Magnetic Resonance Image Tissue Classification Using a Partial Volume Model

Shattuck, David W.; Sandor-Leahy, S.; Schaper, Kirt; Rottenberg, David A.; Leahy, Richard M.

doi:10.1006/nimg.2000.0730

Cited by 872 publications

(761 citation statements)

References 54 publications

Supporting

Mentioning

746

Contrasting

Unclassified

Order By: Relevance

“…The results are also compared against those obtained from an EM-like method, similar to Noe and Gee (2001), but with an advanced initialization technique. Furthermore, we compare our results with a fast PV estimation technique proposed by Shattuck et al (2001) and demonstrate that our technique can yield clear improvements in the accuracy of PV estimates without considerable loss in time efficiency. As a secondary contribution, we consider differences between material and sampling noise models for PVE also on a more theoretical level (cf.…”

Section: Introductionmentioning

confidence: 87%

“…In general, there are three approaches to the parameter estimation problem: histogram analysis (Santago and Gage, 1993), simultaneous parameter, and partial volume estimation by expectation maximization (EM)-like algorithms (Noe and Gee, 2001), and estimation based on a hard segmentation of the image (Shattuck et al, 2001). These three approaches, however, each have their drawbacks.…”

Section: Introductionmentioning

confidence: 99%

“…However, due to the PVE and classification errors in the hard labeling, each class in the hard segmented image contains a large number of outliers. This fact is taken into the account in Shattuck et al (2001), but their approach for the parameter estimation applies only to singlespectral images and assumes that each tissue type has a Gaussian noise distribution with the same variance. Also, since this method involves detecting modes of histograms, it is sensitive to noise and the estimates may not be unique.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast and robust parameter estimation for statistical partial volume models in brain MRI

2004

View full text Add to dashboard Cite

Due to the finite spatial resolution of imaging devices, a single voxel in a medical image may be composed of mixture of tissue types, an effect known as partial volume effect (PVE). Partial volume estimation, that is, the estimation of the amount of each tissue type within each voxel, has received considerable interest in recent years. Much of this work has been focused on the mixel model, a statistical model of PVE. We propose a novel trimmed minimum covariance determinant (TMCD) method for the estimation of the parameters of the mixel PVE model. In this method, each voxel is first labeled according to the most dominant tissue type. Voxels that are prone to PVE are removed from this labeled set, following which robust location estimators with high breakdown points are used to estimate the mean and the covariance of each tissue class. Comparisons between different methods for parameter estimation based on classified images as well as expectation -maximization-like (EM-like) procedure for simultaneous parameter and partial volume estimation are reported. The robust estimators based on a pruned classification as presented here are shown to perform well even if the initial classification is of poor quality. The results obtained are comparable to those obtained using the EM-like procedure, but require considerably less computation time. Segmentation results of real data based on partial volume estimation are also reported. In addition to considering the parameter estimation problem, we discuss differences between different approximations to the complete mixel model. In summary, the proposed TMCD method allows for the accurate, robust, and efficient estimation of partial volume model parameters, which is crucial to a variety of brain MRI data analysis procedures such as the accurate estimation of tissue volumes and the accurate delineation of the cortical surface. D 2004 Elsevier Inc. All rights reserved.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast and robust parameter estimation for statistical partial volume models in brain MRI

2004

View full text Add to dashboard Cite

show abstract

“…The number of methods proposed to address the brain segmentation problem reflects the importance of accurate and robust brain extraction. During the last 15 years, more than 20 brain extraction methods have been proposed using a variety of techniques, such as morphological operations (Goldszal et al, 1998;Lemieux et al, 1999;Mikheev et al, 2008;Park and Lee, 2009;Sandor and Leahy, 1997;Ward, 1999), atlas matching (Ashburner and Friston, 2000;Kapur et al, 1996), deformable surfaces (Dale et al, 1999;Smith, 2002), level sets (Baillard et al, 2001;Zhuang et al, 2006), histogram analysis (Shan et al, 2002), watershed (Hahn andPeitgen, 2000), graph cuts (Sadananthan et al, 2010), label fusion (Leung et al, 2011), and hybrid techniques (Carass et al, 2011;Iglesias et al, 2011;Rehm et al, 2004;Rex et al, 2004;Segonne et al, 2004;Shattuck et al, 2001). Studies evaluating these methods have found varying accuracy (Boesen et al, 2004;Fennema-Notestine et al, 2006;Hartley et al, 2006;Lee et al, 2003;Park and Lee, 2009;Shattuck et al, 2009).…”

