Multimodal neuroimaging: potential biomarkers for response to antiepileptic drugs?

Convolutional Neural Network Algorithm to Determine Lateralization of Seizure Onset in Patients With Epilepsy: A Proof-of-Principle Study

BACKGROUND AND OBJECTIVES

A new frontier in diagnostic radiology is the inclusion of machine-assisted support tools that facilitate the identification of subtle lesions often not visible to the human eye. Structural neuroimaging plays an essential role in the identification of lesions in patients with epilepsy, which often coincide with the seizure focus. In this study, we explored the potential for a convolutional neural network (CNN) to determine lateralization of seizure onset in patients with epilepsy using T1-weighted structural MRI scans as input.

METHODS

Using a dataset of 359 patients with temporal lobe epilepsy (TLE) from 7 surgical centers, we tested whether a CNN based on T1-weighted images could classify seizure laterality concordant with clinical team consensus. This CNN was compared with a randomized model (comparison with chance) and a hippocampal volume logistic regression (comparison with current clinically available measures). Furthermore, we leveraged a CNN feature visualization technique to identify regions used to classify patients.

RESULTS

Across 100 runs, the CNN model was concordant with clinician lateralization on average 78% (SD = 5.1%) of runs with the best-performing model achieving 89% concordance. The CNN outperformed the randomized model (average concordance of 51.7%) on 100% of runs with an average improvement of 26.2% and outperformed the hippocampal volume model (average concordance of 71.7%) on 85% of runs with an average improvement of 6.25%. Feature visualization maps revealed that in addition to the medial temporal lobe, regions in the lateral temporal lobe, cingulate, and precentral gyrus aided in classification.

DISCUSSION

These extratemporal lobe features underscore the importance of whole-brain models to highlight areas worthy of clinician scrutiny during temporal lobe epilepsy lateralization. This proof-of-concept study illustrates that a CNN applied to structural MRI data can visually aid clinician-led localization of epileptogenic zone and identify extrahippocampal regions that may require additional radiologic attention.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that in patients with drug-resistant unilateral temporal lobe epilepsy, a convolutional neural network algorithm derived from T1-weighted MRI can correctly classify seizure laterality.

Macroscale and microcircuit dissociation of focal and generalized human epilepsies

Thalamo-cortical pathology plays key roles in both generalized and focal epilepsies, but there is little work directly comparing these syndromes at the level of whole-brain mechanisms. Using multimodal imaging, connectomics, and computational simulations, we examined thalamo-cortical and cortico-cortical signatures and underlying microcircuits in 96 genetic generalized (GE) and 107 temporal lobe epilepsy (TLE) patients, along with 65 healthy controls. Structural and functional network profiling highlighted extensive atrophy, microstructural disruptions and decreased thalamo-cortical connectivity in TLE, while GE showed only subtle structural anomalies paralleled by enhanced thalamo-cortical connectivity. Connectome-informed biophysical simulations indicated modest increases in subcortical drive contributing to cortical dynamics in GE, while TLE presented with reduced subcortical drive and imbalanced excitation-inhibition within limbic and somatomotor microcircuits. Multiple sensitivity analyses supported robustness. Our multiscale analyses differentiate human focal and generalized epilepsy at the systems-level, showing paradoxically more severe microcircuit and macroscale imbalances in the former.