2007
DOI: 10.1002/jmri.21026
|View full text |Cite
|
Sign up to set email alerts
|

Automated analysis of contrast enhancement in breast MRI lesions using mean shift clustering for ROI selection

Abstract: Purpose: To evaluate a new method for automated determination of a region of interest (ROI) for the analysis of contrast enhancement in breast MRI. Materials and Methods:Mean shift multidimensional clustering (MS-MDC) was employed to divide 92 lesions into several spatially contiguous clusters each, based on multiple enhancement parameters. The ROIs were defined as the clusters with the highest probability of malignancy. The performance of enhancement analysis within these ROIs was estimated using the area und… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
32
0

Year Published

2008
2008
2020
2020

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 27 publications
(32 citation statements)
references
References 26 publications
0
32
0
Order By: Relevance
“…We can speculate that DCE-MRI may reveal areas of subtle bone marrow infiltration at margins of the lesion in territories appearing normal on standard T1-weighted sequences as previously demonstrated in myeloma [22]. Similar statistical approaches of DCE-MRI data already proved to be useful in detecting and delineating the tumor (which, by extension, allows for the quantitative measurement of the extension or the shrinkage of the tumor between two examinations) and grading its aggressiveness [34].…”
Section: Pixel-wise Quantitative Methodologymentioning
confidence: 53%
“…We can speculate that DCE-MRI may reveal areas of subtle bone marrow infiltration at margins of the lesion in territories appearing normal on standard T1-weighted sequences as previously demonstrated in myeloma [22]. Similar statistical approaches of DCE-MRI data already proved to be useful in detecting and delineating the tumor (which, by extension, allows for the quantitative measurement of the extension or the shrinkage of the tumor between two examinations) and grading its aggressiveness [34].…”
Section: Pixel-wise Quantitative Methodologymentioning
confidence: 53%
“…Several works are based on the use of machine learning techniques for DCE-MRI tumour analysis [3,4,5,6]. In [3], a visual data-mining approach is proposed to support the medical researchers in tumoral areas characterization by clustering data according to the transendothelial permeability (kPS) and fractional plasma volume (fPV).…”
Section: Introductionmentioning
confidence: 99%
“…In [3], a visual data-mining approach is proposed to support the medical researchers in tumoral areas characterization by clustering data according to the transendothelial permeability (kPS) and fractional plasma volume (fPV). Although kPS and fPV are accepted estimate of tissue vasculature, their instability under small perturbation of the chosen pharmacokinetics model was proved [4,5]. Therefore, different works are addressed the idea of analyzing directly the raw signals by exploiting possible other compact parameters of the curve shapes.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Recently, Stoutjesdijk et al (11) proposed using mean shift clustering for ROI selection to analyze the dynamic contrast enhancement characteristics of breast lesions. Their approach is dependent on a connected threshold analysis on a feature image initiated by a user selected seed-point.…”
mentioning
confidence: 99%