Computer aided analysis of breast MRI enhancement kinetics using mean shift clustering and multifeature iterative region of interest selection
- PMID: 22786883
- DOI: 10.1002/jmri.23746
Computer aided analysis of breast MRI enhancement kinetics using mean shift clustering and multifeature iterative region of interest selection
Abstract
Purpose: To evaluate automatic characterization of a breast MR lesion by its spatially coherent region of interest (ROI).
Materials and methods: The method delineated 247 enhancing lesions using Otsu thresholding after manually placing a sphere. Mean Shift Clustering subdivided each volume, based on features including pharmacokinetic parameters. An iteratively trained classifier to predict the most suspicious ROI (IsR) was used, to predict the malignancy likelihood of each lesion. Performance was evaluated using receiver operator characteristic (ROC) analysis, and compared with a previous prototype. IsR was compared with noniterative training. The effect of adding BI-RADS™ morphology (from a radiologist) to the classifier was investigated.
Results: The area under the ROC curve (AUC) was 0.83 (95% confidence interval [CI] of 0.77-0.88), and was 0.75 (95%CI = 0.68-0.81; P = 0.029) without pharmacokinetic features. IsR performed better than conventional selection, based on one feature (AUC 0.75, 95%CI = 0.68-0.81; P = 0.035). With morphology, the AUC was 0.84 (95%CI = 0.78-0.88) versus 0.82 without (P = 0.40).
Conclusion: Breast lesions can be characterized by their most suspicious, contiguous ROI using multi-feature clustering and iterative training. Characterization was improved by including pharmacokinetic modeling, while in our experiments, including morphology did not improve characterization.
Copyright © 2012 Wiley Periodicals, Inc.
Similar articles
-
Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis.Magn Reson Imaging. 2014 Apr;32(3):197-205. doi: 10.1016/j.mri.2013.12.002. Epub 2013 Dec 17. Magn Reson Imaging. 2014. PMID: 24439361
-
Optimizing MRI scan time in the computation of pharmacokinetic parameters (K(trans) ) in breast cancer diagnosis.J Magn Reson Imaging. 2013 Sep;38(3):573-9. doi: 10.1002/jmri.24008. Epub 2013 Jan 24. J Magn Reson Imaging. 2013. PMID: 23349046 Clinical Trial.
-
[Quantitative parametric analysis of contrast-enhanced lesions in dynamic MR mammography].Radiologe. 2008 Jun;48(6):593-600. doi: 10.1007/s00117-007-1562-0. Radiologe. 2008. PMID: 18004537 Review. German.
-
Automated analysis of contrast enhancement in breast MRI lesions using mean shift clustering for ROI selection.J Magn Reson Imaging. 2007 Sep;26(3):606-14. doi: 10.1002/jmri.21026. J Magn Reson Imaging. 2007. PMID: 17729367
-
Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI.Med Phys. 2006 Aug;33(8):2878-87. doi: 10.1118/1.2210568. Med Phys. 2006. PMID: 16964864
Cited by
-
Influence of scan duration on the estimation of pharmacokinetic parameters for breast lesions: a study based on CAIPIRINHA-Dixon-TWIST-VIBE technique.Eur Radiol. 2015 Apr;25(4):1162-71. doi: 10.1007/s00330-014-3451-z. Epub 2014 Oct 17. Eur Radiol. 2015. PMID: 25323603
-
Quantitative tumor segmentation for evaluation of extent of glioblastoma resection to facilitate multisite clinical trials.Transl Oncol. 2014 Feb 1;7(1):40-7. doi: 10.1593/tlo.13835. eCollection 2014 Feb. Transl Oncol. 2014. PMID: 24772206 Free PMC article.
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Medical
