Pub Date : 2019-09-10DOI: 10.1080/24699322.2019.1649075
R. Chou, Jung-Hui Li, Liu-Kuo Ying, Cheng-Hsun Lin, Wan Leung
Abstract A metal implant was placed in an acrylic phantom to enable quantitative analysis of the metal artifact reduction techniques used in computed tomography (CT) scanners from three manufacturers. Two titanium rods were placed in a groove in a cylindrical phantom made by acrylic, after which the groove was filled with water. The phantom was scanned using three CT scanners (Toshiba, GE, Siemens) under the abdomen CT setting. CT number accuracy, contrast-to-noise ratio, area of the metal rods in the images, and fraction of affected pixel area of water were measured using ImageJ. Different iterative reconstruction, dual energy, and metal artifact reduction techniques were compared within three vendors. The highest contrast-to-noise ratio of three scanners were 85.7 ± 8.4 (Toshiba), 85.9 ± 11.7 (GE), and 55.0 ± 14.8 (Siemens); and the most correct results of metal area were 157.1 ± 1.4 mm2 (Toshiba), 155.0 ± 1.0 (GE), and 170.6 ± 5.3 (Siemens). The fraction of affected pixel area obtained using single-energy metal artifact reduction of Toshiba scanner was 2.2% ± 0.7%, which is more favorable than 4.1% ± 0.7% obtained using metal artifact reduction software of GE scanner (p = 0.002). Among all quantitative results, the estimations with fraction of affected pixel areas matched the effect of metal artifact reduction in the actual images. Therefore, the single-energy metal artifact reduction technique of Toshiba scanner had a desirable effect. The metal artifact reduction software of GE scanner effectively reduced the effect of metal artifacts; however, it underestimated the size of the metal rods. The monoenergetic and dual energy composition techniques of Siemens scanner could not effectively reduce metal artifacts.
{"title":"Quantitative assessment of three vendor’s metal artifact reduction techniques for CT imaging using a customized phantom","authors":"R. Chou, Jung-Hui Li, Liu-Kuo Ying, Cheng-Hsun Lin, Wan Leung","doi":"10.1080/24699322.2019.1649075","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649075","url":null,"abstract":"Abstract A metal implant was placed in an acrylic phantom to enable quantitative analysis of the metal artifact reduction techniques used in computed tomography (CT) scanners from three manufacturers. Two titanium rods were placed in a groove in a cylindrical phantom made by acrylic, after which the groove was filled with water. The phantom was scanned using three CT scanners (Toshiba, GE, Siemens) under the abdomen CT setting. CT number accuracy, contrast-to-noise ratio, area of the metal rods in the images, and fraction of affected pixel area of water were measured using ImageJ. Different iterative reconstruction, dual energy, and metal artifact reduction techniques were compared within three vendors. The highest contrast-to-noise ratio of three scanners were 85.7 ± 8.4 (Toshiba), 85.9 ± 11.7 (GE), and 55.0 ± 14.8 (Siemens); and the most correct results of metal area were 157.1 ± 1.4 mm2 (Toshiba), 155.0 ± 1.0 (GE), and 170.6 ± 5.3 (Siemens). The fraction of affected pixel area obtained using single-energy metal artifact reduction of Toshiba scanner was 2.2% ± 0.7%, which is more favorable than 4.1% ± 0.7% obtained using metal artifact reduction software of GE scanner (p = 0.002). Among all quantitative results, the estimations with fraction of affected pixel areas matched the effect of metal artifact reduction in the actual images. Therefore, the single-energy metal artifact reduction technique of Toshiba scanner had a desirable effect. The metal artifact reduction software of GE scanner effectively reduced the effect of metal artifacts; however, it underestimated the size of the metal rods. The monoenergetic and dual energy composition techniques of Siemens scanner could not effectively reduce metal artifacts.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649075","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41771440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-29DOI: 10.1080/24699322.2019.1649073
Rui Zhu, M. Maréchal, I. Yamamoto, M. Lawn, T. Nagayasu, Keitaro Matsumoto
Abstract In this study, the authors used the Fujifilm Prescale Pressure Measuring System to measure the contact pressure and distribution at the jaws of laparoscopic grasping forceps. This data was then correlated with measured pressures at the forceps handles to understand the relationship between the surgeon’s actuating pressure and that on the organ being manipulated. The purpose of this study is to create a database of tactile information to provide guidelines in defining minimally invasive surgery (MIS). This is expected to be important as today's society continues to progress in the use of automation, IoT, AI and MIS. In order to achieve the above, the authors developed an experimental device consisting of an actuator, a load cell and an MCU to stably actuate and control the handle side of grasping forceps. Target organs were simulated using triangular prisms of various silicone rubber materials. The experimental method involved actuating the handle side with preset pressure values for fixed time periods and using sensitive film to measure the pressure at the forceps tip. The film data was then scanned, processed and analyzed.
