Texture Analysis: A Review of Neurologic MR Imaging Applications

Abstract

SUMMARY:Texture analysis describes a variety of image-analysis techniques that quantify the variation in surface intensity or patterns, including some that are imperceptible to the human visual system. Texture analysis may be particularly well-suited for lesion segmentation and characterization and for the longitudinal monitoring of disease or recovery. We begin this review by outlining the general procedure for performing texture analysis, identifying some potential pitfalls and strategies for avoiding them. We then provide an overview of some intriguing neuro-MR imaging applications of texture analysis, particularly in the characterization of brain tumors, prediction of seizures in epilepsy, and a host of applications to MS.ABBREVIATIONS: ABSV ϭ absolute gradient value; AIS ϭ acute ischemic stroke; ANN ϭ artificial neural network; CIS ϭ clinically isolated syndrome; d ϭ distance; DCE ϭ dynamic contrastenhanced; FCD ϭ focal cortical dysplasia; FLAIR ϭ fluid-attenuated inversion recovery; f x ϭ second-order gray-level co-occurrence feature number "x"; GLCM ϭ gray-level co-occurrence matrix; GM ϭ gray matter; HT ϭ hemorrhagic transformation; LDA ϭ linear discriminant analysis; MGL ϭ mean gray level; MGR ϭ mean gradient; MS ϭ multiple sclerosis; MTR ϭ magnetization transfer ratio; NAWM ϭ normal-appearing white matter; N g ϭ number of gray levels; PCA ϭ principal components analysis; PPMS ϭ primary-progressive MS; RLM ϭ run-length matrix; ROC ϭ receiver-operator characteristic; ROI ϭ region of interest; RRMS ϭ relapsing-remitting MS; rtPA ϭ recombinant tissue plasminogen activator; SPMS ϭ secondary-progressive MS; SVM ϭ support vector machine; ϭ direction; VGL ϭ variance of gray levels; VGR ϭ variance gradient; WM ϭ white matter

Grey-matter texture abnormalities and reduced hippocampal volume are distinguishing features of schizophrenia

“…This hypothesis about brain texture is motivated by a proof-of-principle study that showed measures of grey-matter heterogeneity distinguished patients with schizophrenia from controls and moreover were sensitive to the patients' genetic status (Ganeshan et al, 2010). Texture analysis (TA) of MR images lies within the domain of morphological surface measurement and provides a higher order means of assessing differences in cortical complexity (Kassner and Thornhill, 2010). TA enables the quantification of the grey-level pattern on MRI, via pixel inter-relations and spectral properties of the images (Kassner and Thornhill, 2010).…”

“…Texture analysis (TA) of MR images lies within the domain of morphological surface measurement and provides a higher order means of assessing differences in cortical complexity (Kassner and Thornhill, 2010). TA enables the quantification of the grey-level pattern on MRI, via pixel inter-relations and spectral properties of the images (Kassner and Thornhill, 2010). Advances in methodological approaches to brain-image analysis, such as automated algorithms and improved image processing (including segmentation procedures), have made TA more accessible and appealing as a research tool for neuropsychiatry (Kassner and Thornhill, 2010).…”

“…TA enables the quantification of the grey-level pattern on MRI, via pixel inter-relations and spectral properties of the images (Kassner and Thornhill, 2010). Advances in methodological approaches to brain-image analysis, such as automated algorithms and improved image processing (including segmentation procedures), have made TA more accessible and appealing as a research tool for neuropsychiatry (Kassner and Thornhill, 2010). TA has established utility when applied to neuropsychiatric disorders including epilepsy (de Oliviera et al, 2013), multiple sclerosis (Theocharkaris et al, 2009), attention deficit hyperactivity disorder (Chang et al, 2012) and Alzheimer disease (Zhang et al, 2012).…”

MRI texture analysis of femoral neck: Detection of exercise load‐associated differences in trabecular bone

“…In this study, we applied the MRI texture analysis based on co-occurrence matrix-derived parameters, which have been successfully applied for quantitative image analysis both in diagnosis and prediction of outcomes in several medical conditions (21)(22)(23). Hip fractures pose a serious public health problem (24), and bone structure undoubtedly accounts for hip fragility (1,2).…”

Hemorrhage detection in MRI brain images using images features

“…It is often used as a region descriptor. Texture analysis is a powerful tool in neuro-MR imaging for lesion segmentation and characterization, mainly when the lesions are indiscernible on the basis of standard T1 and T2 imaging [1]. A variety of computer-extracted features and classification schemes have been used to automatically discriminate between various brain traumas and injuries.…”