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

By Jussi Tohka, Alex P. Zijdenbos, Alan C. Evans. NeuroImage, 2004

700 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/28d3dcfb803552d993466e7689ab32dfb4aa0c7f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

In Statistics and Probability

Citations in the corpus

Automated 3-D extraction and evaluation of the inner and outer cortical surfaces using a Laplacian map and partial volume effect classification (2005, methodology): “The approach taken here is an extension of a method we have previously presented (Tohka et al., 2004) which has been modified to improve segmentation in deep sulci and to differentiate between cortical and subcortical (SC) gray matter.”
An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple Sclerosis (2012, methodology): “This segmentation procedure is further refined by accounting for partial volume effects (Tohka et al., 2004), by applying adaptive maximum a posteriori estimations (Rajapakse et al., 1997), and by applying hidden Markov random field (MRF) model (Rajapakse et al., 1997) as proposed recently (Lüders…”
Generalized Overlap Measures for Evaluation and Validation in Medical Image Analysis (2006, methodology): “Examples include the use of multi-spectral analysis [16] and statistical models of partial volume estimation [17]–[22].”
The NIH MRI study of normal brain development (2006, neutral): “Problems with surface extraction arise due to the mixing of signal from different tissue types in single MRI voxels, i.e., the partial volume effect (Tohka et al., 2004).”
CAT: a computational anatomy toolbox for the analysis of structural MRI data (2024, methodology): “The AMAP segmentation also includes a partial volume estimation [ 18 ].”
Cortical thickness and central surface estimation (2013, positive): “The probability tissue maps 196 CSF, GM, and WM are combined in one probability image SEG 197 (Tohka et al., 2004).”
Multi-Method Analysis of MRI Images in Early Diagnostics of Alzheimer's Disease (2011, methodology): “Tissues were segmented into white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) using the INSECT-algorithm [42] and the magnitude of PVE was estimated by using the trimmed minimum covariance determinant (TMCD) method [43].”
volBrain: An Online MRI Brain Volumetry System (2015, background): “For this reason some authors used the concept of partial volume coeﬃcients (PVC) to represent the actual amount of every tissue within each voxel (Tohka et al., 2004; Manjón et al., 2010a).”
Developmental changes in endogenous testosterone have sexually‐dimorphic effects on spontaneous cortical dynamics (2023, methodology): “Finally, preprocessed images were segmented based on an adaptive maximum a posteriori technique (Ashburner & Friston, 2005) and a partial volume estimation with a simplified mixed model of a maximum of two tissue types (Tohka et al., 2004).”