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
A certain quantity can usually be measured by several different measurement methods. For instance, in medical image analysis, there may be different image segmentation methods to delineate and measure the volume of a certain structure, but the true value may still be uknown or accessible using a more costly or even destructive method. Herein, we propose a novel computational framework that automatically determines the most accurate and precise method of measurement of a certain quantity, when there is no access to the true value of the measurand. The accuracy of each measurement method is characterized by systematic error (bias), which is modeled with polynomials in true values of measurand, and the precision as random error modeled with a Gaussian random variable. In contrast to previous works the random errors are modeled jointly across all methods, thereby enabling the framework to analyze measurement methods based on similar principles, which may have correlated random errors. Furthermore, the posterior distribution of the error model parameters is estimated from samples obtained by Markov chain Monte-Carlo and analyzed to estimate the parameter values and the unknown true values of the measurand. The framework was validated on a dataset containing measurements of total lesion load, a biomarker of neurodegenerative diseases, which was obtained with four automatic methods by analyzing brain magnetic resonance images. The obtained estimates of bias and random error, and true value estimates, were in a good agreement with the corresponding least squares regression estimates against a reference consensus-based measurements.
COBISS.SI-ID: 11948116
Quantified volume and count of white-matter lesions based on magnetic resonance (MR) images are important biomarkers in several neurodegenerative diseases. For a routine extraction of these biomarkers an accurate and reliable automated lesion segmentation is required. A standard segmentation method can only be objectively determined if validation MR datasets are publicly available in conjunction with standardized evaluation methodology. We thus devised a novel MR dataset of 30 multiple sclerosis patients and a novel protocol for creating reference white-matter lesion segmentations based on multi-rater consensus. On these datasets three expert raters individually segmented white-matter lesions, using in-house developed semi-automated lesion contouring tools. Later, the raters revised the segmentations in several joint sessions to reach a consensus on segmentation of lesions. The proposed protocol was verified by assessing intra-consensus variability, which was substantially lower compared to the intra- and inter-rater variabilities observed and reported in previous research. Hence, the obtained reference segmentations may represent a more precise target to evaluate, compare against and also train, the automatic segmentations. To encourage further use and research the developed tools and protocols, and the original and preprocessed MR image datasets and the consensus lesion segmentations were made publicly available at http://lit.fe.uni-lj.si/tools.
COBISS.SI-ID: 11896404
Quantifying changes of white-matter lesions (WMLs) from magnetic resonance (MR) images can be used to predict the progression of neurodegenerative diseases like multiple sclerosis (MS). The need for accurate and reliable WML change quantification led to the development of several automated MR image analysis methods, however, an objective comparison of the methods is difficult without publicly available validation datasets with ground truth WML changes. In this study, we acquired longitudinal MR datasets of 20 MS patients, in which brain regions were extracted, spatially aligned and intensity normalized. Two expert raters then delineated and jointly revised the WML changes on subtracted baseline and follow-up MR images to obtain ground truth WML segmentations. The main contribution are an objective, quantitative and systematic evaluation of two unsupervised and one supervised intensity based change detection method and the datasets with ground truth segmentations made publicly available.
COBISS.SI-ID: 11449428