Scully Mark, Anderson Blake, Lane Terran, Gasparovic Charles, Magnotta Vince, Sibbitt Wilmer, Roldan Carlos, Kikinis Ron, Bockholt Henry J
The Mind Research Network Albuquerque, NM, USA.
Front Hum Neurosci. 2010 Apr 19;4:27. doi: 10.3389/fnhum.2010.00027. eCollection 2010.
We demonstrate an automated, multi-level method to segment white matter brain lesions and apply it to lupus. The method makes use of local morphometric features based on multiple MR sequences, including T1-weighted, T2-weighted, and fluid attenuated inversion recovery. After preprocessing, including co-registration, brain extraction, bias correction, and intensity standardization, 49 features are calculated for each brain voxel based on local morphometry. At each level of segmentation a supervised classifier takes advantage of a different subset of the features to conservatively segment lesion voxels, passing on more difficult voxels to the next classifier. This multi-level approach allows for a fast lesion classification method with tunable trade-offs between sensitivity and specificity producing accuracy comparable to a human rater.
我们展示了一种用于分割脑白质病变的自动化多级方法，并将其应用于狼疮。该方法利用基于多个磁共振序列的局部形态特征，包括T1加权、T2加权和液体衰减反转恢复序列。经过预处理，包括配准、脑提取、偏差校正和强度标准化后，基于局部形态学为每个脑体素计算49个特征。在分割的每个级别，一个监督分类器利用不同的特征子集来保守地分割病变体素，将更难处理的体素传递给下一个分类器。这种多级方法允许一种快速的病变分类方法，在敏感性和特异性之间进行可调权衡，并产生与人类评级者相当的准确性。
