Automatic Detection of Focal Cortical Dysplasia Using MRI: A Systematic Review

Abstract

Focal cortical dysplasia (FCD) is a congenital brain malformation that is closely associated with epilepsy. Early and accurate diagnosis is essential for effectively treating and managing FCD. Magnetic resonance imaging (MRI)-one of the most commonly used non-invasive neuroimaging methods for evaluating the structure of the brain-is often implemented along with automatic methods to diagnose FCD. In this review, we define three categories for FCD identification based on MRI: visual, semi-automatic, and fully automatic methods. By conducting a systematic review following the PRISMA statement, we identified 65 relevant papers that have contributed to our understanding of automatic FCD identification techniques. The results of this review present a comprehensive overview of the current state-of-the-art in the field of automatic FCD identification and highlight the progress made and challenges ahead in developing reliable, efficient methods for automatic FCD diagnosis using MRI images. Future developments in this area will most likely lead to the integration of these automatic identification tools into medical image-viewing software, providing neurologists and radiologists with enhanced diagnostic capabilities. Moreover, new MRI sequences and higher-field-strength scanners will offer improved resolution and anatomical detail for precise FCD characterization. This review summarizes the current state of automatic FCD identification, thereby contributing to a deeper understanding and the advancement of FCD diagnosis and management.

Keywords: deep learning; focal cortical dysplasia; image processing; machine learning; magnetic resonance imaging.

Figure 1

Example of one MRI image on axial view with a focal cortical dysplasia segmented by an expert. (a) MRI slice in axial view. (b) Mask or manual segmentation. (c) Manual segmentation on MRI.

Figure 2

Flowchart of the PRISMA protocol applied in this systematic review. It includes three main steps: (1) identifying studies in selected databases, (2) screening identified studies, and (3) reporting on included studies.

Figure 3

Distribution of FCD studies found with the PRISMA methodology.

Figure 4

General framework for FCD classification. The preprocessing step aims to enhance the image for manual or automatic identification of FCD. Furthermore, some studies lack the feature extraction step because the images can be used as features in deep learning approaches.