Date-driven Based Image Enhancement for Segmenting of MS Lesions in T2-w and Flair MRI

Ziming Zeng, Zhonghua Han, Yitian Zhao, Reyer Zwiggelaar

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddTrafodion Cynhadledd (Nid-Cyfnodolyn fathau)

Crynodeb

This paper proposed a data-driven based image enhancement scheme to segment Multiple Sclerosis (MS) lesions. It utilizes a class-adaptive Gaussian Markov random field modelling (HMRF) and mutual information to automatic enhance the MS lesions. Then an alpha matting technique is used to refine the segmentation results. The advantages of the approach lies in its date-driven processing. It can automatically enhance the density of MS lesions, which is guided by calculating the mutual information value of the segmentation results in the successive steps. In addition, the partial volume effects are considered and the regions of interests are segmented in a sub-pixel precision. The experiments on real MR images show the proposed segmentation method can effectively segment MS lesions.
Iaith wreiddiolSaesneg
TeitlFrontier and Future Development of Information Technology in Medicine and Education, ITME 2013
Is-deitlITME 2013
GolygyddionShaozi Li, Qun Jin, Xiaohong Jiang, James J. (Jong Hyuk) Park
CyhoeddwrSpringer Nature
Tudalennau2827-2832
Nifer y tudalennau6
ISBN (Electronig)978-94-007-7618-0
ISBN (Argraffiad)9789400776173
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 2014

Cyfres gyhoeddiadau

EnwLecture Notes in Electrical Engineering
Cyfrol269 LNEE
ISSN (Argraffiad)1876-1100
ISSN (Electronig)1876-1119

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Date-driven Based Image Enhancement for Segmenting of MS Lesions in T2-w and Flair MRI'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn