Pub Date : 2018-11-01DOI: 10.1109/ICDSP.2018.8631830
Shihao Xu, Zixu Yang, Debsubhra Chakraborty, Yasir Tahir, Tomasz Maszczyk, Y. H. V. Chua, J. Dauwels, D. Thalmann, N. Magnenat-Thalmann, Bhing-Leet Tan, J. Lee
Schizophrenia is a long-term mental disease associated with language impairments that affect about one percent of the population. Traditional assessment of schizophrenic patients is conducted by trained professionals, which requires tremendous resources of time and effort. This study is part of a larger research objective committed to creating automated platforms to aid clinical diagnosis and understanding of schizophrenia. We have analyzed non-verbal cues and movement signals in our previous work. In this study, we explore the feasibility of using automatic transcriptions of interviews to classify patients and predict the observability of negative symptoms in schizophrenic patients. Interview recordings of 50 schizophrenia patients and 25 age-matched healthy controls were automatically transcribed by a speech recognition toolkit. After which, Natural Language Processing techniques were applied to automatically extract the lexical features and document vectors of transcriptions. Using these features, we applied ensemble machine learning algorithm (by leave-one-out cross-validation) to predict the Negative Symptom Assessment subject ratings of schizophrenic patients, and to classify patients from controls, achieving a maximum accuracy of 78.7%. These results indicate that schizophrenic patients exhibit significant differences in lexical usage compared with healthy controls, and the possibility of using these lexical features in the understanding and diagnosis of schizophrenia.
{"title":"Automatic Verbal Analysis of Interviews with Schizophrenic Patients","authors":"Shihao Xu, Zixu Yang, Debsubhra Chakraborty, Yasir Tahir, Tomasz Maszczyk, Y. H. V. Chua, J. Dauwels, D. Thalmann, N. Magnenat-Thalmann, Bhing-Leet Tan, J. Lee","doi":"10.1109/ICDSP.2018.8631830","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631830","url":null,"abstract":"Schizophrenia is a long-term mental disease associated with language impairments that affect about one percent of the population. Traditional assessment of schizophrenic patients is conducted by trained professionals, which requires tremendous resources of time and effort. This study is part of a larger research objective committed to creating automated platforms to aid clinical diagnosis and understanding of schizophrenia. We have analyzed non-verbal cues and movement signals in our previous work. In this study, we explore the feasibility of using automatic transcriptions of interviews to classify patients and predict the observability of negative symptoms in schizophrenic patients. Interview recordings of 50 schizophrenia patients and 25 age-matched healthy controls were automatically transcribed by a speech recognition toolkit. After which, Natural Language Processing techniques were applied to automatically extract the lexical features and document vectors of transcriptions. Using these features, we applied ensemble machine learning algorithm (by leave-one-out cross-validation) to predict the Negative Symptom Assessment subject ratings of schizophrenic patients, and to classify patients from controls, achieving a maximum accuracy of 78.7%. These results indicate that schizophrenic patients exhibit significant differences in lexical usage compared with healthy controls, and the possibility of using these lexical features in the understanding and diagnosis of schizophrenia.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":" 111","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132188031","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631608
Yang Chen, Tong Ma, Ying Wei
A design of variable filters is proposed based on frequency response masking technique and frequency warping. Instead of using traditional masking filters, the masking filters in the proposed method are obtained by nonlinear transformation to a prototype filter using frequency wrapping. The design process is given and the mapping between the final filters and the control parameters are deduced. Experiments illustrate the effectiveness of the proposed method.
{"title":"A Design of Variable Digital Filters Based on FRM Technique and Frequency Warping","authors":"Yang Chen, Tong Ma, Ying Wei","doi":"10.1109/ICDSP.2018.8631608","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631608","url":null,"abstract":"A design of variable filters is proposed based on frequency response masking technique and frequency warping. Instead of using traditional masking filters, the masking filters in the proposed method are obtained by nonlinear transformation to a prototype filter using frequency wrapping. The design process is given and the mapping between the final filters and the control parameters are deduced. Experiments illustrate the effectiveness of the proposed method.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115244324","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631691
Feng-yan Xu, Linfu Duan, Xiansheng Guo, Lin Li, F. Hu
The existing WiFi and geomagnetism based positioning methods using single classifier show low accuracy because they are sensitive to changing environments. In this paper, we propose a global dynamic fusion location algorithm for multiple classifiers based on WiFi and geomagnetic fingerprints. In the offline phase, we first divide a positioning environment into some grid points and construct RSS and geomagnetic fingerprints for each grid point. Then, we train multiple classifiers by using the constructed fingerprints. Second, we derive a global dynamic fusion weight training method for each grid point through the global supervised optimization learning. In the online phase, given an RSS testing sample, we select the matching weights for fusion by using K-nearest neighbor (KNN). Our proposed multiple classifiers global dynamic fusion algorithm can make full use of the intrinsic complementarity of multiple classifiers, thus effectively improving the positioning accuracy of RSS and geomagnetic fingerprints. Experimental results show that the proposed algorithm outperforms some existing methods in complex indoor environments.
{"title":"Multiple Classifiers Global Dynamic Fusion Location System based on WiFi and Geomagnetism","authors":"Feng-yan Xu, Linfu Duan, Xiansheng Guo, Lin Li, F. Hu","doi":"10.1109/ICDSP.2018.8631691","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631691","url":null,"abstract":"The existing WiFi and geomagnetism based positioning methods using single classifier show low accuracy because they are sensitive to changing environments. In this paper, we propose a global dynamic fusion location algorithm for multiple classifiers based on WiFi and geomagnetic fingerprints. In the offline phase, we first divide a positioning environment into some grid points and construct RSS and geomagnetic fingerprints for each grid point. Then, we train multiple classifiers by using the constructed fingerprints. Second, we derive a global dynamic fusion weight training method for each grid point through the global supervised optimization learning. In the online phase, given an RSS testing sample, we select the matching weights for fusion by using K-nearest neighbor (KNN). Our proposed multiple classifiers global dynamic fusion algorithm can make full use of the intrinsic complementarity of multiple classifiers, thus effectively improving the positioning accuracy of RSS and geomagnetic fingerprints. Experimental results show that the proposed algorithm outperforms some existing methods in complex indoor environments.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115114361","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631672
F. Bai, Ruijie Liu
In this paper, we present an improved nonparallel hyperplanes classifier for multi-class classification, termed as INHCMC. As in the nonparallel support vector machine (NPSVM) for binary classification, the ε-insensitive loss function is adopted in the primal problems of multi-class classification to improve the sparseness associated with the nonparallel hyperplanes classifier for multi-class classification (NHCMC) where the quadratic loss function is used. Experimental results on some benchmark datasets are reported to show the effectiveness of our method in terms of sparseness and classification accuracy.
{"title":"Improved Nonparallel Hyperplanes Support Vector Machines for Multi-class Classification","authors":"F. Bai, Ruijie Liu","doi":"10.1109/ICDSP.2018.8631672","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631672","url":null,"abstract":"In this paper, we present an improved nonparallel hyperplanes classifier for multi-class classification, termed as INHCMC. As in the nonparallel support vector machine (NPSVM) for binary classification, the ε-insensitive loss function is adopted in the primal problems of multi-class classification to improve the sparseness associated with the nonparallel hyperplanes classifier for multi-class classification (NHCMC) where the quadratic loss function is used. Experimental results on some benchmark datasets are reported to show the effectiveness of our method in terms of sparseness and classification accuracy.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122052358","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631808
Xingwei Sun, Ziteng Wang, Risheng Xia, Junfeng Li, Yonghong Yan
The minimum variance distortionless response (MV-DR) beamformer is a widely used beamforming technique that extracts sound components coming from a direction specified by a steering vector. In this paper, we present four different steering vector estimation methods and analyze their influence on the MVDR beamformer in speech recognition. The first one is based on the direction of arrival under the plane wave propagation assumption with the prior knowledge of microphone array geometry. The other three methods are based on the decomposition of the observed speech covariance matrix, including the covariance subtraction based method, the eigenvalue decomposition based method, and the generalized eigenvalue decomposition (GEVD) based method. We theoretically prove that the three decomposition based methods are equivalent under the narrowband approximation or after the rank -1 speech covariance matrix approximation. The speech recognition experiments conducted on the CHiME-3 dataset shows that the MVDR beamformer using GEVD-based steering vector estimation achieves the best performance, and word error rates can be further reduced with the rank -1 approximation.
