Yipeng Zhang

Objective: Developmental arrest or regression that results in intellectual disability (ID) is a common neurological sequela of infantile epileptic spasms syndrome. Spindles are the hallmark of non‐rapid eye movement sleep, and their density correlates with cognitive performance. Recent evidence suggests that ictal and interictal epileptic activities hijack the thalamocortical network. Therefore, we aimed to investigate whether thalamocortical dysfunction, as represented by reduced spindle density, is related to cognitive outcomes. Methods: We retrospectively recruited patients diagnosed with infantile epileptic spasms syndrome who were treated at Saitama Children's Hospital. Specifically, we included patients with an unknown etiology to minimize the effects of preceding thalamocortical dysfunction induced by various etiologies before the onset of infantile epileptic spasms syndrome. These cohorts were separated into two groups based on the presence or absence of ID, defined as an intelligence quotient (IQ) or developmental quotient (DQ) of <70, during follow‐up. Information concerning patients' background characteristics, treatment response (defined as seizure cessation for at least 3 months), and cognitive performance was extracted. Pre‐ and posttreatment spindle features were derived from quantitative assessment of spindle features performed using automated algorithms, which were validated against expert human annotations. Additionally, logistic regression was used to validate the independent predictors of cognitive outcomes. Results: Overall, 45 patients were included (23 and 22 patients in the ID and non‐ID groups, respectively). Posttreatment spindle density was significantly higher in the non‐ID group than in the ID group. Moreover, spindle density was positively correlated with DQ/IQ values across the entire cohort. Finally, a logistic regression model revealed that spindle density and treatment response were independent predictors of cognitive outcomes. Significance: Reduced posttreatment spindle density was correlated with cognitive outcome in infantile epileptic spasms syndrome. The thalamocortical network may be a potential treatment target to achieve favorable cognitive outcomes.

Surgical phase recognition (SPR) is essential for surgical workflow analysis and provides immediate guidance during procedures. Existing methods aggregate frame-level information into a global representation and treat the task as frame-wise classification. However, this pipeline lacks a feedback mechanism for integrating historical information into local temporal modeling. To address this limitation, we propose the Bidirectional Branch Query Network (B2Q-Net), which reformulates the SPR task as the bidirectional query between phase-level features and frame-level features. B2Q-Net incorporates historical information during the initialization of phase queries. This enables bidirectional information flow during iterative refinement of two-level feature maps between phases and frames. Furthermore, we introduce a dual-scale selector (DSS) to generate high-quality phase queries for the current video clip. These phase queries retrieve historical information from the proposed state space query (SSQ) module, which uses learnable tokens as the historical state space to preserve historical information. Extensive evaluations on three datasets demonstrate that B2Q-Net consistently outperforms state-of-the-art methods in recognition accuracy while achieving an inference speed of 106 fps. The B2Q-Net code is available at https://github.com/vsislab/B2Q-Net.

Objective: This study was undertaken to determine whether interictal high‐frequency oscillations (HFOs) and phase–amplitude coupling (PAC) can serve as spatial biomarkers on intracranial electroencephalography (iEEG) to guide responsive neurostimulation (RNS) targeting. Methods: We conducted a retrospective study of patients with drug‐resistant epilepsy who underwent iEEG monitoring and subsequent RNS implantation. Eligible participants had ≥60 min of slow‐wave sleep iEEG data and ≥6 months of post‐RNS follow‐up. Patients with simultaneous or subsequent resective surgery or exclusively thalamic RNS electrodes were excluded. Interictal HFOs and delta–HFO PAC (via modulation index [MI]) were calculated using open‐source tools (PyHFO, PACTv0.31). Weighted median distances from each iEEG electrode to the nearest RNS electrode were computed, adjusted by the proportion of HFO and MI. The primary outcome was ≥50% seizure reduction (good outcome group [G]) vs. p < .0001). ROC analysis indicated that distances within 20–30 mm between stimulation sites and peak biomarker locations were optimal (area under the curve > .70 for both HFOs and PAC), outperforming seizure onset zone (SOZ)‐based targeting. Exploratory analysis showed favorable outcomes for patients with thalamic electrodes stimulating areas of elevated HFO or MI. Significance: RNS electrode placement guided by interictal HFOs and delta–HFO PAC distribution may offer a feasible, effective alternative to conventional SOZ‐based approaches. These findings have immediate clinical relevance due to validated open‐source analytical tools, facilitating widespread implementation and prospective validation across multiple institutions.

Gait abnormalities constitute a primary motor symptom of Parkinson’s disease (PD). Clinically, the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) is widely recognized as the standard to evaluate gait impairment in PD. Recent skeleton-based methods have sought to estimate MDS-UPDRS gait scores, but most approaches treat score prediction as a coarse classification task, limiting their ability to capture subtle, progressive gait changes over time. These methods also often neglect clinical prior knowledge and fail to model localized gait features, leading to unsatisfactory performance. In addition, a continuous scale evaluation of gait impairment could result in a better formulation and adjustment of the treatment plan. In this paper, we introduce a novel framework for providing continuous-scale gait impairment estimation from the discrete annotation of MDS-UPDRS using skeleton data. First, we convert non-Euclidean skeleton information into two Euclidean spatiotemporal feature maps, ensuring a rigid spatial-temporal structure around the central joint. Next, we employ an omni-dimensional attention convolutional network to extract local spatiotemporal gait features within these normalized feature maps. We then integrate the features from both maps using an adaptive channel feature fusion module, capturing comprehensive gait information. Finally, we propose a numerical score prediction strategy that leverages MDS-UPDRS scores as anchors to predict gait impairment on a continuous scale without requiring continuous-scale annotations from clinicians. The effectiveness of the proposed approach is validated using a substantial clinical PD gait skeleton dataset.

Artificial intelligence (AI) is rapidly transforming our lives. Machine learning (ML) enables computers to learn from data and make decisions without explicit instructions. Deep learning (DL), a subset of ML, uses multiple layers of neural networks to recognize complex patterns in large datasets through end‐to‐end learning. DL has achieved remarkable success in challenging tasks such as facial recognition, self‐driving cars, and chatbots utilizing natural language processing. This progress extends to clinical practice and research in epilepsy. In this review, we provide an overview of AI applications in one of the most challenging yet crucial tasks in epilepsy: delineating the epileptogenic zone (EZ) using intracranial EEG. We discuss recent ML and DL real‐world workflows in EEG analysis, including preprocessing, training, evaluation, and interpretation. Then, we provide an overview of AI‐based approaches for EZ identification using interictal EEG, with a particular focus on high‐frequency oscillations. Lastly, we address the considerations and challenges that must be overcome to maximize the potential of AI‐based algorithms in EZ identification and biomarker discovery. We hope this review will foster discussions within the community on how to leverage AI to advance research and improve clinical practices in epilepsy.Plain Language Summary: AI has the potential to revolutionize epilepsy care by enhancing how clinicians pinpoint the brain regions responsible for seizures. This article highlights how AI can analyze interictal EEG (recorded between seizures) to detect subtle brain signals linked to epilepsy and to accurately define the epileptogenic zone. The AI‐based approach may lead to quicker diagnoses, more personalized treatments, and better surgical outcomes for patients with epilepsy.