Abdominal anatomical structure database is a necessary precondition for medical image computer-aided diagnosis. In this paper, a Web database system based on the CT abdomen anatomy images is established. The system consists of abdominal viscera segmentation and anatomical structure database. Firstly, we need to segment the spleen and liver in abdominal CT images. For spleen segmentation, an improved Otsu-based algorithm is put forward; for liver segmentation, an improved algorithm combined probability graph and traditional graph cut segmentation algorithm is used. Secondly, a Web oriented abdominal viscera anatomical structure database system using SSI framework is constructed, storing and managing image information of segmented organs. Lastly, through the experimental measurement for abdominal CT image segmentation and database system, the experimental results show that the proposed segmentation algorithm and the liver spleen segmentation algorithm can get more accurate segmentation results. The database system can provide remote management, making it available for medical researchers use the computer remotely access to the Internet to obtain the required data anywhere.
{"title":"A Web abdominal anatomical structure database system","authors":"Jiafeng Li, Baochun He, Huiyan Jiang, Benqiang Yang, Libo Zhang, Qiang Tong, Aoshuang Dong","doi":"10.1109/ICMIPE.2013.6864495","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864495","url":null,"abstract":"Abdominal anatomical structure database is a necessary precondition for medical image computer-aided diagnosis. In this paper, a Web database system based on the CT abdomen anatomy images is established. The system consists of abdominal viscera segmentation and anatomical structure database. Firstly, we need to segment the spleen and liver in abdominal CT images. For spleen segmentation, an improved Otsu-based algorithm is put forward; for liver segmentation, an improved algorithm combined probability graph and traditional graph cut segmentation algorithm is used. Secondly, a Web oriented abdominal viscera anatomical structure database system using SSI framework is constructed, storing and managing image information of segmented organs. Lastly, through the experimental measurement for abdominal CT image segmentation and database system, the experimental results show that the proposed segmentation algorithm and the liver spleen segmentation algorithm can get more accurate segmentation results. The database system can provide remote management, making it available for medical researchers use the computer remotely access to the Internet to obtain the required data anywhere.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132452211","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 : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864513
Y. Xiang, Jianfeng He, Dangguo Shao, Lei Ma
Magnetic resonance (MR) images can be used to detect lesions in the brains of multiple sclerosis (MS) patients and is essential for diagnosing the disease and monitoring its progression. An automatic method is presented for segmentation of MS lesions in multispectral MR images. Firstly a PD-w image is subtracted from its corresponding T1-w image to get an image in which the cerebral spinal fluid (CSF) is enhanced. Then based on kernel fuzzy c-means (KFCM) algorithm, the enhanced image and the corresponding T2-w image are segmented respectively to extract the CSF region and the CSF combining MS lesions region. A raw MS lesions image is obtained by subtracting the CSF region from CSF combining MS region. By applying median filter and thresholding to the raw image, the MS lesions are detected finally. Results are quantitatively evaluated on BrainWeb images using Dice similarity coefficient (DSC). Finally, the potential of the method as well as its limitations are discussed.
{"title":"Automatic segmentation of multiple sclerosis lesions in multispectral MR images using kernel fuzzy c-means clustering","authors":"Y. Xiang, Jianfeng He, Dangguo Shao, Lei Ma","doi":"10.1109/ICMIPE.2013.6864513","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864513","url":null,"abstract":"Magnetic resonance (MR) images can be used to detect lesions in the brains of multiple sclerosis (MS) patients and is essential for diagnosing the disease and monitoring its progression. An automatic method is presented for segmentation of MS lesions in multispectral MR images. Firstly a PD-w image is subtracted from its corresponding T1-w image to get an image in which the cerebral spinal fluid (CSF) is enhanced. Then based on kernel fuzzy c-means (KFCM) algorithm, the enhanced image and the corresponding T2-w image are segmented respectively to extract the CSF region and the CSF combining MS lesions region. A raw MS lesions image is obtained by subtracting the CSF region from CSF combining MS region. By applying median filter and thresholding to the raw image, the MS lesions are detected finally. Results are quantitatively evaluated on BrainWeb images using Dice similarity coefficient (DSC). Finally, the potential of the method as well as its limitations are discussed.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127270046","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 : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864519
Li Lin, X. Meng, X. Liang
A block-based adaptive median filter, which aims to purify impulse noise from an MRI image, is discussed in the paper. The proposed filter blocks the image into several sub-images, and calculates the standard deviation of each sub-image. During filtering process, each point of the sub-image needs to be judged whether it is noise point or not, according to the average value of the filtering window and the standard deviation of the sub-image. Thereafter, the filtering process is the same with traditional adaptive median filter. Experimental results indicate that the proposed filter can maintain the original image details nicely while reducing impulse noise effectively.