{"title":"Effect of Steering Vector Estimation on MVDR Beamformer for Noisy Speech Recognition","authors":"Xingwei Sun, Ziteng Wang, Risheng Xia, Junfeng Li, Yonghong Yan","doi":"10.1109/ICDSP.2018.8631808","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631808","url":null,"abstract":"The minimum variance distortionless response (MV-DR) beamformer is a widely used beamforming technique that extracts sound components coming from a direction specified by a steering vector. In this paper, we present four different steering vector estimation methods and analyze their influence on the MVDR beamformer in speech recognition. The first one is based on the direction of arrival under the plane wave propagation assumption with the prior knowledge of microphone array geometry. The other three methods are based on the decomposition of the observed speech covariance matrix, including the covariance subtraction based method, the eigenvalue decomposition based method, and the generalized eigenvalue decomposition (GEVD) based method. We theoretically prove that the three decomposition based methods are equivalent under the narrowband approximation or after the rank -1 speech covariance matrix approximation. The speech recognition experiments conducted on the CHiME-3 dataset shows that the MVDR beamformer using GEVD-based steering vector estimation achieves the best performance, and word error rates can be further reduced with the rank -1 approximation.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121222727","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631803
Zai Yang, Yonina C. Eldar, Lihua Xie
Compressive multichannel frequency estimation refers to the process of retrieving the frequency profile shared by multiple signals from their compressive samples. A recent approach to this problem relies on atomic norm minimization which exploitsjoint sparsity among the channels, is solved using convex optimization, and has strong theoretical guarantees. We provide in this paper an average-case analysis for atomic norm minimization by assuming proper randomness on the amplitudes of the frequencies. We show that the sample size per channel required for exact frequency estimation from noiseless samples decreases as the number of channels increases and is on the order of $Kdisplaystyle log Kleft(1+frac{1}{L}log Nright)$, where K is the number of frequencies, L is the number of channels, and N is a fixed parameter proportional to the sampling window size and inversely proportional to the desired resolution.
{"title":"Average Case Analysis of Compressive Multichannel Frequency Estimation Using Atomic Norm Minimization","authors":"Zai Yang, Yonina C. Eldar, Lihua Xie","doi":"10.1109/ICDSP.2018.8631803","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631803","url":null,"abstract":"Compressive multichannel frequency estimation refers to the process of retrieving the frequency profile shared by multiple signals from their compressive samples. A recent approach to this problem relies on atomic norm minimization which exploitsjoint sparsity among the channels, is solved using convex optimization, and has strong theoretical guarantees. We provide in this paper an average-case analysis for atomic norm minimization by assuming proper randomness on the amplitudes of the frequencies. We show that the sample size per channel required for exact frequency estimation from noiseless samples decreases as the number of channels increases and is on the order of $Kdisplaystyle log Kleft(1+frac{1}{L}log Nright)$, where K is the number of frequencies, L is the number of channels, and N is a fixed parameter proportional to the sampling window size and inversely proportional to the desired resolution.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121344209","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631573
Micael Bernhardt, J. Cousseau
The upcoming wireless communication systems are expected to integrate a number of nodes remarkably greater than those observed in current technologies, while offering a sensibly improved service quality for critical applications. This generates a need for innovative schemes to share the available resources among the served terminals as well as to increase the system efficiency and node fairness. Aiming to this objective, we propose a combination of non-orthogonal multiple access and interference alignment schemes applied to the downlink transmissions in a multi-cell environment. The two methods presented in this work enable an efficient reutilization of resources and the suppression of intra-and inter-cell interference in a single step during signal reception. We derive the expressions for the feasibility of our proposed solution from an analysis applied to generic system configurations. Additionally, we show numerical results that highlight the benefits of this scheme in a system setup resembling an Internet-of-things scenario.
{"title":"On Interference Alignment Based NOMA for Downlink Multicell Transmissions","authors":"Micael Bernhardt, J. Cousseau","doi":"10.1109/ICDSP.2018.8631573","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631573","url":null,"abstract":"The upcoming wireless communication systems are expected to integrate a number of nodes remarkably greater than those observed in current technologies, while offering a sensibly improved service quality for critical applications. This generates a need for innovative schemes to share the available resources among the served terminals as well as to increase the system efficiency and node fairness. Aiming to this objective, we propose a combination of non-orthogonal multiple access and interference alignment schemes applied to the downlink transmissions in a multi-cell environment. The two methods presented in this work enable an efficient reutilization of resources and the suppression of intra-and inter-cell interference in a single step during signal reception. We derive the expressions for the feasibility of our proposed solution from an analysis applied to generic system configurations. Additionally, we show numerical results that highlight the benefits of this scheme in a system setup resembling an Internet-of-things scenario.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124276464","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631839
Chaosheng Tang, Elizabeth Lee
Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. We treated a three-class classification problem: HC, LHL, and RHL, and checked three different orientation images: coronal, axial, and sagittal. Different methods are compared with 10x6-fold cross validation. The results show that our proposed system shows better performance in detecting hearing loss.
