MULTIPARAMETRIC AUTOMATED SEGMENTATION OF BRAIN VEINS (408 views)
Veins And Lymphatics (ISSN: 2279-7483), 2015; 4(s1): 13-13.
Export to BibTeX Export to EndNote
Paper type: Abstract,
Impact factor: 0, 5-year impact factor: 0
Url: Not available.
Keywords: Brain Veins, Vessel Enhancing Diffusion, Map, Expectation Maximization Algorithm, Multiparametric Segmentation,
Affiliations:
*** IBB - CNR ***
1IRCCS SDN, Naples; 2Department of Bioengineering, Politecnico di Milano, Milan; 3Institute of Biostructure and Bioimaging,National Research Council, Naples; 4Department of Advanced Biomedical Sciences, University Federico II, Naples, Italy
References:
Not available.
Veins And Lymphatics (ISSN: 2279-7483), 2015; 4(s1): 13-13.
Export to BibTeX Export to EndNote
Paper type: Abstract,
Impact factor: 0, 5-year impact factor: 0
Url: Not available.
Keywords: Brain Veins, Vessel Enhancing Diffusion, Map, Expectation Maximization Algorithm, Multiparametric Segmentation,
Affiliations:
*** IBB - CNR ***
1IRCCS SDN, Naples; 2Department of Bioengineering, Politecnico di Milano, Milan; 3Institute of Biostructure and Bioimaging,National Research Council, Naples; 4Department of Advanced Biomedical Sciences, University Federico II, Naples, Italy
References:
Not available.
MULTIPARAMETRIC AUTOMATED SEGMENTATION OF BRAIN VEINS
Background : Manual segmentation of brain vessels in a typical MR dataset is both complex and time-consuming; therefore automated approaches are actively sought for, as they also improve the reproducibility of the results.
Objectives : To present a multiparametric segmentation method (MPS) that,starting from a vessel likeliness function (Vesselness) and R2*map of the brain, applies an Expectation Maximization (EM) algorithm to the bivariate distribution of the data to classify each voxel as belonging or not to veins.
Methods : Based on the assumption that a voxel belonging to a vein has high Vesselness and R2* values, on the log-scale joint histogram of the maps, the voxels whose Vesselness is higher than 0 were assigned to 3 main classes: i) a
Gaussian distribution with low R2*and Vesselness (false positives enhanced by Vesselness); ii) a class with R2* value above a given threshold; iii) another Gaussian distribution with medium-high value of R2* and high value of
Vesselness, the last two truly corresponding to veins. Through an EM algorithm, the parameters of the 3classes were estimated and the voxels belong-ing to the 2 vessel classes were identified. The performance of the MPS was compared to the Vesselness thresholding (VT) by blindly grading on a 0-5 scale the accuracy of vascular tree depiction.
Results: The semiquantitative analysis clearly showed that MPS achieved greater accuracy in vessel display (scores 4-5 in 88% of the test-sample) than VT (scores 2-3 in 74% of the test-sample). In particular, false positives were the main pitfall of VT compared to MPS.
Conclusions: Combining the information obtained from Vesselness and R2* maps, the MPS substantially increased sensitivity and specificity of the monoparametric tresholding based on vesselness images only.
Background : Manual segmentation of brain vessels in a typical MR dataset is both complex and time-consuming; therefore automated approaches are actively sought for, as they also improve the reproducibility of the results.
Objectives : To present a multiparametric segmentation method (MPS) that,starting from a vessel likeliness function (Vesselness) and R2*map of the brain, applies an Expectation Maximization (EM) algorithm to the bivariate distribution of the data to classify each voxel as belonging or not to veins.
Methods : Based on the assumption that a voxel belonging to a vein has high Vesselness and R2* values, on the log-scale joint histogram of the maps, the voxels whose Vesselness is higher than 0 were assigned to 3 main classes: i) a
Gaussian distribution with low R2*and Vesselness (false positives enhanced by Vesselness); ii) a class with R2* value above a given threshold; iii) another Gaussian distribution with medium-high value of R2* and high value of
Vesselness, the last two truly corresponding to veins. Through an EM algorithm, the parameters of the 3classes were estimated and the voxels belong-ing to the 2 vessel classes were identified. The performance of the MPS was compared to the Vesselness thresholding (VT) by blindly grading on a 0-5 scale the accuracy of vascular tree depiction.
