI and peak flow rate of dorsal foot artery in diabetic lower extremity vascular disease patients were changed in different degrees (P < 0.05, P<0.01), and ABI was improved more obviously (P <0.01). Qi and Yin deficiency and Yin and Yang deficiency were also improved (P<0.05). The comparison of desiccation and heat between Qi and Yin deficiency and Yin deficiency after treatment (P<0.05); CONCLUSIONS: Yingwei Fang can significantly improve the ankle-brachial index (ABI) and peak velocity of dorsal foot artery in patients with lower extremity vascular disease of type 2 diabetes mellitus.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131384810","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00052
Pengcheng Li, Haitao Zhang, Haohan Hu, Wanlong Liu, Li Zhang
Based on the massive data of Shanghai Pudong Electric Power Co., Ltd., this paper studies the load data prediction. Based on the theoretical support of KNN, linear regression and ARIMA algorithm, the local optimal decomposition prediction model was established. In this paper, the million-magnitude load control data are used for model training and experiments. The traditional prediction method is a single day dimension model, while the research method in this paper is time-divided optimal model prediction. For different periods of each day, according to the data characteristics, match and train the best local optimal prediction model for each period. The experimental results show that the accuracy of the local optimal decomposition model is higher than that of the single model, which can fully meet the business needs of the current energy data prediction, and also provide support for the subsequent prediction of other energy data.
{"title":"Application research of massive power data prediction based on combinatorial model","authors":"Pengcheng Li, Haitao Zhang, Haohan Hu, Wanlong Liu, Li Zhang","doi":"10.1109/ICCEAI52939.2021.00052","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00052","url":null,"abstract":"Based on the massive data of Shanghai Pudong Electric Power Co., Ltd., this paper studies the load data prediction. Based on the theoretical support of KNN, linear regression and ARIMA algorithm, the local optimal decomposition prediction model was established. In this paper, the million-magnitude load control data are used for model training and experiments. The traditional prediction method is a single day dimension model, while the research method in this paper is time-divided optimal model prediction. For different periods of each day, according to the data characteristics, match and train the best local optimal prediction model for each period. The experimental results show that the accuracy of the local optimal decomposition model is higher than that of the single model, which can fully meet the business needs of the current energy data prediction, and also provide support for the subsequent prediction of other energy data.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125251123","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00048
Wanzhao Li, Peng Zhang, Wei Huang
Human emotions always have been reflected by the facial expression. In recent year, the facial expression recognition has been found that it can be treated as a multi-label task and some databases (such as JAFFE, FER+, RAF-ML.) which include information of multi-label facial expression also have been utilize to address relate issue. Simultaneously, some deep learning methods also be used to solve multi-label facial expression task, such as VGG13 and Deep Bi-Manifold CNN (DBM-CNN). But there are also have many weakness such as the inaccurate recognition of multi-label expressions. To overcome this drawback, a novel Deep learning with local constraint framework, called DL- LC framework, is proposed. The proposed framework will use the MTCNN as an implement to crop the local constraints features which include the infromation of facial expression. And the ResNet18 has been applied as a backbone network to extract the feature from the global and local constraint images, which can get more details of original image after incorporating local constraints in this new framework. The effectiveness of this model has been testified through rigorous experiments in this study. Comprehensive analyses reveal that, this model is outperform the recent state-of-the-art approaches for multi-label facial expression recognition.
{"title":"A New Deep Learning Method for Multi-label Facial Expression Recognition based on Local Constraint Features","authors":"Wanzhao Li, Peng Zhang, Wei Huang","doi":"10.1109/ICCEAI52939.2021.00048","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00048","url":null,"abstract":"Human emotions always have been reflected by the facial expression. In recent year, the facial expression recognition has been found that it can be treated as a multi-label task and some databases (such as JAFFE, FER+, RAF-ML.) which include information of multi-label facial expression also have been utilize to address relate issue. Simultaneously, some deep learning methods also be used to solve multi-label facial expression task, such as VGG13 and Deep Bi-Manifold CNN (DBM-CNN). But there are also have many weakness such as the inaccurate recognition of multi-label expressions. To overcome this drawback, a novel Deep learning with local constraint framework, called DL- LC framework, is proposed. The proposed framework will use the MTCNN as an implement to crop the local constraints features which include the infromation of facial expression. And the ResNet18 has been applied as a backbone network to extract the feature from the global and local constraint images, which can get more details of original image after incorporating local constraints in this new framework. The effectiveness of this model has been testified through rigorous experiments in this study. Comprehensive analyses reveal that, this model is outperform the recent state-of-the-art approaches for multi-label facial expression recognition.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128285524","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00056
Linjie Luo, Chengzhi Deng, Zhaoming Wu, Shengqian Wang, Tianyu Ye
The traditional image processing method has a low detection rate for various kinds of automobile airbag surface defects in the production process, which is difficult to meet the actual demand of industrial production. In order to improve the detection rate of automobile airbag surface defects and meet the real-time requirements of industrial detection, this paper proposes an improved Faster RCNN deep learning algorithm. Firstly, the method adopts the E-FPN to enhance the feature extraction ability of the network for multi-scale targets. Then, ROI Align algorithm is introduced instead of ROI Pooling algorithm to improve the detection ability of small targets. Finally, the designed Light Head is used to improve the running speed of the network. The experimental results show that the average precision of the improved Faster RCNN algorithm for automobile airbag defect detection reaches 97.2%, and the detection time is 23.73 milliseconds, which is obviously superior to the original algorithm and has higher detection accuracy and practicability.
