Deep Learning provides exceptional accuracy to ECoG-based Functional Language Mapping for epilepsy surgery
Harish RaviPrakasha, Milena Korostenskaja, Eduardo M. Castilloc, Ki H. Leed, Christine M. Salinasd, James Baumgartnerd, Concetto Spampinatoe, Ulas Bagcia
Received Date: 22nd November 18
Successful surgical resection in epilepsy patients depends on preserving functionally critical brain regions while removing pathological tissues. Being the gold standard, Electro-cortical Stimulation Mapping (ESM) helps surgeons localize the function of eloquent cortex through electrical stimulation of the electrodes placed directly on the cortical brain surface. Due to the potential hazards of ESM, including increased risk of provoked seizures, Electrocorticography based Functional Mapping (ECOG-FM) was introduced as a safe alternative approach. However, ECoG-FM has a low success rate compared to the ESM. In this study, we address this critical limitation by developing a new deep learning algorithm for ECoG-FM with an accuracy comparable to the ESM when identifying eloquent language cortex. In our experiments with 11 epilepsy patients who underwent presurgical evaluation (through deep learning-based signal analysis on 637 electrodes), the proposed algorithm made an exceptional 34% improvement over the conventional ECoG-FM analysis, reaching the state-of-the-art accuracy of ~89% for identifying language regions, which was never achieved before. Our findings have demonstrated, for the first time, that deep learning powered ECoG-FM can serve as a stand-alone modality and avoid potential hazards of the ESM in epilepsy surgery.
Read in full at bioRxiv.
This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.