Temporal lobe epilepsy lateralisation and surgical outcome prediction using diffusion imaging

• Published in: Journal of neurology, neurosurgery and psychiatry Vol. 93; no. 6; pp. 599 - 608
• Main Authors: Johnson, Graham W., Cai, Leon Y., Narasimhan, Saramati, González, Hernán F. J., Wills, Kristin E., Morgan, Victoria L., Englot, Dario J.
• Format: Journal Article
• Language: English
• Published: England BMJ Publishing Group Ltd 01.06.2022; BMJ Publishing Group LTD
• Subjects: Artificial intelligence; Clinical decision making; Convulsions & seizures; Drug resistance; Electroencephalography; Epilepsy; epilepsy, surgery; Epilepsy, Temporal Lobe - diagnostic imaging; Epilepsy, Temporal Lobe - surgery; Female; Humans; image analysis; Localization; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; neurosurgery; Seizures; Surgery; Surgical outcomes; Tomography; Treatment Outcome; White Matter - pathology; neurosurgery; image analysis; epilepsy, surgery
• DOI: 10.1136/jnnp-2021-328185
• ISSN: 0022-3050; 1468-330X

ObjectiveWe sought to augment the presurgical workup of medically refractory temporal lobe epilepsy by creating a supervised machine learning technique that uses diffusion-weighted imaging to classify patient-specific seizure onset laterality and surgical outcome.Methods151 subjects were included in this analysis: 62 patients (aged 18–68 years, 36 women) and 89 healthy controls (aged 18–71 years, 47 women). We created a supervised machine learning technique that uses diffusion-weighted metrics to classify subject groups. Specifically, we sought to classify patients versus healthy controls, unilateral versus bilateral temporal lobe epilepsy, left versus right temporal lobe epilepsy and seizure-free versus not seizure-free surgical outcome. We then reduced the dimensionality of derived features with community detection for ease of interpretation.ResultsWe classified the subject groups in withheld testing data sets with a cross-fold average testing areas under the receiver operating characteristic curve of 0.745 for patients versus healthy controls, 1.000 for unilateral versus bilateral seizure onset, 0.662 for left versus right seizure onset, 0.800 for left-sided seizure-free vsersu not seizure-free surgical outcome and 0.775 for right-sided seizure-free versus not seizure-free surgical outcome.ConclusionsThis technique classifies important clinical decisions in the presurgical workup of temporal lobe epilepsy by generating discerning white-matter features. We believe that this work augments existing network connectivity findings in the field by further elucidating important white-matter pathology in temporal lobe epilepsy. We hope that this work contributes to recent efforts aimed at using diffusion imaging as an augmentation to the presurgical workup of this devastating neurological disorder.