Self-organizing Features For Regularized Standardization Of Brain Images

Abstract

A semi-automatic, feature-based standardization technique is proposed to complement the existing global image standardization methods. The benefits of our method are speed and accuracy in local alignment. The method consists of three phases: In phase one, templates are generated from the atlas structures, using Self-Organizing Maps (SOMs). The parameters of each SOM are determined using a new topology evaluation technique. In phase two, the atlas templates are reconfigured using points from individual features, to establish a one-to-one correspondence between the atlas and individual structures. During training, a regularization procedure can be optionally invoked to guarantee smoothness in areas where the discrepancy between the atlas and individual feature is high. In the final phase, difference vectors are generated using the corresponding points of the atlas and the individual structure. The whole image is warped by interpolation of the difference vectors through Gaussian radial basis functions, whic h are determined by minimizing a membrane energy. Results are demonstrated on selected sulci in brain MRIs.

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Image standardization; Non-linear warping; Regularized alignment; Self-organizing maps

International Standard Serial Number (ISSN)

0277-786X

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Society of Photo-optical Instrumentation Engineers, All rights reserved.

Publication Date

01 Jan 2001

Link to Full Text

Share

 
COinS