Radiomics, machine learning, and deep learning for hippocampal sclerosis identification: a systematic review and diagnostic meta-analysis.
Authors
Affiliations (9)
Affiliations (9)
- Department of Medicine, State University of Maringa, Maringá, Paraná, Brazil. Electronic address: [email protected].
- Departament of Medicine, State University of Ponta Grossa, Ponta Grossa, Paraná, Brazil.
- Brazilian Institute of Capital Markets, São Paulo, São Paulo, Brazil.
- Department of Medicine, Albert Einstein Israeli Faculty of Health Sciences, São Paulo, São Paulo, Brazil.
- Department of Medicine, State University of Maringa, Maringá, Paraná, Brazil.
- Department of Medicine, Federal University of Triângulo Mineiro, Uberaba, Minas Gerais, Brazil.
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
- Department of Neurological Surgery, Rush University Medical Center, Illinois, Chicago, USA.
- Department of Neurosurgery, University of São Paulo, São Paulo, São Paulo, Brazil.
Abstract
Hippocampal sclerosis (HS) is the primary pathological finding in temporal lobe epilepsy (TLE) and a common cause of refractory seizures. Conventional diagnostic methods, such as EEG and MRI, have limitations. Artificial intelligence (AI) and radiomics, utilizing machine learning and deep learning, offer a non-invasive approach to enhance diagnostic accuracy. This study synthesized recent AI and radiomics research to improve HS detection in TLE. PubMed/Medline, Embase, and Web of Science were systematically searched following PRISMA-DTA guidelines until May 2024. Statistical analysis was conducted using STATA 14. A bivariate model was used to pool sensitivity (SEN) and specificity (SPE) for HS detection, with I2 assessing heterogeneity. Six studies were included. The pooled sensitivity and specificity of AI-based models for HS detection in medial temporal lobe epilepsy (MTLE) were 0.91 (95 % CI: 0.83-0.96; I2 = 71.48 %) and 0.9 (95 % CI: 0.83-0.94; I2 = 69.62 %), with an AUC of 0.96. AI alone showed higher sensitivity (0.92) and specificity (0.93) than AI combined with radiomics (sensitivity: 0.88; specificity: 0.9). Among algorithms, support vector machine (SVM) had the highest performance (SEN: 0.92; SPE: 0.95), followed by convolutional neural networks (CNN) and logistic regression (LR). AI models, particularly SVM, demonstrate high accuracy in detecting HS, with AI alone outperforming its combination with radiomics. These findings support the integration of AI into non-invasive diagnostic workflows, potentially enabling earlier detection and more personalized clinical decision-making in epilepsy care-ultimately contributing to improved patient outcomes and behavioral management.