IRUS Total

Brain Lesion Segmentation through Image Synthesis and Outlier Detection

File Description SizeFormat 
1-s2.0-S2213158217302164-main.pdfAccepted version538.83 kBAdobe PDFView/Open
1-s2.0-S2213158217302164-main.pdfPublished version2.08 MBAdobe PDFView/Open
Title: Brain Lesion Segmentation through Image Synthesis and Outlier Detection
Authors: Bowles
Qin, C
Guerrero, R
Gunn, R
Hammers, A
Dickie, D
Valdes Hernandez, M
Wardlaw, J
Rueckert, D
Item Type: Journal Article
Abstract: Cerebral small vessel disease (SVD) can manifest in a number of ways. Many of these result in hyperintense regions visible on T2-weighted magnetic resonance (MR) images. The automatic segmentation of these lesions has been the focus of many studies. However, previous methods tended to be limited to certain types of pathology, as a consequence of either restricting the search to the white matter, or by training on an individual pathology. Here we present an unsupervised abnormality detection method which is able to detect abnormally hyperintense regions on FLAIR regardless of the underlying pathology or location. The method uses a combination of image synthesis, Gaussian mixture models and one class support vector machines, and needs only be trained on healthy tissue. We evaluate our method by comparing segmentation results from 127 subjects with SVD with three established methods and report significantly superior performance across a number of metrics.
Issue Date: 8-Sep-2017
Date of Acceptance: 5-Sep-2017
URI: http://hdl.handle.net/10044/1/50834
DOI: https://dx.doi.org/10.1016/j.nicl.2017.09.003
ISSN: 2213-1582
Publisher: Elsevier
Start Page: 643
End Page: 658
Journal / Book Title: NeuroImage: Clinical
Volume: 16
Copyright Statement: Creative Commons Attribution 4.0 International (CC BY 4.0)
Sponsor/Funder: Innovate UK
Innovate UK
Funder's Grant Number: TSB Ref: 101685
46917-348146 102167
Publication Status: Published online
Open Access location: http://www.sciencedirect.com/science/article/pii/S2213158217302164
Appears in Collections:Computing
Faculty of Engineering