Individualized statistical learning from medical image databases: Application to identification of brain lesions

• Published in: Medical image analysis Vol. 18; no. 3; pp. 542 - 554
• Main Authors: Erus, Guray, Zacharaki, Evangelia I., Davatzikos, Christos
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.04.2014
• Subjects: Abnormality segmentation; Algorithms; Artificial Intelligence; Brain - pathology; Brain Diseases - pathology; Brain MRI; Computer Simulation; Data Interpretation, Statistical; Databases, Factual; Diffusion Tensor Imaging - methods; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Models, Statistical; Multivariate Analysis; Nerve Fibers, Myelinated - pathology; Pattern Recognition, Automated - methods; PCA; Reproducibility of Results; Sensitivity and Specificity; Statistical learning; Brain MRI; Abnormality segmentation; Statistical learning; PCA
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2014.02.003

[Display omitted] •We present a multi-variate pattern analysis method for segmenting abnormalities.•The method aims to estimate the normal variation of the healthy anatomy.•And to segment abnormalities as deviations from the estimated normal.•An iterative sampling strategy is used to overcome the small sample size limitation.•A target specific feature selection is applied to further reduce the dimensionality. This paper presents a method for capturing statistical variation of normal imaging phenotypes, with emphasis on brain structure. The method aims to estimate the statistical variation of a normative set of images from healthy individuals, and identify abnormalities as deviations from normality. A direct estimation of the statistical variation of the entire volumetric image is challenged by the high-dimensionality of images relative to smaller sample sizes. To overcome this limitation, we iteratively sample a large number of lower dimensional subspaces that capture image characteristics ranging from fine and localized to coarser and more global. Within each subspace, a “target-specific” feature selection strategy is applied to further reduce the dimensionality, by considering only imaging characteristics present in a test subject’s images. Marginal probability density functions of selected features are estimated through PCA models, in conjunction with an “estimability” criterion that limits the dimensionality of estimated probability densities according to available sample size and underlying anatomy variation. A test sample is iteratively projected to the subspaces of these marginals as determined by PCA models, and its trajectory delineates potential abnormalities. The method is applied to segmentation of various brain lesion types, and to simulated data on which superiority of the iterative method over straight PCA is demonstrated.