Pub Date : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974219
Wenyan Wei, Xiangchu Feng
Edge extraction is a central problem in image processing and it is a necessary step for computer vision tasks. In this paper, a novel global method P-GSG for edge extraction of image under Poisson noise is given, which is based on sparse representation. Furthermore, a game model which combines P-GSG with total variation denoising is proposed to get better results. As two players, P-GSG model can apply with iteration latent clean image to robustly get the gradient under the Poisson noise, on the other hand, TV denoising can get an edge-preserving latent clean image, which overcomes the shortcoming of over-smoothing. By cooperation and competition between two tasks, we can attain a satisfactory solution for this game model-Nash equilibrium. The algorithms of P-GSG and TV denoising are given. Based on above algorithms, it is obvious that alternate iteration method is easily used to solve this game model. The effectiveness of these two models is shown by numerical experiments.
{"title":"A novel global method for edge extraction under Poisson noise: game theory","authors":"Wenyan Wei, Xiangchu Feng","doi":"10.1109/CCISP55629.2022.9974219","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974219","url":null,"abstract":"Edge extraction is a central problem in image processing and it is a necessary step for computer vision tasks. In this paper, a novel global method P-GSG for edge extraction of image under Poisson noise is given, which is based on sparse representation. Furthermore, a game model which combines P-GSG with total variation denoising is proposed to get better results. As two players, P-GSG model can apply with iteration latent clean image to robustly get the gradient under the Poisson noise, on the other hand, TV denoising can get an edge-preserving latent clean image, which overcomes the shortcoming of over-smoothing. By cooperation and competition between two tasks, we can attain a satisfactory solution for this game model-Nash equilibrium. The algorithms of P-GSG and TV denoising are given. Based on above algorithms, it is obvious that alternate iteration method is easily used to solve this game model. The effectiveness of these two models is shown by numerical experiments.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128765969","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974280
Zhang Ruoxi, Hu Lei, Cao Xiaoqing
In 2020, the world witnessed a new and severe global health crisis: the outbreak of Covid-19 and the number of positive cases and deaths around the world rose at a frightening rate throughout 2021. Given its highly contagious, convenient and efficient detection means are significant. At present, RT-PCR testing is the common diagnostic method for COVID-19 cases, but the process is time-consuming and inefficient. The recent COVID-19 radiology literature has focused on CT imaging because of its higher sensitivity, but it leads to high costs compared to X-ray imaging. Nowadays, many AI applications are focused on quantification and identification of infections to fully automate diagnoses to assist medical experts. Therefore, we compared seven classic network models including ResNet50, VGG16, VGG19, InceptionV3, InceptionResNetV2, MobileNetV1, DenseNet169 by the diversity measure. DenseNet169 performed pretty well with an accuracy of 97.5% on the training set and 96.58% on the test set. After comparing the results of different model fusion methods, stacking these models by four folds and selecting the tree classifier as second layer models outweighed other methods which reach 100% on the test set, which is helpful in the diagnosis of COVID19.
{"title":"COVID-19 Image Classification Method Based on Model Fusion","authors":"Zhang Ruoxi, Hu Lei, Cao Xiaoqing","doi":"10.1109/CCISP55629.2022.9974280","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974280","url":null,"abstract":"In 2020, the world witnessed a new and severe global health crisis: the outbreak of Covid-19 and the number of positive cases and deaths around the world rose at a frightening rate throughout 2021. Given its highly contagious, convenient and efficient detection means are significant. At present, RT-PCR testing is the common diagnostic method for COVID-19 cases, but the process is time-consuming and inefficient. The recent COVID-19 radiology literature has focused on CT imaging because of its higher sensitivity, but it leads to high costs compared to X-ray imaging. Nowadays, many AI applications are focused on quantification and identification of infections to fully automate diagnoses to assist medical experts. Therefore, we compared seven classic network models including ResNet50, VGG16, VGG19, InceptionV3, InceptionResNetV2, MobileNetV1, DenseNet169 by the diversity measure. DenseNet169 performed pretty well with an accuracy of 97.5% on the training set and 96.58% on the test set. After comparing the results of different model fusion methods, stacking these models by four folds and selecting the tree classifier as second layer models outweighed other methods which reach 100% on the test set, which is helpful in the diagnosis of COVID19.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129116034","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974542
Kaizhi Peng, Gang Cui, Rui Fu, Binbin Xu
In this paper, the characteristics of electromagnetic pulse and its influence on high-frequency communication are studied, the electromagnetic pulse coupling path and vulnerable points of high-frequency communication system are analyzed, and the coupling path model is established. On this basis, the electromagnetic pulse conduction coupling protection method of high-frequency communication system is designed. Finally, the designed protection efficiency is simulated, analyzed and tested. The test results show that the proposed method has an electromagnetic pulse protection capability of not less than 54dB for the RF interface. Thereby, the system survivability in the high-frequency communication strong interference environment is improved.
