干旱区生态环境知识资源中心(Arid): FLAIR(2) improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images

Arid

DOI	10.1016/j.nicl.2019.101918
	FLAIR(2) improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images
	Le, M.1; Tang, L. Y. W.1,2; Hernandez-Torres, E.3,4,9; Jarrett, M.3,5; Brosch, T.1,6,7; Metz, L.8; Li, D. K. B.1,2,4; Traboulsee, A.9; Tam, R. C.1,2; Rauscher, A.3,10,11; Wiggermann, V 3,4,11
通讯作者	Wiggermann, V
来源期刊	NEUROIMAGE-CLINICAL
ISSN	2213-1582
出版年	2019
卷号	23
英文摘要	Background: Accurate segmentation of MS lesions on MRI is difficult and, if performed manually, time consuming. Automatic segmentations rely strongly on the image contrast and signal-to-noise ratio. Literature examining segmentation tool performances in real-world multi-site data acquisition settings is scarce. Objective: FLAIR(2), a combination of T-2-weighted and fluid attenuated inversion recovery (FLAIR) images, improves tissue contrast while suppressing CSF. We compared the use of FLAIR and FLAIR(2) in LesionTOADS, OASIS and the lesion segmentation toolbox (LST) when applied to non-homogenized, multi-center 2D-imaging data. Methods: Lesions were segmented on 47 MS patient data sets obtained from 34 sites using LesionTOADS, OASIS and LST, and compared to a semi-automatically generated reference. The performance of FLAIR and FLAIR(2) was assessed using the relative lesion volume difference (LVD), Dice coefficient (DSC), sensitivity (SEN) and symmetric surface distance (SSD). Performance improvements related to lesion volumes (LVs) were evaluated for all tools. For comparison, LesionTOADS was also used to segment lesions from 3 T single-center MR data of 40 clinically isolated syndrome (CIS) patients. Results: Compared to FLAIR, the use of FLAIR(2) in LesionTOADS led to improvements of 31.6% (LVD), 14.0% (DSC), 25.1% (SEN), and 47.0% (SSD) in the multi-center study. DSC and SSD significantly improved for larger LVs, while LVD and SEN were enhanced independent of LV. OASIS showed little difference between FLAIR and FLAIR(2), likely due to its inherent use of T(2)w and FLAIR. LST replicated the benefits of FLAIR(2) only in part, indicating that further optimization, particularly at low LVs is needed. In the CIS study, LesionTOADS did not benefit from the use of FLAIR(2) as the segmentation performance for both FLAIR and FLAIR(2) was heterogeneous. Conclusions: In this real-world, multi-center experiment, FLAIR(2) outperformed FLAIR in its ability to segment MS lesions with LesionTOADS. The computation of FLAIR(2) enhanced lesion detection, at minimally increased computational time or cost, even retrospectively. Further work is needed to determine how LesionTOADS and other tools, such as LST, can optimally benefit from the improved FLAIR(2) contrast.
英文关键词	FLAIR FLAIR(2) Segmentation Lesion volume Performance evaluation Multi-center
类型	Article
语种	英语
国家	Canada ; Germany
开放获取类型	Green Published, gold
收录类别	SCI-E
WOS记录号	WOS:000485804400120
WOS关键词	WHITE-MATTER LESIONS ; BRAIN MRI ; DIAGNOSIS ; GUIDELINES ; ASSOCIATION ; SINGLE ; ROBUST
WOS类目	Neuroimaging
WOS研究方向	Neurosciences & Neurology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/217766
作者单位	1.Univ British Columbia, Div Neurol, MS MRI Res Grp, Vancouver, BC, Canada; 2.Univ British Columbia, Dept Radiol, Vancouver, BC, Canada; 3.Univ British Columbia, Dept Pediat, Vancouver, BC, Canada; 4.Univ British Columbia, UBC MRI Res Ctr, Room M10,Purdy Pavil,2221 Wesbrook Mall, Vancouver, BC V6T 2B5, Canada; 5.Populat Data BC, Vancouver, BC, Canada; 6.Univ British Columbia, Dept Elect & Comp Engn, Vancouver, BC, Canada; 7.Philips Med Innovat Technol, Hamburg, Germany; 8.Univ Calgary, Dept Clin Neurosci, Calgary, AB, Canada; 9.Univ British Columbia, Dept Neurol, Div Med, Vancouver, BC, Canada; 10.BC Childrens Hosp Res Inst, Vancouver, BC, Canada; 11.Univ British Columbia, Dept Phys & Astron, Vancouver, BC, Canada
推荐引用方式 GB/T 7714	Le, M.,Tang, L. Y. W.,Hernandez-Torres, E.,et al. FLAIR(2) improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images[J],2019,23.
APA	Le, M..,Tang, L. Y. W..,Hernandez-Torres, E..,Jarrett, M..,Brosch, T..,...&Wiggermann, V.(2019).FLAIR(2) improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images.NEUROIMAGE-CLINICAL,23.
MLA	Le, M.,et al."FLAIR(2) improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images".NEUROIMAGE-CLINICAL 23(2019).