Presentation 2009-01-23
Segmentation of Breast Lesions in Ultrasound Images Using Fuzzy Clustering based on Structure Tensors
Yan XU, Chris CARSON, Toshihiro NISHIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Ultrasound imaging of the breasts is typically done as an adjunct to mammography when breast cancer is suspected. In ultrasound imaging, speckle noise which gives a granular appearance is one of the main restrictions of segmentation. In this paper, we propose a segmentation scheme for ultrasound images of breasts based on structure tensors using fuzzy clustering. Firstly, we use nonlinear structure tensors to extract speckle texture. And then we combine the nonlinear structure tensor with the image intensity to extract the features of ultrasound images. Finally, a pixel-based fuzzy c-means clustering is applied on the feature space for image segmentation. We use manual delineated lesion regions as validations of experiment results and good results are achieved in experiments on simulated and real images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Structure Tensor / Fuzzy C-Means Clustering / Ultrasound Image Segmentation
Paper # MBE2008-81
Date of Issue

Conference Information
Committee MBE
Conference Date 2009/1/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To ME and Bio Cybernetics (MBE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Segmentation of Breast Lesions in Ultrasound Images Using Fuzzy Clustering based on Structure Tensors
Sub Title (in English)
Keyword(1) Structure Tensor
Keyword(2) Fuzzy C-Means Clustering
Keyword(3) Ultrasound Image Segmentation
1st Author's Name Yan XU
1st Author's Affiliation Graduate school of Information, Production and System, Waseda University()
2nd Author's Name Chris CARSON
2nd Author's Affiliation Graduate school of Information, Production and System, Waseda University
3rd Author's Name Toshihiro NISHIMURA
3rd Author's Affiliation Graduate school of Information, Production and System, Waseda University
Date 2009-01-23
Paper # MBE2008-81
Volume (vol) vol.108
Number (no) 405
Page pp.pp.-
#Pages 4
Date of Issue