mentioning

confidence: 99%

BEaST: Brain extraction based on nonlocal segmentation technique

et al. 2012

View full text Add to dashboard Cite

-Brain extraction is an important step in the analysis of brain images. The variability in brain morphology and the difference in intensity characteristics due to imaging sequences make the development of a general purpose brain extraction algorithm challenging. To address this issue, we propose a new robust method (BEaST) dedicated to produce consistent and accurate brain extraction. This method is based on nonlocal segmentation embedded in a multi-resolution framework. A library of 80 priors is semi-automatically constructed from the NIH-sponsored MRI study of normal brain development, the International Consortium for Brain Mapping, and the Alzheimer's Disease Neuroimaging Initiative databases.In testing, a mean Dice similarity coefficient of 0.9834±0.0053 was obtained when performing leave-one-out cross validation selecting only 20 priors from the library. Validation using the online Segmentation Validation Engine resulted in a top ranking position with a mean Dice coefficient of 0.9781±0.0047. Robustness of BEaST is demonstrated on all baseline ADNI data, resulting in a very low failure rate. The segmentation accuracy of the method is better than two widely used publicly available methods and recent state-of-the-art hybrid approaches. BEaST provides results comparable to a recent label fusion approach, while being 40 times faster and requiring a much smaller library of priors.Keywords: Brain extraction, skull stripping, patch-based segmentation, multi-resolution, MRI, BET ** Data used in the preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (www.loni.ucla.edu/ADNI). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. IntroductionBrain extraction (or skull stripping) is an important step in many neuroimaging analyses, such as registration, tissue classification, and segmentation. While methods such as the estimation of intensity normalization fields and registration do not require perfect brain masks, other methods such as measuring cortical thickness rely on very accurate brain extraction to work properly. For instance, failure to remove the dura may lead to an overestimation of cortical thickness (van der Kouwe et al., 2008), while removing part of the brain would lead to an underestimation. In cases of incorrect brain extraction, subjects may be excluded from further processing, a potentially expensive consequence for many studies. The solution of manually correcting the brain masks is a labour intensive and time-consuming task that is highly sensitive to inter-and intra-rater variability (Warfield et al., 2004).An accurate brain extraction method should exclude all tissues external to the brain, such as skull, dura, and eyes, without removing any part of the brain. The number of methods proposed to address the brain segmentation problem reflects the importance of accurate and robust brain extraction. During th...

show abstract

“…Each image volume was corrected for magnetic field inhomogeneities (Zijdenbos and Dawant, 1994) and reoriented into the standard position of the ICBM-305 average brain (Mazziotta et al, 1995) using a three-translation and three-rotation rigid-body transformation. Scalp-edited intracranial volumes (inter-rater reliability for scalp-editing procedures, rI=0.99) containing brain tissue and extra-cortical and subarachnoid CSF were separated into voxels most representative of gray matter, white matter and CSF using a partial volume correction method (Shattuck et al, 2001). …”

Section: Mri Proceduresmentioning

confidence: 99%

CSF sub-compartments in relation to plasma osmolality in healthy controls and in patients with first episode schizophrenia

Gunduz‐Bruce

Narr

Gueorguieva

et al. 2007

Psychiatry Research: Neuroimaging

View full text Add to dashboard Cite

Preliminary evidence suggests that plasma Na + level/osmolality may have effects on brain morphology; thus we investigated the link between plasma osmolality and ventricle size in healthy controls and patients with first episode schizophrenia. A total of 16 patients and 28 healthy controls were examined with magnetic resonance imaging (MRI) and gave blood samples. Highresolution 3D SPGR images were obtained on a 1.5 Tesla scanner. Scalp-edited MRI volumes were used for estimates of intracranial gray, white matter and CSF. Regional changes in CSF concentration and ventricular morphology were measured. The groups did not differ in plasma osmolality, but patients had higher plasma Na + . There were no differences in ventricle size. Controlling for plasma osmolality did not change the results. A mixed model procedure indicated a significant group effect and a significant osmolality by group interaction in ventricle measures. Healthy control group showed a significant relationship between osmolality and ventricle measures; this relationship was absent in the patients. Significant correlations between osmolality and lateral ventricle surface deformations were observed along the superior horn of the lateral ventricles in the healthy controls. These results suggest that plasma osmolality is related to ventricle size in healthy volunteers and that this physiological link is impaired in patients with first episode schizophrenia.

show abstract

Magnetic Resonance Image Tissue Classification Using a Partial Volume Model

Cited by 872 publications

References 54 publications

Fast and robust parameter estimation for statistical partial volume models in brain MRI

Fast and robust parameter estimation for statistical partial volume models in brain MRI

BEaST: Brain extraction based on nonlocal segmentation technique

CSF sub-compartments in relation to plasma osmolality in healthy controls and in patients with first episode schizophrenia

Contact Info

Product

Resources

About