NEURAL-NETWORK MAPPING FOR NONLINEAR STEREOTAXIC NORMALIZATION OF BRAIN MR IMAGES

被引：24

作者：

KOSUGI, Y ^{[1
]}

SASE, M ^{[1
]}

KUWATANI, H ^{[1
]}

KINOSHITA, N ^{[1
]}

MOMOSE, T ^{[1
]}

NISHIKAWA, J ^{[1
]}

WATANABE, T ^{[1
]}

机构：

[1] UNIV TOKYO,SCH MED,TOKYO 113,JAPAN

来源：

JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY | 1993年 / 17卷 / 03期

关键词：

STEREOTAXIC NORMALIZATION; MAGNETIC RESONANCE IMAGING; ADAPTIVE MAPPING; NEURAL NETWORKS;

D O I：

10.1097/00004728-199305000-00023

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

We present techniques of automatic nonlinear transformation of MR images (2D or 3D). A neural network automatically finds the corresponding parts between the subject's brain images and the standard images. By iterative operations, the network generates a set of image-shifting vectors to realize a plastic transformation. For precise matching, a set of markers can be placed manually before starting the transformation on landmarks of the images, e.g., on the anterior-posterior commissural line and on the central sulcus.

引用

页码：455 / 460

页数：6

共 10 条

[1]

ARBIB MA, 1988, DYNAMIC INTERACTIONS

[2] PLASTIC TRANSFORMATION OF PET IMAGES [J].