{"title":"Evaluation of laparoscopic forceps jaw contact pressure and distribution using pressure sensitive film","authors":"Rui Zhu, M. Maréchal, I. Yamamoto, M. Lawn, T. Nagayasu, Keitaro Matsumoto","doi":"10.1080/24699322.2019.1649073","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649073","url":null,"abstract":"Abstract In this study, the authors used the Fujifilm Prescale Pressure Measuring System to measure the contact pressure and distribution at the jaws of laparoscopic grasping forceps. This data was then correlated with measured pressures at the forceps handles to understand the relationship between the surgeon’s actuating pressure and that on the organ being manipulated. The purpose of this study is to create a database of tactile information to provide guidelines in defining minimally invasive surgery (MIS). This is expected to be important as today's society continues to progress in the use of automation, IoT, AI and MIS. In order to achieve the above, the authors developed an experimental device consisting of an actuator, a load cell and an MCU to stably actuate and control the handle side of grasping forceps. Target organs were simulated using triangular prisms of various silicone rubber materials. The experimental method involved actuating the handle side with preset pressure values for fixed time periods and using sensitive film to measure the pressure at the forceps tip. The film data was then scanned, processed and analyzed.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649073","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42603454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-26DOI: 10.1080/24699322.2019.1649067
Baoliang Zhao, Y. Fu, Yuanyuan Yang, Peng Zhang, Ying Hu
Abstract Percutaneous needle puncture operation is widely used in the image-guided interventions, including biopsy and ablation. MRI guidance has the advantages of high-resolution soft tissue imaging and thermal monitoring during energy-based ablation. This paper proposes the design of a 5-DOF pneumatic needle puncture robot, with all the cylinders, sensors and structure material MRI-compatible. Also, a hybrid fuzzy-PID controller is designed for the pneumatic driven system to adjust the PID parameters adaptively. The experiment validation result shows that, compared with the traditional fix-parameter PID control, the proposed hybrid fuzzy-PID control has no overshoot, and the settle time/steady state error remains low even with increasing load. This proves that the hybrid fuzzy-PID control strategy can increases the positioning accuracy and robustness of the pneumatic driven needle puncture robot, which is significant for the safety of percutaneous needle puncture operation.
{"title":"Design and control of a MRI-compatible pneumatic needle puncture robot","authors":"Baoliang Zhao, Y. Fu, Yuanyuan Yang, Peng Zhang, Ying Hu","doi":"10.1080/24699322.2019.1649067","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649067","url":null,"abstract":"Abstract Percutaneous needle puncture operation is widely used in the image-guided interventions, including biopsy and ablation. MRI guidance has the advantages of high-resolution soft tissue imaging and thermal monitoring during energy-based ablation. This paper proposes the design of a 5-DOF pneumatic needle puncture robot, with all the cylinders, sensors and structure material MRI-compatible. Also, a hybrid fuzzy-PID controller is designed for the pneumatic driven system to adjust the PID parameters adaptively. The experiment validation result shows that, compared with the traditional fix-parameter PID control, the proposed hybrid fuzzy-PID control has no overshoot, and the settle time/steady state error remains low even with increasing load. This proves that the hybrid fuzzy-PID control strategy can increases the positioning accuracy and robustness of the pneumatic driven needle puncture robot, which is significant for the safety of percutaneous needle puncture operation.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45278140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-19DOI: 10.1080/24699322.2019.1649069
Lei Geng, Jia Wang, Zhitao Xiao, Jun Tong, Fang Zhang, Jun Wu
Abstract Automatic segmentation of prostate magnetic resonance (MR) images has great significance for the diagnosis and clinical application of prostate diseases. It faces enormous challenges because of the low contrast of the tissue boundary and the small effective area of the prostate MR images. In order to solve these problems, we propose a novel end-to-end professional network which consists of an Encoder-Decoder structure with dense dilated spatial pyramid pooling (DDSPP) for prostate segmentation based on deep learning. First, the DDSPP module is used to extract the multi-scale convolution features in the prostate MR images, and then the decoder is used to capture the clear boundary of prostate. Competitive results are produced over state of the art on 130 MR images which key metrics Dice similarity coefficient (DSC) and Hausdorff distance (HD) are 0.954 and 1.752 mm respectively. Experimental results show that our method has high accuracy and robustness.
