Knowledge-based 3D analysis from 2D medical images

Author

Dhawan, A.P. ; Arata, L.

Author_Institution

Dept. of Electr. & Comput. Eng., Cincinnati Univ., OH, USA

Volume

10

Issue

4

fYear

1991

Firstpage

30

Lastpage

37

Abstract

An anatomical knowledge-based system for image analysis that interprets CT/MR (computed tomography/magnetic resonance) images of the human chest cavity is reported. The approach utilizes a low-level image analysis system with the ability to analyze the data in bottom-up (or data-driven) and top-down (or model-driven) modes to improve the high-level recognition process. Several image segmentation algorithms, including K-means clustering, pyramid-based region extraction, and rule-based merging, are used for obtaining the segmented regions. To obtain a reasonable number of well-segmented regions that have a good correlation with the anatomy, a priori knowledge in the form of masks is used to guide the segmentation process. Segmentation of the brain is also considered.<>

Keywords

biomedical NMR; brain; computerised pattern recognition; computerised picture processing; computerised tomography; knowledge based systems; medical diagnostic computing; 2D medical images; CT images; K-means clustering; MRI; anatomical knowledge-based system; bottom up mode; brain; computed tomography; high-level recognition process; human chest cavity; image segmentation algorithms; low-level image analysis system; magnetic resonance images; masks; pyramid-based region extraction; rule-based merging; top down mode; Biomedical imaging; Computed tomography; Data analysis; Humans; Image analysis; Image recognition; Image segmentation; Knowledge based systems; Magnetic analysis; Magnetic resonance;

fLanguage

English

Journal_Title

Engineering in Medicine and Biology Magazine, IEEE

Publisher

ieee

ISSN

0739-5175

Type

jour

DOI

10.1109/51.107166

Filename

107166