Sparse patch‐based representation with combined information of atlas for multi‐atlas label fusion. Issue 8 (1st August 2018)

• Record Type: Journal Article
• Authors: Yan, Meng; Liu, Hong; Song, Enmin; Qian, Yuejing; Jin, Lianghai; Hung, Chih‐Cheng
• Is Part Of: IET image processing. Volume 12:Issue 8(2018)
• Page Start: 1345
• Page End: 1353
• Publication Date: 2018-08-01
• Subjects: image fusion -- image segmentation -- brain -- medical image processing -- biomedical MRI -- image representation -- image classification; multiatlas label fusion -- multiatlas patch -- label fusion method -- representation method -- atlas image -- atlas label information -- sparse linear combination -- sparse patch‐based representation -- atlas information -- local binary texture -- voxel vector; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.1108
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : To obtain a higher accuracy in the multi‐atlas patch‐based label fusion method, it is essential to have the accurate similarity measure of selected patches. In this study, the authors propose a new sparse patch‐based representation method using a local binary texture (LBT) in the atlas image and atlas label information for the multi‐atlas label fusion. In the proposed method, the intensity information in a patch is converted into a LBT which is then combined with the labels of corresponding patches from the atlas to form an atom of a dictionary. The initial labels of target images are estimated through a rough segmentation. The voxel in a patch to be labelled is also constructed as a vector similar to the atom. The voxel vector is then modelled as a sparse linear combination of the atoms in the dictionary. Experimental results on two MR brain data sets demonstrated that the proposed method is efficient in the segmentation which can achieve competitive performance compared with the state‐of‐the‐art methods.