The paper was submitted and accepted for publication in 2015, but published in january 2016 in NeuroImage, IF= 6.357, RX - neuroimaging ; 1/14. Accurate characterization of white-matter lesions from magnetic resonance (MR) images has increasing importance for diagnosis and management of treatment of certain neurological diseases, and can be performed in an objective and effective way by automated lesion segmentation. This usually involves modeling the whole-brain MR intensity distribution, however, capturing various sources of MR intensity variability and lesion heterogeneity results in highly complex whole-brain MR intensity models, thus their robust estimation on a large set of MR images presents a huge challenge. We propose a novel approach employing stratified mixture modeling, where the main premise is that the otherwise complex whole-brain model can be reduced to a tractable parametric form in small brain subregions. We show on MR images of multiple sclerosis (MS) patients with different lesion loads that robust estimators enable accurate mixture modeling of MR intensity in small brain subregions even in the presence of lesions. Recombination of the mixture models across strata provided an accurate whole-brain MR intensity model. Increasing the number of subregions and, thereby, the model complexity, consistently improved the accuracy of whole-brain MR intensity modeling and segmentation of normal structures. The proposed approach was incorporated into three unsupervised lesion segmentation methods and, compared to original and three other state-of-the-art methods, the proposed modeling approach significantly improved lesion segmentation according to increased Dice similarity indices and lower number of false positives on real MR images of 30 patients with MS.
COBISS.SI-ID: 11198292
Mixture models are often used to compactly represent samples from heterogeneous sources. However, in real world, the samples generally contain an unknown fraction of outliers and the sources generate different or unbalanced numbers of observations. Such unbalanced and contaminated samples may, for instance, be obtained by high density data sensors such as imaging devices. Estimation of unbalanced mixture models from samples with outliers requires robust estimation methods. In this paper, we propose a novel robust mixture estimator incorporating trimming of the outliers based on component-wise confidence level ordering of observations. The proposed method is validated and compared to the state-of-the-art FAST-TLE method on two data sets, one consisting of synthetic samples with a varying fraction of outliers and a varying balance between mixture weights, while the other data set contained structural magnetic resonance images of the brain with tumors of varying volumes. The results on both data sets clearly indicate that the proposed method is capable to robustly estimate unbalanced mixtures over a broad range of outlier fractions. As such, it is applicable to real-world samples, in which the outlier fraction cannot be estimated in advance.
COBISS.SI-ID: 10969940
White-matter brain lesions are associated to several diseases, which can be characterized with neuroimaging biomarkers through MR image analysis. This generally requires highly accurate segmentation of the lesions. We present a novel method for lesion segmentation consisting of unsupervised extraction of candidate lesion voxels, based on which a supervised random decision forest classifier learns a set of low-level MR intensity features to perform accurate classification of lesion candidates. The intensities from proximal neighborhoods of lesion candidate voxels are used as features for classification. The pruned set of candidate lesion voxels enables the supervised method to learn highly discriminating decision rules during the training phase based on simple visual features, which present no computational overhead and are easy to extract from the MR images. The obtained median Dice similarity of 0.73, sensitivity of 0.90 and positive predictive value of 0.61 on 18 patients with multiple sclerosis indicate a good segmentation of white-matter lesions.
COBISS.SI-ID: 11182420