2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)最新文献

{"title":"An Adaptive Topology-enhanced Deep Learning Method Combined with Fast Label Extraction Scheme for Retinal Vessel Segmentation","authors":"Yiheng Shi, Li Liu, Feng Li","doi":"10.1109/CISP-BMEI53629.2021.9624457","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624457","url":null,"abstract":"Retinal vessel segmentation is vital for the eye disease diagnosis and treatment. Recently, the deep learning method has been commonly used to achieve vessel segmentation, but it usually requires manual labels, which is time-consuming and laborious. In this work, we propose a fast vessel label extraction scheme, which can detect labels accurately and automatically. We first construct vesselness maps using the vessel structure features detected by the optimally oriented flux (OOF) filter. Then, we extracted the main vessel structure by the threshold approach. Thirdly, we utilize the local maximum method to detect the vessel skeleton that contains the entire vessel structures, especially the thin vessels. Besides, the existing topological enhancement methods do not consider the differences between thick and thin vessels, which may lead to poor extraction of thin vessels. Hence, we propose an adaptive topology-enhanced loss function to increase the different weights of thick and thin vessels. The correct topology of vessels is guaranteed, especially for thin vessels. The segmentation performance of the method is analyzed through extensive experiments. The results show that the method extracts excellent vessel labels, and the model trained with the automatically extracted labels is comparable to the supervised learning method.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123915207","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}

{"title":"Comb Jamming Mitigation in Frequency Hopping Spread Spectrum Communications Via Aid Block Sparse Bayesian Learning","authors":"Yongshun Zhang, Zhaoqing Yun, Jun Zheng, Feng Sun","doi":"10.1109/CISP-BMEI53629.2021.9624412","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624412","url":null,"abstract":"Comb jamming is an effective jamming mode for spectrum spread frequency hopping (FHSS) communication. In order to ensure the effectiveness of FHSS communication under strong interference conditions, it is necessary to suppress the comb jamming effectively. The existing FHSS communication comb jamming suppression method has the disadvantage that its application is limited by the high sampling rate. The compressive sensing (CS) is applied to the suppression of comb jamming in FHSS communication in this study. According to the different sparse characteristics of FHSS signal and comb jamming in frequency domain, a block sparse Bayesian learning (BSBL) based FHSS communication comb interference suppression model is constructed. To further improve the performance of the BSBL algorithm used in this model, a BSBL based algorithm, aid BSBL (ABSBL), is proposed exploiting the nature of comb jamming in the frequency domain, where the intra-correlation matrix is modeled as unit matrix. A comb jamming suppression algorithm for FHSS communications is designed based on ABSBL. The efficiency of comb jamming mitigation is improved while keeping the performance of comb jamming mitigation using the proposed algorithm. Besides, the performance of the algorithm does not rely on the block sparse structure information of the comb jamming. The simulation results show the performance of the proposed algorithm could suppress the comb jamming in FHSS communications effectively, and achieves better performance compared to other conventional algorithms.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124283204","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}

{"title":"Path-following Phase Unwrapping Algorithm based on Priority-guided Map","authors":"Heping Zhong, Han Li","doi":"10.1109/CISP-BMEI53629.2021.9624423","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624423","url":null,"abstract":"Phase unwrapping is a key step in interferometric signal processing. The unwrapped result directly affects the accuracy of the final reconstructed DEM. In order to improve the performance of phase unwrapping algorithm, a path-following phase unwrapping method guided by priority-guided map is proposed. Firstly, phase quality map is calculated according to the local phase characteristic, and high and low quality areas are segmented according to the quality value. Then, according to the distance between the high-quality point and the low-quality area, the guidance order of the high-quality area is determined to guide the unwrapping path to grow along the most reliable path, and the modified phase quality map is called priority-guided map. Finally, the priority-guided map is used as an indicator of the unwrapping path, and priority queue is used for quantitative guidance to obtain the final unwrapped result. In order to verify the performance of the proposed algorithm, phase unwrapping experiments are performed on simulated data and real InSAR interferogram, and the reliability of the proposed method is verified.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"48 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125884590","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}

