Han Deok, Singh Vikas, Lee Jee Eun, Zakszewski Elizabeth, Adluru Nagesh, Oakes Terrance R, Alexander Andrew
Waisman Laboratory for Brain Imaging and Behavior, University of Wisconsin-Madison, WI, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:5653-6. doi: 10.1109/IEMBS.2009.5333767.
The segmentation of diffusion tensor imaging (DTI) data is a challenging problem due to the high variation and overlap of the distributions induced by individual DTI measures (e.g., fractional anisotropy). Accurate tissue segmentation from DTI data is important for characterizing the mi-crostructural properties of white matter (WM) in a subsequent analysis. This step may also be useful for generating a mask to constrain the results of WM tractography. In this study, a graph-cuts segmentation method was applied to the problem of extracting WM, gray matter (GM) and cerebral spinal fluid (CSF) from brain DTI data. A two-phase segmentation method was adopted by first segmenting CSF signal from the DTI data using the third eigenvalue (lambda(3)) maps, and then extracting WM regions from the fractional anisotropy (FA) maps. The algorithm was evaluated on ten real DTI data sets obtained from in vivo human brains and the results were compared against manual segmentation by an expert. Overall, the graph cuts method performed well, giving an average segmentation accuracy of about 0.90, 0.77 and 0.88 for WM, GM and CSF respectively in terms of volume overlap(VO).
由于个体扩散张量成像（DTI）测量值（例如，分数各向异性）所导致的分布具有高度变异性和重叠性，DTI数据的分割是一个具有挑战性的问题。从DTI数据中准确进行组织分割对于在后续分析中表征白质（WM）的微观结构特性非常重要。这一步骤对于生成一个掩码以约束WM纤维束成像的结果也可能有用。在本研究中，一种图割分割方法被应用于从脑部DTI数据中提取WM、灰质（GM）和脑脊液（CSF）的问题。采用了一种两阶段分割方法，首先使用第三特征值（λ(3)）图从DTI数据中分割出CSF信号，然后从分数各向异性（FA）图中提取WM区域。该算法在从活体人类大脑获得的十个真实DTI数据集上进行了评估，并将结果与专家的手动分割进行了比较。总体而言，图割方法表现良好，就体积重叠（VO）而言，WM、GM和CSF的平均分割准确率分别约为0.90、0.77和0.88。