{"title":"Encoder-decoder with dense dilated spatial pyramid pooling for prostate MR images segmentation","authors":"Lei Geng, Jia Wang, Zhitao Xiao, Jun Tong, Fang Zhang, Jun Wu","doi":"10.1080/24699322.2019.1649069","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649069","url":null,"abstract":"Abstract Automatic segmentation of prostate magnetic resonance (MR) images has great significance for the diagnosis and clinical application of prostate diseases. It faces enormous challenges because of the low contrast of the tissue boundary and the small effective area of the prostate MR images. In order to solve these problems, we propose a novel end-to-end professional network which consists of an Encoder-Decoder structure with dense dilated spatial pyramid pooling (DDSPP) for prostate segmentation based on deep learning. First, the DDSPP module is used to extract the multi-scale convolution features in the prostate MR images, and then the decoder is used to capture the clear boundary of prostate. Competitive results are produced over state of the art on 130 MR images which key metrics Dice similarity coefficient (DSC) and Hausdorff distance (HD) are 0.954 and 1.752 mm respectively. Experimental results show that our method has high accuracy and robustness.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41987857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-14DOI: 10.1080/24699322.2019.1649070
Seung-Hyeok Shin, Won-Sok Yoo, Hojong Choi
Abstract Purpose: Encryption of patient information has become an important issue in medical ultrasound instrumentation to secure information when images are accessed off-site. The proposed algorithm is used to encrypt private medical images and transfer the encrypted images to improve the encryption capability and elapsed time. Materials and methods: We generate a public key using three prime numbers, including a fixed Mersenne prime number, in the modified Rivest-Shamir-Adelman (RSA) algorithm to compare the encryption capability. We calculated and compared the elapsed time using the modified RSA algorithm with a breast phantom in the medical ultrasound imaging instrumentation. Results: The encryption capability is improved because the elapsed time when using three prime numbers is longer (1.2337 s) than that when using two prime numbers (1.0712 s). However, the elapsed time using fixed Mersenne prime numbers (0.8360 s) is a similar to that using two prime numbers (0.8389 s). Conclusions: Our proposed cryptographic algorithm provides improved encryption in medical ultrasound imaging compared to algorithms that use two prime numbers that are not Mersenne prime numbers, while transmitting images with adequate elapsed times.
