CLASSIC: Consistent longitudinal alignment and segmentation for serial image computing
CLASSIC: Consistent longitudinal alignment and segmentation for serial image computing
复制标题
DOI：
10.1016/j.neuroimage.2005.09.054
复制
发表时间：
2006-04-01
期刊：
影响因子：
5.7
通讯作者：
Davatzikos, C
中科院分区：
文献类型：
--
作者：
Xue, Z;Shen, DG;Davatzikos, C
本文提出了一种时间一致和空间自适应的纵向MR脑图像分割算法，简称CLASSIC，其目的是获得准确的测量率的区域和全球脑体积前序列MR图像的变化。该算法结合了图像自适应聚类，时空平滑约束，和图像扭曲，共同分割一系列的3-D MR脑图像的同一主题，可能会经历的变化，由于发展，衰老，或疾病。形态学变化，如生长或萎缩，也被估计为算法的一部分。仿真和真实的纵向MR脑图像的实验结果表明，分割精度和纵向一致性。(c)2005年爱思唯尔公司All rights reserved.
This paper proposes a temporally consistent and spatially adaptive longitudinal MR brain image segmentation algorithm, referred to as CLASSIC, which aims at obtaining accurate measurements of rates of change of regional and global brain volumes front serial MR images. The algorithm incorporates image-adaptive clustering, spatiotemporal smoothness constraints, and image warping to jointly segment a series of 3-D MR brain images of the same subject that might be undergoing changes due to development, aging, or disease. Morphological changes, such as growth or atrophy, are also estimated as part of the algorithm. Experimental results on simulated and real longitudinal MR brain images show both segmentation accuracy and longitudinal consistency. (c) 2005 Elsevier Inc. All rights reserved.