Bayesian classification of multiple sclerosis lesions in longitudinal MRI using subtraction images.

Centre for Intelligent Machines, McGill University, Canada.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention 01/2010; 13(Pt 2):290-7. DOI: 10.1007/978-3-642-15745-5_36
Source: PubMed

ABSTRACT Accurate and precise identification of multiple sclerosis (MS) lesions in longitudinal MRI is important for monitoring disease progression and for assessing treatment effects. We present a probabilistic framework to automatically detect new, enlarging and resolving lesions in longitudinal scans of MS patients based on multimodal subtraction magnetic resonance (MR) images. Our Bayesian framework overcomes registration artifact by explicitly modeling the variability in the difference images, the tissue transitions, and the neighbourhood classes in the form of likelihoods, and by embedding a classification of a reference scan as a prior. Our method was evaluated on (a) a scan-rescan data set consisting of 3 MS patients and (b) a multicenter clinical data set consisting of 212 scans from 89 RRMS (relapsing-remitting MS) patients. The proposed method is shown to identify MS lesions in longitudinal MRI with a high degree of precision while remaining sensitive to lesion activity.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Intensity normalization is an important pre-processing step in the study and analysis of Magnetic Resonance Images (MRI) of human brains. As most parametric supervised automatic image segmentation and classification methods base their assumptions regarding the intensity distributions on a standardized intensity range, intensity normalization takes on a very significant role. One of the fast and accurate approaches proposed for intensity normalization is that of Nyul and colleagues. In this work, we present, for the first time, an extensive validation of this approach in real clinical domain where even after intensity inhomogeneity correction that accounts for scanner-specific artifacts, the MRI volumes can be affected from variations such as data heterogeneity resulting from multi-site multi-scanner acquisitions, the presence of multiple sclerosis (MS) lesions and the stage of disease progression in the brain. Using the distributional divergence criteria, we evaluate the effectiveness of the normalization in rendering, under the distributional assumptions of segmentation approaches, intensities that are more homogenous for the same tissue type while simultaneously resulting in better tissue type separation. We also demonstrate the advantage of the decile based piece-wise linear approach on the task of MS lesion segmentation against a linear normalization approach over three image segmentation algorithms: a standard Bayesian classifier, an outlier detection based approach and a Bayesian classifier with Markov Random Field (MRF) based post-processing. Finally, to demonstrate the independence of the effectiveness of normalization from the complexity of segmentation algorithm, we evaluate the Nyul method against the linear normalization on Bayesian algorithms of increasing complexity including a standard Bayesian classifier with Maximum Likelihood parameter estimation and a Bayesian classifier with integrated data priors, in addition to the above Bayesian classifier with MRF based post-processing to smooth the posteriors. In all relevant cases, the observed results are verified for statistical relevance using significance tests.
    Medical image analysis 04/2011; 15(2):267-82. · 3.09 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: PurposeTo propose and evaluate a new automated method for the identification of new/enlarging multiple sclerosis (MS) lesions on subtracted images (SI). The subtraction of serially acquired images has shown great potential in assessing new/enlarging brain magnetic resonance imaging (MRI) lesions in MS patients. However, this approach relies on the manual definition of lesions, which is labor-intensive and subject to operator-dependent variability.Materials and Methods An overestimated mask of candidate SI lesions was created and then these hyperintense voxel clusters were filtered using specific constraints for extent, shape, and intensity. The method was tested on normal and pathological MRI datasets.ResultsThe automated method did not detect hyperintense voxels on SI of healthy controls. SI lesions were identified manually and automatically in a multicenter MS dataset of 19 patients with paired MRI over 36 weeks. Sensitivity of the method was high (0.91) and in agreement with the results of manually defined SI lesions (Cohen's k = 0.82, 95% confidence interval [CI]: 0.77–0.87). On a second multicenter MS dataset of 103 patients with paired MRI over 76 weeks, the number of SI lesions detected automatically correlated with the number of gadolinium-enhancing lesions (r = 0.74).Conclusion The proposed method is robust, accurate, and sensitive and may be used with confidence in Phase II MS trials. J. Magn. Reson. Imaging 2014;39:1543–1549. © 2013 Wiley Periodicals, Inc.
    Journal of Magnetic Resonance Imaging 06/2014; 39(6). · 2.57 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: With the ever-increasing amount of anatomical information radiologists have to evaluate for routine diagnoses, computational support that facilitates more efficient education and clinical decision making is highly desired. Despite the rapid progress of image analysis technologies for magnetic resonance imaging of the human brain, these methods have not been widely adopted for clinical diagnoses. To bring computational support into the clinical arena, we need to understand the decision-making process employed by well-trained clinicians and develop tools to simulate that process. In this review, we discuss the potential of atlas-based clinical neuroinformatics, which consists of annotated databases of anatomical measurements grouped according to their morphometric phenotypes and coupled with the clinical informatics upon which their diagnostic groupings are based. As these are indexed via parametric representations, we can use image retrieval tools to search for phenotypes along with their clinical metadata. The review covers the current technology, preliminary data, and future directions of this field. Expected final online publication date for the Annual Review of Biomedical Engineering Volume 15 is July 11, 2013. Please see for revised estimates.
    Annual review of biomedical engineering 04/2013; · 11.24 Impact Factor

Full-text (2 Sources)

Available from
Jun 3, 2014