{"title":"Development of modified RSA algorithm using fixed mersenne prime numbers for medical ultrasound imaging instrumentation","authors":"Seung-Hyeok Shin, Won-Sok Yoo, Hojong Choi","doi":"10.1080/24699322.2019.1649070","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649070","url":null,"abstract":"Abstract Purpose: Encryption of patient information has become an important issue in medical ultrasound instrumentation to secure information when images are accessed off-site. The proposed algorithm is used to encrypt private medical images and transfer the encrypted images to improve the encryption capability and elapsed time. Materials and methods: We generate a public key using three prime numbers, including a fixed Mersenne prime number, in the modified Rivest-Shamir-Adelman (RSA) algorithm to compare the encryption capability. We calculated and compared the elapsed time using the modified RSA algorithm with a breast phantom in the medical ultrasound imaging instrumentation. Results: The encryption capability is improved because the elapsed time when using three prime numbers is longer (1.2337 s) than that when using two prime numbers (1.0712 s). However, the elapsed time using fixed Mersenne prime numbers (0.8360 s) is a similar to that using two prime numbers (0.8389 s). Conclusions: Our proposed cryptographic algorithm provides improved encryption in medical ultrasound imaging compared to algorithms that use two prime numbers that are not Mersenne prime numbers, while transmitting images with adequate elapsed times.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649070","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44194308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Assisted therapy is increasingly used in autism spectrum disorders (ASD) for improving social interaction and communication skills in recent years. A lot of studies have proven that the form of interactive games for therapy has a good effect on children with autism. Thus, our study provided an assisted therapeutic system based on Reinforcement Learning (RL) for children with ASD, which has five interactive subgames. As is well known, it is necessary to establish and maintain compelling interactions in therapeutic process. Therefore, we aim to adjust the interactive content according to the emotions of children with autism. However, due to the atypical and unusually differences in children with autism, most systems are based on off-line training of small samples of individuals and online recognition, so the existing assisted systems are limited in their ability to automatically update system parameters of new mappings. The integration of RL and Convolutional Neural Network (CNN)-Support Vector Regression (SVR) was used to deal with the updating online of prediction model’s weights. The normalized emotion labels were evaluated by the therapists. Eleven children with autism as subjects were invited in this experiment and captured facial video images. The experiment lasted for five weeks of intermittent assisted therapy, and the results were evaluated for the system and the therapy effect. Finally, we achieved a general reduction in the root mean square error of the model prediction results and labels. Although there is no significant difference in Social Responsiveness Scale (SRS) scores before and after assisted therapy (p value = 0.60), in individual subjects (Sub. 1, Sub. 2 and Sub.3), the SRS total score is significantly reduced (Average drop of 19 points). These results demonstrate the effectiveness of prediction model based on RL and show the feasibility of assisted therapeutic system in children with autism.
{"title":"Assisted therapeutic system based on reinforcement learning for children with autism","authors":"Minjia Li, Xue Li, Lun Xie, Jing Liu, Feifei Wang, Zhiliang Wang","doi":"10.1080/24699322.2019.1649072","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649072","url":null,"abstract":"Abstract Assisted therapy is increasingly used in autism spectrum disorders (ASD) for improving social interaction and communication skills in recent years. A lot of studies have proven that the form of interactive games for therapy has a good effect on children with autism. Thus, our study provided an assisted therapeutic system based on Reinforcement Learning (RL) for children with ASD, which has five interactive subgames. As is well known, it is necessary to establish and maintain compelling interactions in therapeutic process. Therefore, we aim to adjust the interactive content according to the emotions of children with autism. However, due to the atypical and unusually differences in children with autism, most systems are based on off-line training of small samples of individuals and online recognition, so the existing assisted systems are limited in their ability to automatically update system parameters of new mappings. The integration of RL and Convolutional Neural Network (CNN)-Support Vector Regression (SVR) was used to deal with the updating online of prediction model’s weights. The normalized emotion labels were evaluated by the therapists. Eleven children with autism as subjects were invited in this experiment and captured facial video images. The experiment lasted for five weeks of intermittent assisted therapy, and the results were evaluated for the system and the therapy effect. Finally, we achieved a general reduction in the root mean square error of the model prediction results and labels. Although there is no significant difference in Social Responsiveness Scale (SRS) scores before and after assisted therapy (p value = 0.60), in individual subjects (Sub. 1, Sub. 2 and Sub.3), the SRS total score is significantly reduced (Average drop of 19 points). These results demonstrate the effectiveness of prediction model based on RL and show the feasibility of assisted therapeutic system in children with autism.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649072","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46515683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-12DOI: 10.1080/24699322.2019.1649071
Lei Geng, Siqi Zhang, Jun Tong, Zhitao Xiao
Abstract Lung cancer has become one of the life-threatening killers. Lung disease need to be assisted by CT images taken doctor's diagnosis, and the segmented CT image of the lung parenchyma is the first step to help doctor diagnosis. For the problem of accurately segmenting the lung parenchyma, this paper proposes a segmentation method based on the combination of VGG-16 and dilated convolution. First of all, we use the first three parts of VGG-16 network structure to convolution and pooling the input image. Secondly, using multiple sets of dilated convolutions make the network has a large enough receptive field. Finally, the multi-scale convolution features are fused, and each pixel is predicted using MLP to segment the parenchymal region. Experimental results were produced over state of the art on 137 images which key metrics Dice similarity coefficient (DSC) is 0.9867. Experimental results show that this method can effectively segment the lung parenchymal area, and compared to other conventional methods better.