{"title":"Reduction of impulse noise in MRI images using block-based adaptive median filter","authors":"Li Lin, X. Meng, X. Liang","doi":"10.1109/ICMIPE.2013.6864519","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864519","url":null,"abstract":"A block-based adaptive median filter, which aims to purify impulse noise from an MRI image, is discussed in the paper. The proposed filter blocks the image into several sub-images, and calculates the standard deviation of each sub-image. During filtering process, each point of the sub-image needs to be judged whether it is noise point or not, according to the average value of the filtering window and the standard deviation of the sub-image. Thereafter, the filtering process is the same with traditional adaptive median filter. Experimental results indicate that the proposed filter can maintain the original image details nicely while reducing impulse noise effectively.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125401680","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 : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864568
Yanchun Zhu, Song Gao, Liuquan Cheng, S. Bao
Many of the recent technological developments in MRI had been focused on improving imaging speed, resolution, and signal-to-noise (SNR). These parameters were often pre-estimate by sampling trajectory in k-space. A large number of patterns of k-space trajectories had been put forward to illustrate the acquisition strategy, including Cartesian raster, radial, zigzag, spiral, stochastic, rosette, TWIRL and WHIRL trajectories. This article reviewed the literatures to provide different k-space trajectories and discuss the characteristic of each trajectory. Only 2D k-space trajectories was described in this article, undersampling trajectories for parallel imaging, 3D and hybrid 3D that combined two or more types of trajectories were out of range of this paper.
{"title":"Review: K-space trajectory development","authors":"Yanchun Zhu, Song Gao, Liuquan Cheng, S. Bao","doi":"10.1109/ICMIPE.2013.6864568","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864568","url":null,"abstract":"Many of the recent technological developments in MRI had been focused on improving imaging speed, resolution, and signal-to-noise (SNR). These parameters were often pre-estimate by sampling trajectory in k-space. A large number of patterns of k-space trajectories had been put forward to illustrate the acquisition strategy, including Cartesian raster, radial, zigzag, spiral, stochastic, rosette, TWIRL and WHIRL trajectories. This article reviewed the literatures to provide different k-space trajectories and discuss the characteristic of each trajectory. Only 2D k-space trajectories was described in this article, undersampling trajectories for parallel imaging, 3D and hybrid 3D that combined two or more types of trajectories were out of range of this paper.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116928163","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 : 1900-01-01DOI: 10.1109/ICMIPE.2013.6864517
Xinqiang Yan, Lei Shi, Y. Zhuo, Xiaohong Joe Zhou, Long Wei, R. Xue
Transmit/receive MTL (Microstrip Transmission Line) array has been widely used for ultra-high-field MRI because of its low mutual coupling characteristics. However, several design issues such as limit to the length of a single coil element still remains. For traditional MTL coils, two capacitors (one fixed, one variable) were put at both ends of the coil element for tuning. Based on our experimental observations, the length of the traditional MTL element is limited at 7T MRI because of increased non-uniform distribution of B1 field along the Z direction. In this study, an optimized MTL array with six capacitors equally distributed along the strip line was investigated. The optimized MTL array can generate a more uniform B1 field along the Z direction compared with the traditional MTL array. The numerical investigation was performed using the RF circuit and 3-D EM co-simulation.
{"title":"Optimized MTL array with serial capacitors for 7T MRI","authors":"Xinqiang Yan, Lei Shi, Y. Zhuo, Xiaohong Joe Zhou, Long Wei, R. Xue","doi":"10.1109/ICMIPE.2013.6864517","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864517","url":null,"abstract":"Transmit/receive MTL (Microstrip Transmission Line) array has been widely used for ultra-high-field MRI because of its low mutual coupling characteristics. However, several design issues such as limit to the length of a single coil element still remains. For traditional MTL coils, two capacitors (one fixed, one variable) were put at both ends of the coil element for tuning. Based on our experimental observations, the length of the traditional MTL element is limited at 7T MRI because of increased non-uniform distribution of B1 field along the Z direction. In this study, an optimized MTL array with six capacitors equally distributed along the strip line was investigated. The optimized MTL array can generate a more uniform B1 field along the Z direction compared with the traditional MTL array. The numerical investigation was performed using the RF circuit and 3-D EM co-simulation.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"303 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123233434","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：