Focal cortical dysplasia detection by artificial intelligence using MRI: A systematic review and meta-analysis.
Authors
Affiliations (9)
Affiliations (9)
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran; Interdisciplinary Neuroscience Research Program, Tehran University of Medical Sciences, Tehran, Iran.
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran; School of Medicine, Iran University of Medical Sciences, Tehran, Iran.
- Computer Science Department, Sharif University of Technology, Tehran, Iran.
- Student Research Committee, School of Medicine, Mazandaran University of Medical Sciences, Sari, Iran.
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran.
- Center for Neuroscience Research, Children's National Hospital, The George Washington University School of Medicine, Washington, DC, USA.
- Department of Neurosciences, University of California San Diego, La Jolla, CA, USA.
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran; Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran. Electronic address: [email protected].
Abstract
Focal cortical dysplasia (FCD) is a common cause of pharmacoresistant epilepsy. However, it can be challenging to detect FCD using MRI alone. This study aimed to review and analyze studies that used machine learning and artificial neural networks (ANN) methods as an additional tool to enhance MRI findings in FCD patients. A systematic search was conducted in four databases (Embase, PubMed, Scopus, and Web of Science). The quality of the studies was assessed using QUADAS-AI, and a bivariate random-effects model was used for analysis. The main outcome analyzed was the sensitivity and specificity of patient-wise outcomes. Heterogeneity among studies was assessed using I<sup>2</sup>. A total of 41 studies met the inclusion criteria, including 24 ANN-based studies and 17 machine learning studies. Meta-analysis of internal validation datasets showed a pooled sensitivity of 0.81 and specificity of 0.92 for AI-based models in detecting FCD lesions. Meta-analysis of external validation datasets yielded a pooled sensitivity of 0.73 and specificity of 0.66. There was moderate heterogeneity among studies in the external validation dataset, but no significant publication bias was found. Although there is an increasing number of machine learning and ANN-based models for FCD detection, their clinical applicability remains limited. Further refinement and optimization, along with longitudinal studies, are needed to ensure their integration into clinical practice. Addressing the identified limitations and intensifying research efforts will improve their relevance and reliability in real medical scenarios.