Automatic segmentation of white matter hyperintensities in the elderly using FLAIR images at 3T.
Automatic segmentation of white matter hyperintensities in the elderly using FLAIR images at 3T.
复制标题
DOI：
10.1002/jmri.22004
复制
发表时间：
2010-06
影响因子：
4.4
通讯作者：
Lobaugh, Nancy J.
中科院分区：
文献类型：
--
作者：
Gibson, Erin;Gao, Fuqiang;Black, Sandra E.;Lobaugh, Nancy J.
确定在3 T下老年人大脑快速液体衰减反转恢复（FLAIR）图像上分割白色高信号（WMH）的自动方法的精确度和准确度。FLAIR图像从18个人（60-82岁，9名女性）与WMH负荷范围从1-80立方厘米。该协议包括清除明显高强度体素;两类模糊C均值聚类（FCM）;和阈值分割可能的WMH。使用白色物质模板的两种假阳性最小化（FPM）方法进行了测试。通过将合成高强度体素添加到脑切片来评估精度。通过比较自动和手动分割的准确性进行了验证。全脑，体素的相似性度量，下和高估被用来评估精度和准确性。精确度很高，因为合成数据集中的最低准确度为93%。两种FPM策略都成功地提高了整体准确性。单独FCM分割的全脑准确率范围为45%-81%，使用FPM策略提高到75%-85%。该方法在老年人中常见的WMH负荷范围内是准确的。准确度达到或超过了使用多光谱和/或更复杂的模式识别方法的其他方法。J.磁共振Imaging 2010;31：1311-1322.© 2010 Wiley-Liss公司。
To determine the precision and accuracy of an automated method for segmenting white matter hyperintensities (WMH) on fast fluid-attenuated inversion-recovery (FLAIR) images in elderly brains at 3T. FLAIR images from 18 individuals (60–82 years, 9 females) with WMH burdens ranging from 1–80 cm3 were used. The protocol included the removal of clearly hyperintense voxels; two-class fuzzy C-means clustering (FCM); and thresholding to segment probable WMH. Two false-positive minimization (FPM) methods using white matter templates were tested. Precision was assessed by adding synthetic hyperintense voxels to brain slices. Accuracy was validated by comparing automatic and manual segmentations. Whole-brain, voxel-wise metrics of similarity, under- and overestimation were used to evaluate both precision and accuracy. Precision was high, as the lowest accuracy in the synthetic datasets was 93%. Both FPM strategies successfully improved overall accuracy. Whole-brain accuracy for the FCM segmentation alone ranged from 45%–81%, which improved to 75%–85% using the FPM strategies. The method was accurate across the range of WMH burden typically seen in the elderly. Accuracy levels achieved or exceeded those of other approaches using multispectral and/or more sophisticated pattern recognition methods. J. Magn. Reson. Imaging 2010;31:1311–1322. © 2010 Wiley-Liss, Inc.
登录
查看更多内容
影响因子：
10.6
作者：
Sled, JG;Zijdenbos, AP;Evans, AC
通讯作者：
Evans, AC
影响因子：
4.8
作者：
Smith, SM
通讯作者：
Smith, SM
影响因子：
5.7
作者：
Dade, LA;Gao, FQ;Black, SE
通讯作者：
Black, SE
影响因子：
5.7
作者：
Admiraal-Behloul, F;van den Heuvel, DMJ;Relber, JHC
通讯作者：
Relber, JHC
DOI：
10.1001/jama.1997.03540340047031
发表时间：
1997-03-12
影响因子：
120.7
作者：
Snowdon, DA;Greiner, LH;Markesbery, WR
通讯作者：
Markesbery, WR