{"title":"Hearing loss identification via wavelet entropy and combination of Tabu search and particle swarm optimization","authors":"Chaosheng Tang, Elizabeth Lee","doi":"10.1109/ICDSP.2018.8631839","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631839","url":null,"abstract":"Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. We treated a three-class classification problem: HC, LHL, and RHL, and checked three different orientation images: coronal, axial, and sagittal. Different methods are compared with 10x6-fold cross validation. The results show that our proposed system shows better performance in detecting hearing loss.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114523914","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631848
Kai Kang, Zhou Fang, Haifeng Wang, H. Qian, Yang Yang
Modern communication signals such as orthogonal frequency division multiplexing (OFDM) signals suffers from large peak-to-average power ratio (PAPR), which may sacrifice power efficiency and/or distort the signal in the presence of radio front end nonlinearity. In this paper, we propose a dummy signal precoding method to deal with the inherent PAPR problem in a multiple-input multiple-output OFDM (MIMO-OFDM) system. The idea is to generate a set of random dummy signals and combine them with existing input data. Precoding is applied to eliminate the multiuser interference. The signal with low PAPR is chosen for transmission. Simulation shows that the proposed method can effectively reduce the PAPR of the transmit signal. In addition, no side information needs to be transmitted with the proposed method. Thus the proposed method complies with existing MIMO-OFDM architecture.
{"title":"Dummy Signal Precoding for PAPR Reduction in MIMO Communication System","authors":"Kai Kang, Zhou Fang, Haifeng Wang, H. Qian, Yang Yang","doi":"10.1109/ICDSP.2018.8631848","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631848","url":null,"abstract":"Modern communication signals such as orthogonal frequency division multiplexing (OFDM) signals suffers from large peak-to-average power ratio (PAPR), which may sacrifice power efficiency and/or distort the signal in the presence of radio front end nonlinearity. In this paper, we propose a dummy signal precoding method to deal with the inherent PAPR problem in a multiple-input multiple-output OFDM (MIMO-OFDM) system. The idea is to generate a set of random dummy signals and combine them with existing input data. Precoding is applied to eliminate the multiuser interference. The signal with low PAPR is chosen for transmission. Simulation shows that the proposed method can effectively reduce the PAPR of the transmit signal. In addition, no side information needs to be transmitted with the proposed method. Thus the proposed method complies with existing MIMO-OFDM architecture.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128611534","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631796
Jianguo Sun, Tianxu Sun, Ye Yuan, Xingjian Zhang, Yiqi Shi, Yun Lin
An automatic method applied to the thyroid ultrasound images for lesion localization and diagnosis of benign and malignant lesions was proposed in this paper. The FCN-AlexNet of deep learning method was used to segment images, and accurate localization of thyroid nodules was achieved. Then, the method of transfer learning was introduced to solve the problem of training data shortages during training process. According to the performance of AlexNet in classification, it was used to diagnose benign and malignant lesions. The localization effects of TBD, RGI, PAORGB, and ASPS methods were comparatively evaluated by IoU indicators, and the accuracy of benign and malignant diagnosis of those methods are evaluated by Accuracy, Sensitivity, Specificity, and AUC. The experimental results shown that the proposed method has better performance in localization and diagnosis of benign and malignant lesions.
{"title":"Automatic Diagnosis of Thyroid Ultrasound Image Based on FCN-AlexNet and Transfer Learning","authors":"Jianguo Sun, Tianxu Sun, Ye Yuan, Xingjian Zhang, Yiqi Shi, Yun Lin","doi":"10.1109/ICDSP.2018.8631796","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631796","url":null,"abstract":"An automatic method applied to the thyroid ultrasound images for lesion localization and diagnosis of benign and malignant lesions was proposed in this paper. The FCN-AlexNet of deep learning method was used to segment images, and accurate localization of thyroid nodules was achieved. Then, the method of transfer learning was introduced to solve the problem of training data shortages during training process. According to the performance of AlexNet in classification, it was used to diagnose benign and malignant lesions. The localization effects of TBD, RGI, PAORGB, and ASPS methods were comparatively evaluated by IoU indicators, and the accuracy of benign and malignant diagnosis of those methods are evaluated by Accuracy, Sensitivity, Specificity, and AUC. The experimental results shown that the proposed method has better performance in localization and diagnosis of benign and malignant lesions.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128259879","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：