ECoG-based visual semantic decoding enables inference of semantic interpretation of visual perception from complex, noisy brain activity. This study examines the feasibility of visual semantic decoding using an end-to-end deep learning framework using electrocorticography (ECoG). Specifically, the decoding task is to predict visual categories from video stimuli using time-series neural inputs. A previously collected ECoG dataset from participants ($n=17$) with drug-resistant epilepsy is used for analysis. With fewer than 50 training samples per visual category, this study evaluates multiple deep learning approaches, artificial neural network architectures, and frequency-band filtered inputs. The best-performing approach is analyzed to shed light on the discriminative information it relies on across spectral, temporal, and cortical dimensions. The selected decoding system uses mixup augmentation, a Transformer-based encoder, and high-gamma (80-150 Hz) inputs with a 900 ms post-stimulus window. Further analysis shows that early visual cortex (V2-V4), ventral stream visual cortex, MT+ complex with neighbouring visual areas, and lateral temporal cortex contributed substantially to decoding performance. This study demonstrates that an end-to-end deep learning framework can yield promising decoding performance from dynamic visual stimuli without handcrafted features, while the model behavior remains interpretable through spectral, temporal, and cortical dimensions, which are broadly consistent with established neuroscience knowledge.
Stella Ho, Joel Villalobos, Joseph West et al.· 0 citations
Non-invasive brain stimulation techniques, such as transcranial electric stimulation (tES), are increasingly promoted as methods to enhance attention. However, their efficacy and optimal stimulation targets remain uncertain. We conducted a preregistered meta-analysis of randomized controlled trials in healthy adults (58 trials, 295 outcomes) examining the effects of tES on attentional functions (PROSPERO: CRD42023487035), complemented by a performance-electric field correlation (PEC) analysis to identify brain regions most strongly linked to tES-induced behavioral improvements. In general, tES produced a small but significant improvement in attentional functions compared to control conditions (standardized mean difference [SMD] = 0.24, 95% confidence interval [CI] = 0.12-0.36, I2 = 61%). Small but consistent benefits were observed in trials assessing attentional functions after stimulation (40 trials, SMD = 0.23, 95% CI = 0.12-0.33, I2 = 39%) and in trials applying anodal transcranial direct current stimulation (tDCS) targeting prefrontal regions (vs sham; 31 trials, SMD = 0.26, 95% CI = 0.12-0.39, I2 = 46%) with no evidence of publication bias or serious imprecision. The PEC analysis further revealed that tDCS-induced electric fields in the ventral subregion of the left dorsolateral prefrontal cortex (left vDLPFC) were most strongly associated with improvements in attentional functions following tDCS. Taken together, these findings suggest that tES may enhance attentional functions and the left vDLPFC may be a potential target for future tES studies aiming to improve attention.
Toru Takahashi, Ikko Kimura, S. Vafaei et al.· Biological Psychology· 0 citations
Using a portable EEG device with a low participant burden and a deep learning model to distinguish between the typical development group (TD) and the NDD group, comprising children with ASD, ADHD, and ASD + ADHD is used.