{"title":"Lung segmentation method with dilated convolution based on VGG-16 network","authors":"Lei Geng, Siqi Zhang, Jun Tong, Zhitao Xiao","doi":"10.1080/24699322.2019.1649071","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649071","url":null,"abstract":"Abstract Lung cancer has become one of the life-threatening killers. Lung disease need to be assisted by CT images taken doctor's diagnosis, and the segmented CT image of the lung parenchyma is the first step to help doctor diagnosis. For the problem of accurately segmenting the lung parenchyma, this paper proposes a segmentation method based on the combination of VGG-16 and dilated convolution. First of all, we use the first three parts of VGG-16 network structure to convolution and pooling the input image. Secondly, using multiple sets of dilated convolutions make the network has a large enough receptive field. Finally, the multi-scale convolution features are fused, and each pixel is predicted using MLP to segment the parenchymal region. Experimental results were produced over state of the art on 137 images which key metrics Dice similarity coefficient (DSC) is 0.9867. Experimental results show that this method can effectively segment the lung parenchymal area, and compared to other conventional methods better.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649071","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43876257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-12DOI: 10.1080/24699322.2019.1649074
Jue Zhang, Li Chen
Abstract To overcome the two-class imbalanced classification problem existing in the diagnosis of breast cancer, a hybrid of Random Over Sampling Example, K-means and Support vector machine (RK-SVM) model is proposed which is based on sample selection. Random Over Sampling Example (ROSE) is utilized to balance the dataset and further improve the diagnosis accuracy by Support Vector Machine (SVM). As there is one different sample selection factor via clustering that encourages selecting the samples near the class boundary. The purpose of clustering here is to reduce the risk of removing useful samples and improve the efficiency of sample selection. To test the performance of the new hybrid classifier, it is implemented on breast cancer datasets and the other three datasets from the University of California Irvine (UCI) machine learning repository, which are commonly used datasets in class imbalanced learning. The extensive experimental results show that our proposed hybrid method outperforms most of the competitive algorithms in term of G-mean and accuracy indices. Additionally, experimental results show that this method also performs superiorly for binary problems.
{"title":"Clustering-based undersampling with random over sampling examples and support vector machine for imbalanced classification of breast cancer diagnosis","authors":"Jue Zhang, Li Chen","doi":"10.1080/24699322.2019.1649074","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649074","url":null,"abstract":"Abstract To overcome the two-class imbalanced classification problem existing in the diagnosis of breast cancer, a hybrid of Random Over Sampling Example, K-means and Support vector machine (RK-SVM) model is proposed which is based on sample selection. Random Over Sampling Example (ROSE) is utilized to balance the dataset and further improve the diagnosis accuracy by Support Vector Machine (SVM). As there is one different sample selection factor via clustering that encourages selecting the samples near the class boundary. The purpose of clustering here is to reduce the risk of removing useful samples and improve the efficiency of sample selection. To test the performance of the new hybrid classifier, it is implemented on breast cancer datasets and the other three datasets from the University of California Irvine (UCI) machine learning repository, which are commonly used datasets in class imbalanced learning. The extensive experimental results show that our proposed hybrid method outperforms most of the competitive algorithms in term of G-mean and accuracy indices. Additionally, experimental results show that this method also performs superiorly for binary problems.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649074","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42793989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-10DOI: 10.1080/24699322.2019.1649078
Dong-Wei Chen, Wei-Qi Yang, Rui Miao, Lan Huang, Liu Zhang, Chunjian Deng, Na Han
Abstract At present, in the field of electroencephalogram (EEG) signal recognition, the classification and recognition in complex scenarios with more categories of EEG signals have gained more attention. Based on the joint fast Fourier transform (FFT) and support vector machine (SVM) methods, this study proposed a novel EEG signal-processing joint method for the complex scenarios with 10 classifications of EEG signals. Moreover, a comprehensive efficiency formula was put forward. The formula considered the accuracy and time consumption of the joint method. This new joint method could improve the accuracy and comprehensive efficiency of multiclass EEG signal recognition. The new joint approach used standardization for data preprocessing. Feature extraction was performed by combining FFT and principal component analysis methods. EEG signals were classified using the weighted k-nearest nenighbour method. In this study, experiments were conducted using public datasets of brainwave 0-9 digits classification. The result demonstrated that the accuracy and comprehensive efficiency of the novel joint method were 84% and 87%, respectively, which were better than those of the existing methods. The precision rate, recall rate, and F1 score of the novel joint method were 89%, 85%, and 0.85, respectively. In conclusion, the proposed joint method was effective in a complex scenario for multiclass EEG signal recognition.
