PuSH - Publikationsserver des Helmholtz Zentrums München

Parker, G.J.M.* ; Schnabel, J.A.* ; Barker, G.J.*

Nonlinear smoothing of MR images using approximate entropy — A local measure of signal intensity irregularity.

In: (Biennial International Conference on Information Processing in Medical Imaging). Berlin [u.a.]: Springer, 1999. 484-489 (Lect. Notes Comput. Sc. ; 1613)
DOI
Open Access Green möglich sobald Postprint bei der ZB eingereicht worden ist.
Approximate entropy (ApEn) is a computable measure of sequential irregularity that is applicable to sequences of numbers of finite length. As such, it may be used to determine how random a sequence of numbers is. We exploit this property to determine the relevance of image information; to determine whether a spatial signal intensity distribution varies in a regular fashion — and is therefore likely to be an image feature or image texture, or is highly random — and likely to be noise. We present an outline of two possible methodologies for creating an ApEn-based noise filter: a modified median filter and a modified anisotropic diffusion scheme. We show that both approaches lead to effective noise reduction in MR images, with improved information-retaining properties when compared with their conventional counterparts.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Biennial International Conference on Information Processing in Medical Imaging
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 1613, Heft: , Seiten: 484-489 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Nichtpatentliteratur Publikationen
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)