Deep Learning provides exceptional accuracy to ECoG-based Functional Language Mapping for epilepsy surgery

Abstract

<jats:title>Abstract</jats:title><jats:p>The success of 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 in localizing the function of eloquent cortex through electrical stimulation of 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 safer alternative approach. However, ECoG-FM has a low success rate when compared to the ESM. In this study, we address this critical limitation by developing a new algorithm based on deep learning for ECoG-FM and thereby we achieve an accuracy comparable to ESM in identifying eloquent language cortex. In our experiments, with 11 epilepsy patients who underwent presurgical evaluation (through deep learning-based signal analysis on 637 electrodes), our proposed algorithm made an exceptional 23% improvement with respect to the conventional ECoG-FM analysis (∼60%). We obtained the state-of-the-art accuracy of 83.05% in identifying language regions, which has never been 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 likely hazards of the ESM in epilepsy surgery. Hence, reducing the potential for developing post-surgical morbidity in the language function.</jats:p>

Decoding Movement From Electrocorticographic Activity: A Review

“…Deep learning is rapidly gaining popularity as a BCI decoding method. In the last few years, deep learning algorithms have been applied to ECoG data processing (Roy et al, 2019), seizure forecasting (Meisel and Bailey, 2019), language mapping (RaviPrakash et al, 2018), and speech decoding (Livezey et al, 2018; Angrick et al, 2019a,b). Several studies have already employed deep learning for decoding movements from ECoG.…”

A Deep Learning Approach to Detecting Temporal Characteristics of Cortical Regions

“…In this study, we used a transformer-based model called TERA [23] known for its high accuracy in time-series analysis. While there are various analysis methods available for ECoG [24][25][26][27], our research employs this transformer-based model due to its proven 2/14 TERA acquires the latent features of waveform data in a self-supervised manner by reconstructing the original spectrogram through a one-to-one correspondence between the input data converted into a spectrogram and the data partially masked from the spectrogram. The following is the method used in this study to train TERA to acquire the latent space of ECoG and the corresponding feature vectors.…”

An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works

“…RaviPrakash et al (RaviPrakash et al, 2020) introduced an algorithm based on DL for Electrocorticography based functional mapping (ECoG-FM) for eloquent language cortex identification. ECoG-FM's success rate is low compared to Electro-cortical Stimulation Mapping (ESM).…”