{"title":"Novel joint algorithm based on EEG in complex scenarios","authors":"Dong-Wei Chen, Wei-Qi Yang, Rui Miao, Lan Huang, Liu Zhang, Chunjian Deng, Na Han","doi":"10.1080/24699322.2019.1649078","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649078","url":null,"abstract":"Abstract At present, in the field of electroencephalogram (EEG) signal recognition, the classification and recognition in complex scenarios with more categories of EEG signals have gained more attention. Based on the joint fast Fourier transform (FFT) and support vector machine (SVM) methods, this study proposed a novel EEG signal-processing joint method for the complex scenarios with 10 classifications of EEG signals. Moreover, a comprehensive efficiency formula was put forward. The formula considered the accuracy and time consumption of the joint method. This new joint method could improve the accuracy and comprehensive efficiency of multiclass EEG signal recognition. The new joint approach used standardization for data preprocessing. Feature extraction was performed by combining FFT and principal component analysis methods. EEG signals were classified using the weighted k-nearest nenighbour method. In this study, experiments were conducted using public datasets of brainwave 0-9 digits classification. The result demonstrated that the accuracy and comprehensive efficiency of the novel joint method were 84% and 87%, respectively, which were better than those of the existing methods. The precision rate, recall rate, and F1 score of the novel joint method were 89%, 85%, and 0.85, respectively. In conclusion, the proposed joint method was effective in a complex scenario for multiclass EEG signal recognition.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47383231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-10DOI: 10.1080/24699322.2019.1649077
Chi Zhang, Mingxia Sun, Yinan Wei, Hao Zhang, S. Xie, Tongxi Liu
Abstract Pulmonary embolism (PE) and other pulmonary vascular diseases, have been found associated with the changes in arterial morphology. To detect arterial changes, we propose a novel, fully automatic method that can extract pulmonary arterial tree in computed tomographic pulmonary angiography (CTPA) images. The approach is based on the fuzzy connectedness framework, combined with 3D vessel enhancement and Harris Corner detection to achieve accurate segmentation. The effectiveness and robustness of the method is validated in clinical datasets consisting of 10 CT angiography scans (6 without PE and 4 with PE). The performance of our method is compared with manual classification and machine learning method based on random forest. Our method achieves a mean accuracy of 92% when compared to manual reference, which is higher than the 89% accuracy achieved by machine learning. This performance of the segmentation for pulmonary arteries may provide a basis for the CAD application of PE.
{"title":"Automatic segmentation of arterial tree from 3D computed tomographic pulmonary angiography (CTPA) scans","authors":"Chi Zhang, Mingxia Sun, Yinan Wei, Hao Zhang, S. Xie, Tongxi Liu","doi":"10.1080/24699322.2019.1649077","DOIUrl":"https://doi.org/10.1080/24699322.2019.1649077","url":null,"abstract":"Abstract Pulmonary embolism (PE) and other pulmonary vascular diseases, have been found associated with the changes in arterial morphology. To detect arterial changes, we propose a novel, fully automatic method that can extract pulmonary arterial tree in computed tomographic pulmonary angiography (CTPA) images. The approach is based on the fuzzy connectedness framework, combined with 3D vessel enhancement and Harris Corner detection to achieve accurate segmentation. The effectiveness and robustness of the method is validated in clinical datasets consisting of 10 CT angiography scans (6 without PE and 4 with PE). The performance of our method is compared with manual classification and machine learning method based on random forest. Our method achieves a mean accuracy of 92% when compared to manual reference, which is higher than the 89% accuracy achieved by machine learning. This performance of the segmentation for pulmonary arteries may provide a basis for the CAD application of PE.","PeriodicalId":56051,"journal":{"name":"Computer Assisted Surgery","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2019-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/24699322.2019.1649077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45698765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","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：