The Application of Local Structure Classification in Content-Based 3D Medical Image Retrieval

Author

Shuzhao Dong ; Kaikun Dong ; Lu Yin

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol. at Weihai, Weihai, China

fYear

2013

fDate

26-28 July 2013

Firstpage

639

Lastpage

642

Abstract

An approach is proposed to classify local structures for 3D medical images into line-like, blob-like and sheet-like patterns in different sizes. This approach is based on the second-order derivatives in multiscale space, using normalized response functions. The application of this approach in content-based 3D medical image retrieval is discussed. Experiments on CT images are performed and the method is proved to be efficient for filtering specific local structures in selected range of sizes.

Keywords

Hessian matrices; biomedical MRI; computerised tomography; content-based retrieval; filtering theory; image classification; image retrieval; medical image processing; CT images; Hessian matrix; MRI images; blob-like pattern; content-based 3D medical image retrieval; line-like pattern; local structure classification; multiscale space; normalized response functions; second-order derivatives; sheet-like pattern; volume images; Computed tomography; Eigenvalues and eigenfunctions; Image retrieval; Medical diagnostic imaging; Optical filters; Three-dimensional displays; 3D medical image; Hessian Matrix; content-based image retrieval; filtering; multi-scale analysis; response function;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Graphics (ICIG), 2013 Seventh International Conference on

Conference_Location

Qingdao

Type

conf

DOI

10.1109/ICIG.2013.132

Filename

6643749