2011
DOI: 10.1002/mrm.23138
|View full text |Cite
|
Sign up to set email alerts
|

Automatic segmentation of amyloid plaques in MR images using unsupervised support vector machines

Abstract: Deposition of the β-amyloid peptide (Aβ) is an important pathological hallmark of Alzheimer’s disease (AD). However, reliable quantification of amyloid plaques in both human and animal brains remains a challenge. We present here a novel automatic plaque segmentation algorithm based on the intrinsic MR signal characteristics of plaques. This algorithm identifies plaque candidates in MR data by using watershed transform, which extracts regions with low intensities completely surrounded by higher intensity neighb… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 39 publications
0
3
0
Order By: Relevance
“…This method can be used in addition to histological evaluations as a useful tool for the development of new therapies. Future improvement of the method may be based on the automatic segmentation of the amyloid load to speed-up plaque quantification after Gd-staning ( Iordanescu et al, 2012 ). Also, our study showed that individual plaque labeling is feasible in vivo with a conventional MR contrast agent, as long as the contrast agent remains furtive for the BBB.…”
Section: Discussionmentioning
confidence: 99%
“…This method can be used in addition to histological evaluations as a useful tool for the development of new therapies. Future improvement of the method may be based on the automatic segmentation of the amyloid load to speed-up plaque quantification after Gd-staning ( Iordanescu et al, 2012 ). Also, our study showed that individual plaque labeling is feasible in vivo with a conventional MR contrast agent, as long as the contrast agent remains furtive for the BBB.…”
Section: Discussionmentioning
confidence: 99%
“…Teipel et al () proposed an alternative voxel‐based analysis of T2 relaxation time in AβPP/PS1 mice as a surrogate measure of plaque burden. In a recent study, Further automatic plaque segmentation algorithm have been reported (Iordanescu et al, ) which can reliably quantify amyloid plaques in mouse brains by the combination of watershed transform and SVM. This method can detect the spatial and temporal progression of amyloid deposition, which is necessary for the understanding of the Aβ formation, progression of plaque pathology in mouse models of AD and accessing the efficacy of amyloid clearance therapies.…”
Section: Amyloid Plaque Imaging Using Mrmmentioning
confidence: 99%
“…In recent years, successful attempts with an implementation of the watershed algorithm was made on samples of different anatomical structures evaluated with a use of MR. In this field of studies, an evaluation of the bone erosions of the hand [11,12], brain amyloid plaques [13] and even breast lesions [14] were presented. There are a few publications present image processing algorithms dedicated to the knee joint, but directed to evaluate cartilage [15] on weight bearing parts.…”
Section: Introductionmentioning
confidence: 99%