Popescu V, Ran N C G, Barkhof F, Chard D T, Wheeler-Kingshott C A, Vrenken H
Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands.
NMR Research Unit, Queen Square Multiple Sclerosis Centre, University College London (UCL) Institute of Neurology, London, UK ; National Institute for Health Research (NIHR), University College London Hospitals (UCLH), Biomedical Research Centre, London, UK.
Neuroimage Clin. 2014 Jan 18;4:366-73. doi: 10.1016/j.nicl.2014.01.004. eCollection 2014.
In multiple sclerosis (MS), brain atrophy quantification is affected by white matter lesions. LEAP and FSL-lesion_filling, replace lesion voxels with white matter intensities; however, they require precise lesion identification on 3DT1-images.
To determine whether 2DT2 lesion masks co-registered to 3DT1 images, yield grey and white matter volumes comparable to precise lesion masks.
2DT2 lesion masks were linearly co-registered to 20 3DT1-images of MS patients, with nearest-neighbor (NNI), and tri-linear interpolation. As gold-standard, lesion masks were manually outlined on 3DT1-images. LEAP and FSL-lesion_filling were applied with each lesion mask. Grey (GM) and white matter (WM) volumes were quantified with FSL-FAST, and deep gray matter (DGM) volumes using FSL-FIRST. Volumes were compared between lesion mask types using paired Wilcoxon tests.
Lesion-filling with gold-standard lesion masks compared to native images reduced GM overestimation by 1.93 mL (p < .001) for LEAP, and 1.21 mL (p = .002) for FSL-lesion_filling. Similar effects were achieved with NNI lesion masks from 2DT2. Global WM underestimation was not significantly influenced. GM and WM volumes from NNI, did not differ significantly from gold-standard. GM segmentation differed between lesion masks in the lesion area, and also elsewhere. Using the gold-standard, FSL-FAST quantified as GM on average 0.4% of the lesion area with LEAP and 24.5% with FSL-lesion_filling. Lesion-filling did not influence DGM volumes from FSL-FIRST.
These results demonstrate that for global GM volumetry, precise lesion masks on 3DT1 images can be replaced by co-registered 2DT2 lesion masks. This makes lesion-filling a feasible method for GM atrophy measurements in MS.
在多发性硬化症（MS）中，脑萎缩的量化受到白质病变的影响。LEAP和FSL-lesion_filling方法通过用白质强度替换病变体素来处理病变；然而，它们需要在3D T1图像上精确识别病变。
确定与3D T1图像配准的2D T2病变掩码是否能产生与精确病变掩码相当的灰质和白质体积。
使用最近邻插值（NNI）和三线性插值将2D T2病变掩码线性配准到20例MS患者的3D T1图像上。作为金标准，在3D T1图像上手动勾勒病变掩码。对每个病变掩码应用LEAP和FSL-lesion_filling方法。使用FSL-FAST量化灰质（GM）和白质（WM）体积，使用FSL-FIRST量化深部灰质（DGM）体积。使用配对Wilcoxon检验比较不同病变掩码类型之间的体积。
与原始图像相比，使用金标准病变掩码进行病变填充时，LEAP方法使GM高估减少了1.93 mL（p <.001），FSL-lesion_filling方法使GM高估减少了1.21 mL（p =.002）。2D T2的NNI病变掩码也有类似效果。整体WM低估没有受到显著影响。NNI的GM和WM体积与金标准没有显著差异。病变区域及其他部位的病变掩码之间的GM分割存在差异。使用金标准时，FSL-FAST将LEAP方法处理的病变区域平均0.4%量化为GM，将FSL-lesion_filling方法处理的病变区域平均24.5%量化为GM。病变填充不影响FSL-FIRST的DGM体积。
这些结果表明，对于整体GM体积测量，3D T1图像上的精确病变掩码可以被配准的2D T2病变掩码替代。这使得病变填充成为MS中GM萎缩测量的一种可行方法。