{"title":"Entropy-Facilitated Machine Learning for Blood Pressure Estimation Using Electrocardiogram and Photoplethysmogram in a Wearable Device","authors":"K. Ma, Hong Hao, Hung-Chun Huang, Yun-Hsiang Tang","doi":"10.1109/CISP-BMEI53629.2021.9624370","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624370","url":null,"abstract":"Wearable devices that detect electrocardiogram (ECG) signals and photoplethysmogram (PPG) signals have been proposed to be effective at identifying early stage hypertension and estimating blood pressure. On the other hand, information entropy has been applied to determine whether certain biomedical signals represent pathological changes. In this study, Shannon entropy, sample entropy, and permutation entropy were derived from ECG and PPG signals collected through a wrist band wearable device, and were used to test whether the combination use of common features extracted from ECG and PPG, plus information entropies of ECG and PPG, may serve as effective features for blood pressure estimation when using machine learning-based linear regression (LR), random forest (RF), support vector regression (SVR), deep neural network (DNN), and XGBoost. Overall, the accuracy for blood pressure estimation was higher for diastolic blood pressure (DBP) than that for systolic blood pressure (SBP). The use of the entropies of ECG, PPG, or both, may increase the performance of BP estimation at an increase ranging from 3.3% to 10%. Accuracy of DBP estimation reached the highest when using entropies of ECG and PPG in either SVR or RF, with RF having a lower root-mean-square error (RMSE) compared with that for SVR. Likewise, SVR outperformed other models for the estimation of systolic blood pressure (SBP). The use of PPG entropy benefited the performance of LR, RF, and DNN in SBP estimation, which was better than when using entropies of ECG; for DNN, PPG entropy also brought about higher accuracy when it comes to the estimation of DBP. In conclusion, the use of entropies of ECG and PPG can improve the performance of blood pressure estimation, thus appears to be useful features in wearable devices that may facilitate blood pressure monitoring.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124995124","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}

{"title":"Study on Hyperspectral Inversion Model for Water Depth of the Yangtze Estuary Based on Remote Sensing Satellite","authors":"Deyan Peng, Xia Jiang, Qifan Bao, Qingli Li, Li Sun, Mei Zhou, Daoyang Bao, Fei Lou","doi":"10.1109/CISP-BMEI53629.2021.9624330","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624330","url":null,"abstract":"Based on GaoFen-5 remote sensing satellite, the satellite and ground synchronous monitoring experiment of water depth in the Yangtze Estuary was carried out, and the satellite and ground monitoring data required for modeling were obtained. The hyperspectral inversion model of water depth parameters is established by using function fitting method, and the output effect of the optimized model is given.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"268 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129900531","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}

{"title":"An Imaging Genetics Study Based on Brain-wide Genome-wide Association for Identifying Quantitative Trait Loci Related to Pain Sensitivity","authors":"Li Zhang, Yiwen Pan, G. Huang, Zhen Liang, Linling Li, Zhiguo Zhang","doi":"10.1109/CISP-BMEI53629.2021.9624411","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624411","url":null,"abstract":"Pain sensitivity has significant individual differences and it is associated with many factors, such as the differentiation of regional structural features of the brain and genetic variation among the population. Until now, a large part of the heritability of pain sensitivity remains unclear. This research focuses on exploring the genetic and neuroimage bases of pain sensitivity. A brain-wide genome-wide association study was carried out on 462 normal subjects, which were divided into high and low pain sensitivity groups according to the cold pain threshold from the cold pressor test. By using voxel-based morphometry (VBM), 116 brain structural features of grey matter (GM) densities were extracted based on high-resolution structural T1-weighted images from magnetic resonance imaging (MRI) scans. Afterward, a genome-wide association study (GWAS) was performed on each phenotype using quality-controlled genotype and analysis data including 755,875 single nucleotide polymorphisms (SNPs). Hierarchical clustering and heat maps were used to demonstrate the GWAS results. Significant associations between SNPs and phenotypes were reported at the threshold ($p < 10^{-6}$). SNPs in the NECTIN1 gene were identified to be strongly associated with various of brain regions, such as the amygdala, hippocampus, and regions at basal ganglia. These results suggest that the imaging genetics study is able to to reveal possible candidate genes and loci that may be associated with pain sensitivity.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121942357","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}

{"title":"An Improved Detection Algorithm For Pre-processing Problem Based On PointPillars","authors":"Jing Zhang, Da Xu, Jiajun Wang, Yunsong Li","doi":"10.1109/CISP-BMEI53629.2021.9624329","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624329","url":null,"abstract":"In the field of automatic driving, target detection by processing lidar point cloud is one of the key points. In order to effectively utilize point cloud information and reduce the information loss, this paper proposes a new pseudo-image generation method. Inspired by the basic idea of attention mechanism, a two-dimensional fusion attention module is proposed, which fuses features from multiple pseudo-images in height and channel dimensions, enhancing the ability of expression of feature information. The results show that the improved network performs better than the original network.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121950022","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}

