PulseAugur
实时 06:38:06
English(EN) DIVER-1: Scaling Intracranial EEG Foundation Models for Transferable Representations

新AI模型解码脑信号,提供医学和认知见解

研究人员开发了DIVER-1,一个用于颅内脑电图(iEEG)数据的大规模基础模型,能够处理可变的电极布局和记录条件。该模型在超过5310小时的iEEG数据上进行了预训练,并在认知解码和癫痫检测基准测试中表现出色。此外,一个名为NeuroFlowNet的新框架使用条件归一化流从非侵入性头皮脑电图中重建深部颞叶iEEG信号,解决了理解深部脑动力学方面的局限性。另外,还创建了一个脑到图像系统,可以从脑电图信号中解码视觉刺激,从而能够从脑电图中检索刺激图像,并重建与感知视觉一致的图像。 AI

影响 脑电图分析AI模型的进步为神经科学研究和临床诊断提供了新工具,有望增进对脑动力学的理解并辅助癫痫检测。

排序理由 多篇研究论文介绍了用于分析和重建脑电图数据中大脑活动的新型AI模型和方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Danny Dongyeop Han, Yonghyeon Gwon, Ahhyun Lucy Lee, Taeyang Lee, Seong Jin Lee, Jubin Choi, Sebin Lee, Jihyun Bang, Seungju Lee, David Keetae Park, Shinjae Yoo, Chun Kee Chung, Jiook Cha ·

    DIVER-1: Scaling Intracranial EEG Foundation Models for Transferable Representations

    arXiv:2512.19097v3 Announce Type: replace-cross Abstract: Intracranial EEG (iEEG) provides direct, millisecond-scale recordings of human neural activity, but reusable representation learning is difficult because electrode layouts, anatomical coverage, referencing schemes, and rec…

  2. arXiv cs.AI TIER_1 English(EN) · Dongyi He, Bin Jiang, Kecheng Feng, Luyin Zhang, Ling Liu, Yuxuan Li, Yun Zhao, He Yan ·

    Non-Invasive Reconstruction of Intracranial EEG Across the Deep Temporal Lobe from Scalp EEG based on Conditional Normalizing Flow

    arXiv:2603.03354v3 Announce Type: replace-cross Abstract: Although obtaining deep brain activity from non-invasive scalp electroencephalography (sEEG) is crucial for neuroscience and clinical diagnosis, directly generating high-fidelity intracranial electroencephalography (iEEG) …

  3. arXiv cs.CV TIER_1 English(EN) · Chi Kit Wong, Yan Liu, Haowen Yan ·

    Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment

    arXiv:2605.23996v1 Announce Type: new Abstract: We present a brain-to-image system that decodes visual stimuli from EEG signals recorded during natural image viewing. Our system addresses two tasks: (1) EEG-to-image retrieval, which ranks the correct stimulus image among 200 cand…