Results: The semiquantitative analysis clearly showed that MPS achieved greater accuracy in vessel display (scores 4-5 in 88% of the test-sample) than VT (scores 2-3 in 74% of the test-sample). In particular, false positives were the main pitfall of VT compared to MPS.
Conclusions: Combining the information obtained from Vesselness and R2* maps, the MPS substantially increased sensitivity and specificity of the monoparametric tresholding based on vesselness images only.
MULTIPARAMETRIC AUTOMATED SEGMENTATION OF BRAIN VEINS
No results. |
MULTIPARAMETRIC AUTOMATED SEGMENTATION OF BRAIN VEINS
Other filter: ([btitle,keywords] "Brain Veins" OR [bti ...
Monti S, Cocozza S, Borrelli P, Straub S, Ladd ME, Salvatore M, Tedeschi E, Palma G
* MAVEN: An Algorithm for Multi-Parametric Automated Segmentation of Brain Veins from Gradient Echo Acquisitions (220 views) (PDF 188 views)
Ieee T Med Imaging (ISSN: 0278-0062), 2017; 36(5): 1054-1065.
Impact Factor: 6.131
View Export to BibTeX Export to EndNote
Monti S, Palma G, Borrelli P, Tedeschi E, Cocozza S, Salvatore M, Mancini M
* A multiparametric and multiscale approach to automated segmentation of brain veins (478 views) (PDF 260 views)
Proceedings Of Engineering In Medicine And Biology Society, 2015; N/D: 3041-3044.
Impact Factor: 0
View Export to BibTeX Export to EndNote
Monti S, Palma G, Tedeschi E, Cocozza S, Borrelli P, Salvatore M, Mancini M
* ENHANCED VESSELNESS MAPPING TO DETECT SMALL CEREBRAL VEINS ON SWI IMAGES (330 views)
Veins And Lymphatics (ISSN: 2279-7483), 2015; 4(s1): 16-17.
Impact Factor: 0
View Export to BibTeX Export to EndNote
Varrone A, Sjoholm N, Eriksson L, Gulyas B, Halldin C, Farde L
* Advancement in PET quantification using 3D-OP-OSEM point spread function reconstruction with the HRRT (605 views) (PDF 259 views)
Eur J Nucl Med (ISSN: 1619-7070, 1619-7089, 0340-6997), 2009 Oct; 36(10): 1639-1650.
Impact Factor: 4.531
View Export to BibTeX Export to EndNote
* MAVEN: An Algorithm for Multi-Parametric Automated Segmentation of Brain Veins from Gradient Echo Acquisitions (220 views) (PDF 188 views)
Ieee T Med Imaging (ISSN: 0278-0062), 2017; 36(5): 1054-1065.
Impact Factor: 6.131
View Export to BibTeX Export to EndNote
Monti S, Palma G, Borrelli P, Tedeschi E, Cocozza S, Salvatore M, Mancini M
* A multiparametric and multiscale approach to automated segmentation of brain veins (478 views) (PDF 260 views)
Proceedings Of Engineering In Medicine And Biology Society, 2015; N/D: 3041-3044.
Impact Factor: 0
View Export to BibTeX Export to EndNote
Monti S, Palma G, Tedeschi E, Cocozza S, Borrelli P, Salvatore M, Mancini M
* ENHANCED VESSELNESS MAPPING TO DETECT SMALL CEREBRAL VEINS ON SWI IMAGES (330 views)
Veins And Lymphatics (ISSN: 2279-7483), 2015; 4(s1): 16-17.
Impact Factor: 0
View Export to BibTeX Export to EndNote
Varrone A, Sjoholm N, Eriksson L, Gulyas B, Halldin C, Farde L
* Advancement in PET quantification using 3D-OP-OSEM point spread function reconstruction with the HRRT (605 views) (PDF 259 views)
Eur J Nucl Med (ISSN: 1619-7070, 1619-7089, 0340-6997), 2009 Oct; 36(10): 1639-1650.
Impact Factor: 4.531
View Export to BibTeX Export to EndNote
4 Records (3 excluding Abstracts).
Total impact factor: 10.662 (10.662 excluding Abstracts).
Total 5 year impact factor: 9.81 (9.81 excluding Abstracts).
Total impact factor: 10.662 (10.662 excluding Abstracts).
Total 5 year impact factor: 9.81 (9.81 excluding Abstracts).
408 views. Last view on Saturday 14 January 2023, 12:28:18
ibb.cnr.it