{"title":"The Relationship Between Funcation Connectivity and Amyloid Accumulation in AD Continuum","authors":"Ronghua Ling, Yinghui Yang, Ling Wei, Chengcheng Fan","doi":"10.1109/CISP-BMEI53629.2021.9624445","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624445","url":null,"abstract":"Alzheimer's disease (AD) is characterized by the pathology's amyloid-beta and tau, as the common form of neurodegenerative dementia. There has great challenge for the understanding of AD functional and metabolic pathological changes. In this study, we aimed to study the relationship between functional connectivity and amyloid metabolic activity in the whole AD continuum. The functional magnetic resonance imaging (fMRI) and amyloid positron emission tomography (PET) imaging data were collected from the ADNI database, including 43 normal controls (NCs), 37 patients with mild cognitive impairment (MCI), and 32 patients with AD. We calculated the functional and amyloid metabolic connectivity for each subject and group. To assess the relationship between the functional connectivity of specific region and amyloid regions, we used the general linear model (GLM) model to measure the association between region-to-region functional connectivity and amyloid PET metabolic connectivity, controlled with other variances (sex, age, education level). The results showed that the average amyloid uptake of AD patients was highest ($1.62pm 0.22, mathrm{P} < 0.001$) rather than other groups (MCI: $1.41pm 0.18$ and NC: $1.13+0.21$). The functional connectivity of default mode network showed that there was significant connectivity difference ($mathrm{P} < 0.001$), and the functional strength was decrease with disease severity. There was significant positive correlation between functional connectivity and amyloid metabolic connectivity in both NC group ($mathrm{r}=0.31, mathrm{P} < 0.001$), MCI group ($mathrm{r}=0.42, mathrm{P} < 0.001$), and AD group ($mathrm{r}=0.47, mathrm{P} < 0.001$). This study showed that the higher amyloid metabolic connectivity in AD continuum maybe related with a higher AD-related functional connectivity strength, which may indicate the co-pathology of functional activity and amyloid accumulation might be caused using similar mechanisms.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116296675","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}

{"title":"Dual-Chip Guide Blind Device Based on STC89C51 and STM32","authors":"Li Cheng, Chenru Hao, Jingjing Zhang, Ziqiang Chi, Lisha Guo, Haibo Yang, Yanru Wu, Ruibin Zhao, Jing Zhang, Zipin Zhao","doi":"10.1109/CISP-BMEI53629.2021.9624377","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624377","url":null,"abstract":"The paper introduces a kind of dual-processor guide blind device based on chip STC89C51 and STM32. The STC89C51 single-chip microcontroller as the main controller, with an integrated ultrasonic module, calculates obstacle distance while achieving voice broadcast. STM32 single-chip microcontroller serially receives GPS module data to assist the main chip in completing GPS positioning and reduces the system response time by using dual processors while realizing the essential functions of the guide blind instrument. The reliability and practicability in the guide blind of the dual-chip device are verified by testing and analyzing the ranging error, system response time, and position offset rate on the dual-processor and the emergency program.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133598289","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}

{"title":"Patient-Specific Automatic Seizure Detection Method from EEG Signals Based on Random Forest","authors":"Qi Sun, Yuanjian Liu, Shuangde Li","doi":"10.1109/CISP-BMEI53629.2021.9624400","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624400","url":null,"abstract":"Epilepsy is an abnormal discharge in focal or whole part of brain, lasting a few seconds or minutes. The detection of epileptic seizure by the way of visual inspection is time-consuming, so the study for automatic seizure detection methods toward long-term electroencephalogram (EEG) recording is valuable. Due to the nonstationary characteristics of EEG signal, traditional analysis methods cannot achieve epilepsy diagnosis successfully. In this paper, we presented a method, namely, the patient-specific automatic seizure detection method, to identify epilepsy in EEG signals. First, a method based on time-domain and nonlinear characteristics is used to analyze the selected EEG segment and obtain the features of each segment. Then, these features are applied as the input of random forest to get classification result, concerning the existence of seizures or not. The accuracy of proposed method is 92.05%. Therefore, the proposed method is validated by using available dataset of online.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116776151","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}