1999
DOI: 10.1007/s002590050410
|View full text |Cite
|
Sign up to set email alerts
|

An automatic classification technique for attenuation correction in positron emission tomography

Abstract: In this paper a clustering technique is proposed for attenuation correction (AC) in positron emission tomography (PET). The method is unsupervised and adaptive with respect to counting statistics in the transmission (TR) images. The technique allows the classification of pre- or post-injection TR images into main tissue components in terms of attenuation coefficients. The classified TR images are then forward projected to generate new TR sinograms to be used for AC in the reconstruction of the corresponding em… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
38
0

Year Published

2002
2002
2006
2006

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 71 publications
(38 citation statements)
references
References 18 publications
0
38
0
Order By: Relevance
“…The region grower also has the ability to iterate around this critical point, and thus overcomes gross region underestimates caused by potentially large incremental step size. The resulting grown regions were stored as templates for the five different tissue types of interest, 3 I for Lung, 4 I for Bone, 5 I for soft tissue and 6 I for dense tissue. The purpose of the region grower is to provide a refinement on the tissue templates produced by globally thresholding the intensity values via the k-means algorithm.…”
Section: Tissue Template Generationmentioning
confidence: 99%
“…The region grower also has the ability to iterate around this critical point, and thus overcomes gross region underestimates caused by potentially large incremental step size. The resulting grown regions were stored as templates for the five different tissue types of interest, 3 I for Lung, 4 I for Bone, 5 I for soft tissue and 6 I for dense tissue. The purpose of the region grower is to provide a refinement on the tissue templates produced by globally thresholding the intensity values via the k-means algorithm.…”
Section: Tissue Template Generationmentioning
confidence: 99%
“…The majority of segmentation methods used for attenuation correction fall into one of the following two classes (see chapter 10): histogram-based thresholding techniques 72,73 and fuzzy-clustering based segmentation techniques. 74,75 Threshold approaches use the grey-level histogram counts to distinguish between regions. However, if the geometry of the attenuation map is based solely on the characteristics of the histogram, the technique is most likely to fail in regions where the total number of counts is small (e.g.…”
Section: 21d Segmentation Of Transmission Datamentioning
confidence: 99%
“…The segmentation method introduced by Bettinardi et al [11] is an automated adaptive clustering method. The main properties of this technique are that there are no a priori assumptions made about the number of clusters and the centroid values.…”
Section: Segmentationmentioning
confidence: 99%
“…To achieve low noise levels for short acquisition times of transmission data, methods of segmentation have been introduced (e.g. [9] - [11]) which result in an essentially noiseless image and potentially more accurate estimate of attenuation.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation