Surface-Based Texture and Morphological Analysis Detects Subtle Cortical Dysplasia

Abstract

Abstract. Focal cortical dysplasia (FCD), a malformation of cortical development, is an important cause of pharmacoresistant epilepsy. Small FCD lesions are difficult to distinguish from normal cortex and remain often overlooked on radiological MRI inspection. This paper presents a method to detect small FCD lesions on T1-MRI relying on surface-based features that model their textural and morphometric characteristics. The automatic detection was performed by a two step classification. First, a vertex-wise classifier based on a neural-network bagging trained on manual labels. Then, a cluster-wise classification designed to remove false positive clusters. The method was tested on 19 patients with small FCD. At the first classification step, 18/19 (95%) lesions were detected. The second classification step kept 13/19 (68%) lesions and decreased efficiently the amount of false positive. This new approach may assist the presurgical evaluation of patients with intractable epilepsy, especially those with unremarkable MRI findings.

Cortical feature analysis and machine learning improves detection of “MRI-negative” focal cortical dysplasia

“…Cortical surface-based methods have been combined in a multivariate approach with high accuracy in classifying small, visually subtle FCD lesions [17, 48]. Surface-based measures of cortical thickness, gray and white matter blurring, and sulcal depth contribute the most predictive weight in multivariate linear discriminant analyses, with cortical thickness offering the greatest specificity to the primary lesion [48].…”

MR Imaging Texture Analysis of the Corpus Callosum and Thalamus in Amnestic Mild Cognitive Impairment and Mild Alzheimer Disease

“…It has been applied to a large variety of pathologies, by using many different approaches. For example, Besson et al 13 used surface-based features extracted from brain T1 MR images to detect focal cortical dysplasia; Georgiadis et al 14 applied co-occurrence and run-length matrices features to the characterization of different types of brain tumors. McLaren et al 15 used morphologic, co-occurrence, and Laws texture parameters in MR images for breast cancer diagnosis; Rachidi et al 16 assessed osteoporosis through TA (among other tools).…”

Structural and Quantitative MRI in Epilepsy

“…Surfacebased methods have identifi ed that areas of focal cortical dysplasia can be preferentially located at the bottom of abnormally deep sulci (Besson, Andermann, Dubeau, & Bernasconi, 2008 ), a fi nding which may be used to direct the search for developmental abnormalities, particularly when MRI features are only mildly abnormal or absent. Uniquely, surface-based methods can characterize subtle surface features, such as cortical thickening, blurred gray-white matter boundary, and hyperintense T1 signal (Besson, Bernasconi, Colliot, Evans, & Bernasconi, 2008 ). These characteristic features, particularly in combination, can be used to detect subtle abnormalities that escape visual detection.…”