{"title":"Electromagnetic pulse protection technology of high frequency communication system","authors":"Kaizhi Peng, Gang Cui, Rui Fu, Binbin Xu","doi":"10.1109/CCISP55629.2022.9974542","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974542","url":null,"abstract":"In this paper, the characteristics of electromagnetic pulse and its influence on high-frequency communication are studied, the electromagnetic pulse coupling path and vulnerable points of high-frequency communication system are analyzed, and the coupling path model is established. On this basis, the electromagnetic pulse conduction coupling protection method of high-frequency communication system is designed. Finally, the designed protection efficiency is simulated, analyzed and tested. The test results show that the proposed method has an electromagnetic pulse protection capability of not less than 54dB for the RF interface. Thereby, the system survivability in the high-frequency communication strong interference environment is improved.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127733456","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974553
Di Xiao, Zhao Lv, Shiang Hu
The microstate analysis of EEG signals makes full use of the spatial information of the brain topographic map, and reflects the active association of different brain regions. Different from the traditional EEG features that mostly focus on single-channel information, the microstate feature contains the spatio-temporal information of EEG signals. Unlike microstate studies that mostly focus on dimensional emotions, the experiments classify positive, neutral, and negative discrete emotions using the SEED database. This work filters the data of a single subject into five frequency bands and calculates the microstate topographic maps of EEG signals in different frequency bands, respectively. The extracted features of microstate classes are coverage, duration, occurrence, and transition probability between microstates. The gender difference as to the dominant microstate pattern for emotions and the comparison between microstates, we found that the brain activity of males in three emotional states and females in negative emotions were related to the frontal-occipital pattern, the females of positive and neutral emotional states were associated with the left and right brain areas. We also investigated the traditional power spectra features, these features which be fused over frequency bands or not fused were fed into the classifiers such as the K-Nearest Neighbor (KNN) and the the Support Vector Machine(SVM) to classify discrete emotional labels in SEED. The average classification accuracy of 15 subjects was 97.67±1.4% and 92.58±3.24%, respectively.
