Automated hippocampal sclerosis detection, using AID-HS, shows robust performance across multi-centre paired 7T and 3T MRI
Year: 2026
Type: preprint
Abstract: Background Hippocampal sclerosis (HS) is a common cause of drug-resistant focal epilepsy (DRFE) and amenable to neurosurgical treatment. Detection relies on MRI but can be challenging. 7 Tesla (T) ultra-high field MRI and automated MRI post-processing tools have independently been shown to improve radiological diagnosis of HS. However, combining these approaches remains underexplored. This study evaluated whether AID-HS, a tool for HS detection developed using 3T MRI, generalises to 7T MRI data. Methods We collated a dataset of paired 3T and 7T T1-weighted MRI from four epilepsy centres, including 23 patients with HS, 39 healthy controls, and 23 individuals with focal cortical dysplasia as disease controls. Histopathology served as the gold standard for defining HS where available (n=7), otherwise radiological findings (n=16). AID-HS was applied to images acquired at both field strengths, and sensitivity and specificity for detection and lateralisation of HS were compared. Additionally, agreement of hippocampal features across 3T and 7T was evaluated. Results We found no evidence of a difference in performance of AID-HS between 3T and 7T. Sensitivity for detection of unilateral HS was 63% (12/19) at 3T and 68% (13/19) at 7T (McNemar’s exact test p=1.0). Specificity in controls was 97% (60/62) at 3T and 100% (62/62) at 7T (p=0.5). Bilateral HS was correctly flagged in 3 of 4 cases using feature-based criteria, with high specificity in controls. Quantitative hippocampal features showed moderate to good agreement across field strengths (ICC 0.70 to 0.98), with small differences observed for volume and thickness estimates. Conclusion AID-HS provides robust detection and lateralisation of HS across multiple 7T MRI centres, highlighting its potential to enhance lesion detection. Future work is needed to investigate whether models trained on 7T data can leverage the improved image quality for further gains in HS detection performance.
Source: medRxiv
Authors: Cornelius Kronlage, Mathilde Ripart, Rory J Piper, Martin M Tisdall, David W Carmichael, Torsten Baldeweg, John S Duncan, Jonathan O’Muircheartaigh, Maria H Eriksson, Chiara Casella, Philippa Bridgen, Tobias Bauer, Simon R Bouschery, Annalena Lange, Eberhard D Pracht, Tony Stöcker, Rainer Surges, Theodor Rüber, Krzysztof Klodowski, Christopher T Rodgers, Thomas E Cope, Konrad Wagstyl, Sophie Adler
Institutions: King's College London, University of Tübingen, University College London, Great Ormond Street Hospital, Great Ormond Street Hospital for Children NHS Foundation Trust, UCL Queen Square Institute of Neurology, Guy's and St Thomas' NHS Foundation Trust, University Hospital Bonn, University of Bonn, Bonn Aachen International Center for Information Technology, German Center for Neurodegenerative Diseases, University of Cambridge, Cambridge University Hospitals NHS Foundation Trust
Language: English
Subfield: Clinical Neurology
Field: Medicine
Domain: Health Sciences
Open Access status: green
Funders: South London and Maudsley NHS Foundation Trust, Wellcome Trust, National Institute for Health and Care Research, Department of Health and Social Care, Foulkes Foundation, King's College London, Deutsche Forschungsgemeinschaft, Cambridge University Hospitals, BMA Foundation for Medical Research, German Network for Bioinformatics Infrastructure, Medical Research Council, NIHR Cambridge Biomedical Research Centre
Awards: A new collaborative ultra-high field MRI facility for dementia and neuroscience research, MRC IAA 2021 University of Cambridge, G2493601830, G2537968379, G3256465746, G3724075105, Terra.X upgrade providing whole-brain clinically-approved 7T MRI for clinically impactful research, Transforming neurodevelopmental disorders using multi scale imaging and genomics, G4753630297, Parallel transmit 7T MRI to find epileptogenic lesions in patients with drug-resistant focal epilepsy, G6998158526, Transforming neurodevelopmental disorders using multi scale imaging and genomics, NeuroaCSis – Bonn Neuroscience Clinician Scientist Programm
OpenAlex ID: W7204757762