{"title":"Automobile airbag defect detection algorithm based on improved Faster RCNN","authors":"Linjie Luo, Chengzhi Deng, Zhaoming Wu, Shengqian Wang, Tianyu Ye","doi":"10.1109/ICCEAI52939.2021.00056","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00056","url":null,"abstract":"The traditional image processing method has a low detection rate for various kinds of automobile airbag surface defects in the production process, which is difficult to meet the actual demand of industrial production. In order to improve the detection rate of automobile airbag surface defects and meet the real-time requirements of industrial detection, this paper proposes an improved Faster RCNN deep learning algorithm. Firstly, the method adopts the E-FPN to enhance the feature extraction ability of the network for multi-scale targets. Then, ROI Align algorithm is introduced instead of ROI Pooling algorithm to improve the detection ability of small targets. Finally, the designed Light Head is used to improve the running speed of the network. The experimental results show that the average precision of the improved Faster RCNN algorithm for automobile airbag defect detection reaches 97.2%, and the detection time is 23.73 milliseconds, which is obviously superior to the original algorithm and has higher detection accuracy and practicability.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132929664","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00046
Wenchao Lu, Wenhang Ge, Rongyu Li, Lin Yang
According to well-stablished results in the literature, the Long Short Term Memory (LSTM) model is one of learning models most widely used in stock price prediction given its characteristic feature. In this paper, we employ a novel neural network, Gated Recurrent Unit (GRU), in performing individual stock price prediction task in Chinese A-share market. As shown by the experiment results, GRU has comparable performance with LSTM and both them outperform the conventional Recurrent Neural Network (RNN) model. Further, regression analysis indicates that there may exist quadratic relationship between prediction accuracy and training data size. Thereby attempts have been made on adding nonlinear time-weight functions to substantially improve the prediction accuracy with the LSTM model.
{"title":"A Comparative Study on the Individual Stock Price Prediction with the Application of Neural Network Models","authors":"Wenchao Lu, Wenhang Ge, Rongyu Li, Lin Yang","doi":"10.1109/ICCEAI52939.2021.00046","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00046","url":null,"abstract":"According to well-stablished results in the literature, the Long Short Term Memory (LSTM) model is one of learning models most widely used in stock price prediction given its characteristic feature. In this paper, we employ a novel neural network, Gated Recurrent Unit (GRU), in performing individual stock price prediction task in Chinese A-share market. As shown by the experiment results, GRU has comparable performance with LSTM and both them outperform the conventional Recurrent Neural Network (RNN) model. Further, regression analysis indicates that there may exist quadratic relationship between prediction accuracy and training data size. Thereby attempts have been made on adding nonlinear time-weight functions to substantially improve the prediction accuracy with the LSTM model.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130768005","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 : 2021-08-01DOI: 10.1109/ICCEAI52939.2021.00005
Feihong Li, Peng Zhang, Wei Huang
Arterial spin labeling (ASL) images that are capable to quantitatively measure the cerebral blood flow receive increasing research attention in recent dementia diseases diagnosis studies. However, this important and relatively new imaging modality is unfortunately not commonly seen in many well-established image-based dementia datasets, including the ADNI-1/2/3/Go datasets. Hence, synthesizing ASL images to supplement this important modality is valuable. In this study, a new framework based on a cascade of generative adversarial networks (GANs) and difference images generated from a Laplacian pyramid is proposed. This framework is novel as it is the first attempt to incorporate difference images for synthesizing medical images. Experimental results based on a 355-demented patient dataset and ADNI-1 dataset suggest that, this new framework outperforms all state-of-the-arts in ASL image synthesis. Also, synthesized ASL images obtained by this new framework are capable to significantly improve the accuracy of dementia diseases diagnosis performance.
{"title":"A Novel Framework to Synthesize Arterial Spin Labeling Images using Difference Images","authors":"Feihong Li, Peng Zhang, Wei Huang","doi":"10.1109/ICCEAI52939.2021.00005","DOIUrl":"https://doi.org/10.1109/ICCEAI52939.2021.00005","url":null,"abstract":"Arterial spin labeling (ASL) images that are capable to quantitatively measure the cerebral blood flow receive increasing research attention in recent dementia diseases diagnosis studies. However, this important and relatively new imaging modality is unfortunately not commonly seen in many well-established image-based dementia datasets, including the ADNI-1/2/3/Go datasets. Hence, synthesizing ASL images to supplement this important modality is valuable. In this study, a new framework based on a cascade of generative adversarial networks (GANs) and difference images generated from a Laplacian pyramid is proposed. This framework is novel as it is the first attempt to incorporate difference images for synthesizing medical images. Experimental results based on a 355-demented patient dataset and ADNI-1 dataset suggest that, this new framework outperforms all state-of-the-arts in ASL image synthesis. Also, synthesized ASL images obtained by this new framework are capable to significantly improve the accuracy of dementia diseases diagnosis performance.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130080766","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：