{"title":"A study on Frequency Domain Microstate Feature Fusion for EEG Emotion Recognition","authors":"Di Xiao, Zhao Lv, Shiang Hu","doi":"10.1109/CCISP55629.2022.9974553","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974553","url":null,"abstract":"The microstate analysis of EEG signals makes full use of the spatial information of the brain topographic map, and reflects the active association of different brain regions. Different from the traditional EEG features that mostly focus on single-channel information, the microstate feature contains the spatio-temporal information of EEG signals. Unlike microstate studies that mostly focus on dimensional emotions, the experiments classify positive, neutral, and negative discrete emotions using the SEED database. This work filters the data of a single subject into five frequency bands and calculates the microstate topographic maps of EEG signals in different frequency bands, respectively. The extracted features of microstate classes are coverage, duration, occurrence, and transition probability between microstates. The gender difference as to the dominant microstate pattern for emotions and the comparison between microstates, we found that the brain activity of males in three emotional states and females in negative emotions were related to the frontal-occipital pattern, the females of positive and neutral emotional states were associated with the left and right brain areas. We also investigated the traditional power spectra features, these features which be fused over frequency bands or not fused were fed into the classifiers such as the K-Nearest Neighbor (KNN) and the the Support Vector Machine(SVM) to classify discrete emotional labels in SEED. The average classification accuracy of 15 subjects was 97.67±1.4% and 92.58±3.24%, respectively.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116890988","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974356
Gao Junya, Cao Shuai
With the increase of business scenarios in 5G communication, the 5G bearer network puts forward higher requirements in terms of bandwidth, time delay, pan-connection and reliability, and also puts forward extremely high requirements for network-level protection technology. The introduction of segment routing tunnel technology, the innovative establishment of 5G efficient carrying network. Due to the working mechanism of the SR tunnel, the traditional signal degradation protection technology is no longer suitable. This paper proposes a protection scheme for the existence of signal degradation in the Segment Routing - Best Effort tunnel through the OAM message transmission alarm. The signal degradation detection and ISIS protocol, can realize link protection, in order to further improve the user experience, design method trigger TI-LFA protection business protection reverse, improve the reliability and viability of 5G carrying network, confirmed that the scheme has the ability to detect and protect the business flow signal, can be protected in the east-west eX2 traffic business.
{"title":"Link protection for the signal degradation of the SR-BE tunnels in the SPN","authors":"Gao Junya, Cao Shuai","doi":"10.1109/CCISP55629.2022.9974356","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974356","url":null,"abstract":"With the increase of business scenarios in 5G communication, the 5G bearer network puts forward higher requirements in terms of bandwidth, time delay, pan-connection and reliability, and also puts forward extremely high requirements for network-level protection technology. The introduction of segment routing tunnel technology, the innovative establishment of 5G efficient carrying network. Due to the working mechanism of the SR tunnel, the traditional signal degradation protection technology is no longer suitable. This paper proposes a protection scheme for the existence of signal degradation in the Segment Routing - Best Effort tunnel through the OAM message transmission alarm. The signal degradation detection and ISIS protocol, can realize link protection, in order to further improve the user experience, design method trigger TI-LFA protection business protection reverse, improve the reliability and viability of 5G carrying network, confirmed that the scheme has the ability to detect and protect the business flow signal, can be protected in the east-west eX2 traffic business.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124281910","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}
Distribution cable is one of the most important equipment in the process of power transmission. In the manufacturing process of distribution cable, it is inevitable that there will be defects in production and manufacturing, which will further lead to the generation of partial discharge (PD) of distribution cable. It is of great significance to monitor and identify the types of partial discharges to ensure the running status of distribution cables and improve the service life of cables. In this paper, a fault identification algorithm of PD UHF signals based on multi-information fusion is proposed. Firstly, four common types of PD defect models are simulated. The time-domain fault signals and PRPD pattern of PD are extracted by UHF sensors, and the typical features of PD fault signals are further obtained. The traditional machine learning algorithms support vector machine (SVM) and Gradient Boosted Decision Tree (GBDT) are used to statistically learn the signal features, and the deep residual network is used to identify the PRPD pattern image. A multi-model weighted fusion algorithm is used to identify PD defect types. The proposed method has a certain generalization ability and makes full use of the information contained in the discharge pulse and PRPD image to realize the task of insulation fault diagnosis.
