Saeed N, Hajnal J V, Oatridge A
Picker Research Laboratory, GEC Hirst Research Centre, Borehamwood, England.
J Comput Assist Tomogr. 1997 Mar-Apr;21(2):192-201. doi: 10.1097/00004728-199703000-00005.
An automated procedure has been developed to isolate the brain in single/multislice or whole-volume MR images obtained from various sequences.
T1-weighted, T2-weighted, and inversion recovery images were acquired. The brain segmentation procedure employed (A) a knowledge base that held generic information about the brain in the three orthogonal views and (B) a texture definition and intensity characteristics of features within the head. The brain was segmented by selectively blurring scans using components of B; contour following with region growing was initiated until the isolated feature satisfied the measurements in A.
The brain was segmented automatically from 210 subjects (whole volume) and 52 subjects (multi/single slice). Detailed analysis of seven segmented brains showed that < 0.8% of the contour pixels were erroneously identified. Whole-volume head scans consisting of 140 x 256 x 256 pixels were segmented in < 30 min.
A robust, fast, and efficient procedure has been developed to segment the brain from MR images.
已开发出一种自动化程序，用于从各种序列获取的单/多层或全容积磁共振成像（MR）图像中分离出大脑。
采集了T1加权、T2加权和反转恢复图像。大脑分割程序采用（A）一个知识库，该知识库保存了大脑在三个正交视图中的一般信息，以及（B）头部内特征的纹理定义和强度特征。通过使用B的组件选择性地模糊扫描来分割大脑；开始进行轮廓跟踪和区域生长，直到分离出的特征满足A中的测量要求。
从210名受试者（全容积）和52名受试者（多层/单层）中自动分割出大脑。对七个分割后的大脑进行详细分析表明，轮廓像素的错误识别率<0.8%。由140×256×256像素组成的全容积头部扫描在<30分钟内完成分割。
已开发出一种强大、快速且高效的程序，用于从MR图像中分割大脑。
