It is difficult to automatically segment and classify tomographic images of an actual patient's brain. Therefore, many interactive operations are performed. It is very time consuming and its precision is user-dependent. Here, the authors combined a brain atlas and 3D fuzzy image segmentation into the image matching. It can not only find out the precise boundary of an anatomic structure, but also save time in the interactive operation. At first, the anatomic information of the atlas is mapped onto tomograph images of an actual brain with an image matching method. Then, based on the mapping result, a 3D fuzzy structure mask is calculated. With the fuzzy information of anatomic structure, a new method of fuzzy clustering is used to segment and classify the real brain image. There is only a minimum requirement of interaction in the whole process, including removing the skull and selecting some intrinsic point pairs.
[1]
F. Bookstein,et al.
Morphometric Tools for Landmark Data: Geometry and Biology
,
1999
.
[2]
Andreas Pommert,et al.
Intepretation of tomographic images using automatic atlas lookup
,
1994,
Other Conferences.
[3]
Michael J. Ackerman,et al.
The Visible Human Project of the National Library of Medicine: Remote access and distribution of a multi-gigabyte data set
,
1993
.
[4]
Lawrence O. Hall,et al.
Knowledge-based classification and tissue labeling of MR images of human brain
,
1993,
IEEE Trans. Medical Imaging.
[5]
F. Bookstein,et al.
Morphometric Tools for Landmark Data: Geometry and Biology
,
1999
.