{"title":"Partial Discharge Identification of Distribution Cable Based on Multi-Feature Machine Learning","authors":"Xueyou Huang, Yu Zhang, Guoqing Wang, Zhe Xu, Boyong Lin, Liang Wang","doi":"10.1109/CCISP55629.2022.9974345","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974345","url":null,"abstract":"Distribution cable is one of the most important equipment in the process of power transmission. In the manufacturing process of distribution cable, it is inevitable that there will be defects in production and manufacturing, which will further lead to the generation of partial discharge (PD) of distribution cable. It is of great significance to monitor and identify the types of partial discharges to ensure the running status of distribution cables and improve the service life of cables. In this paper, a fault identification algorithm of PD UHF signals based on multi-information fusion is proposed. Firstly, four common types of PD defect models are simulated. The time-domain fault signals and PRPD pattern of PD are extracted by UHF sensors, and the typical features of PD fault signals are further obtained. The traditional machine learning algorithms support vector machine (SVM) and Gradient Boosted Decision Tree (GBDT) are used to statistically learn the signal features, and the deep residual network is used to identify the PRPD pattern image. A multi-model weighted fusion algorithm is used to identify PD defect types. The proposed method has a certain generalization ability and makes full use of the information contained in the discharge pulse and PRPD image to realize the task of insulation fault diagnosis.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115438392","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974559
Ying Ruan, Lei Chen, Fang Yang
A 2.4GHz class E power amplifier (PA) for new generation Bluetooth Low Energy application is designed and implemented in 22nm silicon on insulator (SOI) CMOS technology. The proposed PA is fully integrated, which has a two-stage differential structure with cascode stacking power transistors to improve the efficiency and prevent the breakdown with almost no increase in die area. S parameter simulation results show that output impedance matching S22 is less than - 12.1dB in the frequency range from 2.4GHz to 2.5GHz. The power amplifier achieves a power gain of 15.9dB, output power of 4.9dBm, and a power added efficiency(PAE) of 41.5%.
{"title":"A 2.4GHz SOI CMOS Power Amplifier for New Generation Bluetooth Application","authors":"Ying Ruan, Lei Chen, Fang Yang","doi":"10.1109/CCISP55629.2022.9974559","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974559","url":null,"abstract":"A 2.4GHz class E power amplifier (PA) for new generation Bluetooth Low Energy application is designed and implemented in 22nm silicon on insulator (SOI) CMOS technology. The proposed PA is fully integrated, which has a two-stage differential structure with cascode stacking power transistors to improve the efficiency and prevent the breakdown with almost no increase in die area. S parameter simulation results show that output impedance matching S22 is less than - 12.1dB in the frequency range from 2.4GHz to 2.5GHz. The power amplifier achieves a power gain of 15.9dB, output power of 4.9dBm, and a power added efficiency(PAE) of 41.5%.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115480697","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974269
Zhou Ying-xi, Shao Lei
With the rapid development of digital signal processing technology in image processing, radar, communication, fast Fourier transform (FFT) has important research significance. FFT is a fast algorithm of discrete Fourier Transform (DFT). Based on FPGA chip, this paper implements FFT of 256 and 1024 points using pipeline architecture by combining the Mixed-Radix algorithm and Cooly-Tukey algorithm. The main work of this paper includes the optimization of data uploading and storage in FPGA chip, the architecture analysis of mixed-radix algorithm implementation, and the improvement of FFT data computing architecture. Full use of FPGA parallel processing, easy programming implementation, pipeline processing architecture and other advantages to achieve high-speed FFT calculation.
{"title":"Design of mixed-radix FFT algorithm based on FPGA","authors":"Zhou Ying-xi, Shao Lei","doi":"10.1109/CCISP55629.2022.9974269","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974269","url":null,"abstract":"With the rapid development of digital signal processing technology in image processing, radar, communication, fast Fourier transform (FFT) has important research significance. FFT is a fast algorithm of discrete Fourier Transform (DFT). Based on FPGA chip, this paper implements FFT of 256 and 1024 points using pipeline architecture by combining the Mixed-Radix algorithm and Cooly-Tukey algorithm. The main work of this paper includes the optimization of data uploading and storage in FPGA chip, the architecture analysis of mixed-radix algorithm implementation, and the improvement of FFT data computing architecture. Full use of FPGA parallel processing, easy programming implementation, pipeline processing architecture and other advantages to achieve high-speed FFT calculation.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115648089","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 : 2022-11-01DOI: 10.1109/CCISP55629.2022.9974503
Xiao Hu, Hongtu Xie, Jiaxing Chen, Jinfeng He, Guoqian Wang
Compared with the traditional monostatic synthetic aperture radar (SAR), the low frequency (LF) ultra-wideband (UWB) one-stationary bistatic SAR (OS-BiSAR) has the advantages of flexible configuration, difficulty to intercept, anti-jamming, and strong penetrating ability, thus it has the broader application prospect. However, the measured echo data of the LF UWB OS-BiSAR is still less, especially the measured echo data of the moving targets. Thus, the hybrid echo data generation of the natural scenes including the moving targets for the LF UWB OS-BiSAR is proposed. First, the inverse range-Doppler (RD) algorithm is used to generate the natural static scene echo data from the real SAR image. After superimposing the echo data of moving targets, the mixed echo data containing both the natural static scene and the moving targets is obtained. This method alleviates the shortage of the measured echo data of the LF UWB OS-BiSAR. Simulation experiments are shown to demonstrate the validity of the present method.
