Shangling Jui, Chao Lin, Haibing Guan, A. Abraham, A. Hassanien, Kai Xiao
{"title":"Fuzzy c-means with wavelet filtration for MR image segmentation","authors":"Shangling Jui, Chao Lin, Haibing Guan, A. Abraham, A. Hassanien, Kai Xiao","doi":"10.1109/NaBIC.2014.6921884","DOIUrl":null,"url":null,"abstract":"In this paper, we present an image segmentation technique based on fuzzy c-means (FCM) incorporated with wavelet domain noise filtration. With the use of image noise feature estimation composed of preliminary coefficient classification and wavelet domain indicator, a filter for balancing the preservation of relevant details against the degree of noise reduction can be created. The filter is further incorporated with FCM algorithm into the membership function for clustering. This approach allows FCM not only to exploit useful spatial information, but also dynamically minimize clustering errors caused by common noise in medical images. Experimental results suggest its usefulness for reducing FCM clustering noise sensitivity. In MR image segmentation applications, the proposed method outperforms other FCM variations, in terms of quantitative performance measure and visual quality.","PeriodicalId":209716,"journal":{"name":"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NaBIC.2014.6921884","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12
Abstract
In this paper, we present an image segmentation technique based on fuzzy c-means (FCM) incorporated with wavelet domain noise filtration. With the use of image noise feature estimation composed of preliminary coefficient classification and wavelet domain indicator, a filter for balancing the preservation of relevant details against the degree of noise reduction can be created. The filter is further incorporated with FCM algorithm into the membership function for clustering. This approach allows FCM not only to exploit useful spatial information, but also dynamically minimize clustering errors caused by common noise in medical images. Experimental results suggest its usefulness for reducing FCM clustering noise sensitivity. In MR image segmentation applications, the proposed method outperforms other FCM variations, in terms of quantitative performance measure and visual quality.