Recent advances in sMRI and artificial intelligence for presurgical planning in focal cortical dysplasia: A systematic review - 21/08/25
Highlights |
• | Enhanced Detection Accuracy: AI, particularly deep learning models, significantly improves FCD detection, achieving sensitivities up to 97.1 % and specificities up to 84.3 %, outperforming conventional MRI interpretation. |
• | Superior Performance in Type II FCD: Deep learning architectures (e.g., 3D CNNs) excel in detecting Type II FCD lesions, with sensitivity as high as 97.1 %, compared to lower sensitivity for Type I (47–68 %) and Type III (72–91 %) subtypes. |
• | Multimodal MRI Integration: Combining advanced MRI sequences (e.g., FLAIR, MP2RAGE) with AI enhances lesion conspicuity by 12–15 %, though scanner-dependent variability (1.5T vs. 3T) remains a challenge. |
• | Human-AI Collaboration: Hybrid frameworks combining AI pre-screening with radiologist validation boost detection rates by 18 %, bridging the gap between automated analysis and clinical expertise. |
• | Clinical and Technical Challenges: Suboptimal generalizability due to fragmented imaging protocols, underrepresented FCD subtypes in training data, and the "black box" nature of AI models underscore the need for standardized datasets and explainable algorithms. |
Abstract |
Background |
Focal Cortical Dysplasia (FCD) is a leading cause of drug-resistant epilepsy, particularly in children and young adults, necessitating precise presurgical planning. Traditional structural MRI often fails to detect subtle FCD lesions, especially in MRI-negative cases. Recent advancements in Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), have the potential to enhance FCD detection's sensitivity and specificity.
Methods |
This systematic review, following PRISMA guidelines, searched PubMed, Embase, Scopus, Web of Science, and Science Direct for articles published from 2020 onwards, using keywords related to “Focal Cortical Dysplasia,” “MRI,” and “Artificial Intelligence/Machine Learning/Deep Learning.” Included were original studies employing AI and structural MRI (sMRI) for FCD detection in humans, reporting quantitative performance metrics, and published in English. Data extraction was performed independently by two reviewers, with discrepancies resolved by a third.
Results |
The included studies demonstrated that AI significantly improved FCD detection, achieving sensitivity up to 97.1 % and specificities up to 84.3 % across various MRI sequences, including MPRAGE, MP2RAGE, and FLAIR. AI models, particularly deep learning models, matched or surpassed human radiologist performance, with combined AI-human expertise reaching up to 87 % detection rates. Among 88 full-text articles reviewed, 27 met inclusion criteria. The studies emphasized the importance of advanced MRI sequences and multimodal MRI for enhanced detection, though model performance varied with FCD type and training datasets.
Conclusion |
Recent advances in sMRI and AI, especially deep learning, offer substantial potential to improve FCD detection, leading to better presurgical planning and patient outcomes in drug-resistant epilepsy. These methods enable faster, more accurate, and automated FCD detection, potentially enhancing surgical decision-making. Further clinical validation and optimization of AI algorithms across diverse datasets are essential for broader clinical translation.
El texto completo de este artículo está disponible en PDF.Keywords : Focal Cortical Dysplasia, Structural MRI, Artificial Intelligence, Machine Learning, Deep Learning, Pre-surgical Planning, Epilepsy, Systematic Review
Abbreviations : AI, ANN, AUC, CNN, DL, DT, EEG, FCD, FLAIR, ILAE, ML, MP2RAGE, MPRAGE, MRI, MEG, MELD, Qmri, RoB, ROC, sMRI, SVM, T1WI, T2WI, VBM, XAI
Esquema
Vol 52 - N° 5
Artículo 101359- septembre 2025 Regresar al número
Artículo precedente
- Single-stent strategy for a dissected carotid loop in acute tandem occlusion: Technical considerations
- Jean Papaxanthos, Malgorzata Milnerowicz, Xavier Barreau, Omer Eker, Jerome Berge, Gaultier Marnat, Thomas Courret
- The Role of MRI as a key evaluator of mesenchymal stem Cell Therapy in Multiple Sclerosis: A systematic review and meta-analysis
- Mohammadreza Elhaie, Abolfazl Koozari, Mohammadhossein Mozafari, Iraj Abedi
Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
El acceso al texto completo de este artículo requiere una suscripción.
¿Ya suscrito a @@106933@@ revista ?