{"title":"Hybrid Echo Data Generation of Natural Scenes Including Moving Targets for Low Frequency Ultra-wideband One-stationary Bistatic SAR","authors":"Xiao Hu, Hongtu Xie, Jiaxing Chen, Jinfeng He, Guoqian Wang","doi":"10.1109/CCISP55629.2022.9974503","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974503","url":null,"abstract":"Compared with the traditional monostatic synthetic aperture radar (SAR), the low frequency (LF) ultra-wideband (UWB) one-stationary bistatic SAR (OS-BiSAR) has the advantages of flexible configuration, difficulty to intercept, anti-jamming, and strong penetrating ability, thus it has the broader application prospect. However, the measured echo data of the LF UWB OS-BiSAR is still less, especially the measured echo data of the moving targets. Thus, the hybrid echo data generation of the natural scenes including the moving targets for the LF UWB OS-BiSAR is proposed. First, the inverse range-Doppler (RD) algorithm is used to generate the natural static scene echo data from the real SAR image. After superimposing the echo data of moving targets, the mixed echo data containing both the natural static scene and the moving targets is obtained. This method alleviates the shortage of the measured echo data of the LF UWB OS-BiSAR. Simulation experiments are shown to demonstrate the validity of the present method.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124967330","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}
A accurately segmented tumor region has great significance in assessing the sick person with the conditions. Aiming at the problems that existing deep learning has limited ability to perceive 3D context in medical image segmentation tasks, and the edge information of tumors cannot be well preserved. Therefore, we propose an effective method to improve 3D U-Net model for segmentation. Firstly, adding a multi-scale feature extraction module can extract more receptive fields and improve the adaptability of the model to features of different scales. Secondly, decoding the position attention mechanism is added after the first upsampling, so that more effective global and local details can be extracted. Using the public dataset BraTS 2020 for training and testing, the average dice values of the proposed network model in the overall tumor area, tumor core region and tumor enhancement area reached 88.96%, 86.48% and 84.32%, respectively. From those results, we can see that the improved model has a better segmentation effect in evaluation indexes than basic models.
{"title":"A multi-scale method based on U-Net for brain tumor segmentation","authors":"Lei Wang, Mingtao Liu, Yunyu Wang, Xianbiao Bai, Mengjie Zhu, Fuchun Zhang","doi":"10.1109/CCISP55629.2022.9974427","DOIUrl":"https://doi.org/10.1109/CCISP55629.2022.9974427","url":null,"abstract":"A accurately segmented tumor region has great significance in assessing the sick person with the conditions. Aiming at the problems that existing deep learning has limited ability to perceive 3D context in medical image segmentation tasks, and the edge information of tumors cannot be well preserved. Therefore, we propose an effective method to improve 3D U-Net model for segmentation. Firstly, adding a multi-scale feature extraction module can extract more receptive fields and improve the adaptability of the model to features of different scales. Secondly, decoding the position attention mechanism is added after the first upsampling, so that more effective global and local details can be extracted. Using the public dataset BraTS 2020 for training and testing, the average dice values of the proposed network model in the overall tumor area, tumor core region and tumor enhancement area reached 88.96%, 86.48% and 84.32%, respectively. From those results, we can see that the improved model has a better segmentation effect in evaluation indexes than basic models.","PeriodicalId":431851,"journal":{"name":"2022 7th International Conference on Communication, Image and Signal Processing (CCISP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121518031","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：