{"title":"改进的自适应概率神经网络用于MR图像分割","authors":"Yuanfeng Lian, Yan Zhao, Falin Wu, Huiguang He","doi":"10.1109/YCICT.2010.5713118","DOIUrl":null,"url":null,"abstract":"This paper presents a new approach based on modified adaptive probabilistic neural network for brain segmentation with magnetic resonance imaging (MRI). The SOM (Self-Organizing Map) neural network is employed to overly segment the input MR image, and yield reference vectors with a large training data set for the probabilistic classification. For improving the training quality of neural work, the feature set is extracted from the statistical intensity and gradient information of the image pixels. The proposed approach also incorporates modified particle swarm optimization (MPSO) to optimize the smoothing parameter of the kernel function in the neural network, enhancing its performance. The experimental results demonstrate the effectiveness and robustness of the proposed approach.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Modified adaptive probabilistic neural network using for MR image segmentation\",\"authors\":\"Yuanfeng Lian, Yan Zhao, Falin Wu, Huiguang He\",\"doi\":\"10.1109/YCICT.2010.5713118\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a new approach based on modified adaptive probabilistic neural network for brain segmentation with magnetic resonance imaging (MRI). The SOM (Self-Organizing Map) neural network is employed to overly segment the input MR image, and yield reference vectors with a large training data set for the probabilistic classification. For improving the training quality of neural work, the feature set is extracted from the statistical intensity and gradient information of the image pixels. The proposed approach also incorporates modified particle swarm optimization (MPSO) to optimize the smoothing parameter of the kernel function in the neural network, enhancing its performance. The experimental results demonstrate the effectiveness and robustness of the proposed approach.\",\"PeriodicalId\":179847,\"journal\":{\"name\":\"2010 IEEE Youth Conference on Information, Computing and Telecommunications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 IEEE Youth Conference on Information, Computing and Telecommunications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/YCICT.2010.5713118\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/YCICT.2010.5713118","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Modified adaptive probabilistic neural network using for MR image segmentation
This paper presents a new approach based on modified adaptive probabilistic neural network for brain segmentation with magnetic resonance imaging (MRI). The SOM (Self-Organizing Map) neural network is employed to overly segment the input MR image, and yield reference vectors with a large training data set for the probabilistic classification. For improving the training quality of neural work, the feature set is extracted from the statistical intensity and gradient information of the image pixels. The proposed approach also incorporates modified particle swarm optimization (MPSO) to optimize the smoothing parameter of the kernel function in the neural network, enhancing its performance. The experimental results demonstrate the effectiveness and robustness of the proposed approach.