Machine learning approaches for imaging-based prognostication of the outcome of surgery for mesial temporal lobe epilepsy

Abstract

Objectives: Around 30% of patients undergoing surgical resection for drug-resistant mesial temporal lobe epilepsy (MTLE) do not obtain seizure freedom. Success of anterior temporal lobe resection (ATLR) critically depends on the careful selection of surgical candidates, aiming at optimizing seizure freedom while minimizing postoperative morbidity. Structural MRI and FDG-PET neuroimaging are routinely used in presurgical assessment and guide the decision to proceed to surgery. In this study, we evaluate the potential of machine learning techniques applied to standard presurgical MRI and PET imaging features to provide enhanced prognostic value relative to current practice.

Methods: Eighty two patients with drug resistant MTLE were scanned with FDG-PET pre-surgery and T1-weighted MRI pre- and postsurgery. From these images the following features of interest were derived: volume of temporal lobe (TL) hypometabolism, % of extratemporal hypometabolism, presence of contralateral TL hypometabolism, presence of hippocampal sclerosis, laterality of seizure onset volume of tissue resected and % of temporal lobe hypometabolism resected. These measures were used as predictor variables in logistic regression, support vector machines, random forests and artificial neural networks.

Results: In the study cohort, 24 of 82 (28.3%) who underwent an ATLR for drug-resistant MTLE did not achieve Engel Class I (i.e., free of disabling seizures) outcome at a minimum of 2 years of postoperative follow-up. We found that machine learning approaches were able to predict up to 73% of the 24 ATLR surgical patients who did not achieve a Class I outcome, at the expense of incorrect prediction for up to 31% of patients who did achieve a Class I outcome. Overall accuracies ranged from 70% to 80%, with an area under the receiver operating characteristic curve (AUC) of .75-.81. We additionally found that information regarding overall extent of both total and significantly hypometabolic tissue resected was crucial to predictive performance, with AUC dropping to .59-.62 using presurgical information alone. Incorporating the laterality of seizure onset and the choice of machine learning algorithm did not significantly change predictive performance.

Significance: Collectively, these results indicate that "acceptable" to "good" patient-specific prognostication for drug-resistant MTLE surgery is feasible with machine learning approaches utilizing commonly collected imaging modalities, but that information on the surgical resection region is critical for optimal prognostication.

Keywords: FDG-PET; epilepsy; machine learning; surgery.

FIGURE 1

Images for a patient who underwent a right anterior temporal lobe resection for drug‐resistant mesial temporal lobe epilepsy, who had contralateral mesial hypometabolism (in addition to the ipsilateral hypometabolism) on a preoperative fluorodeoxyglucose positron emission tomography (FDG‐PET), and who did not achieve seizure freedom at 2‐year follow up. (A) Preoperative magnetic resonance imaging (MRI). (B) postoperative MRI. (C) Subtraction of segmented preoperative and postoperative MRIs (red), used to calculate volume of tissue resected. (D) FDG‐PET coregistered to MRI. (E) Hypometabolism (green–blue) measured by comparison to 20 healthy controls. (F) Overlay of resection region with hypometabolism (shaded green–blue), used to calculate the percentage of temporal lobe hypometabolism resected

FIGURE 2

Classification performance for each machine learning algorithm: area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Colors indicate inputs to model (see legend). ANN, artificial neural network; LR, logistic regression; RF, random forest; SVM, support vector machine