PulseAugur
LIVE 06:59:44
research · [2 sources] ·
0
research

AI framework integrates EEG and video for precise mouse seizure detection

Researchers have developed EEGVFusion, a novel multimodal framework designed to improve seizure detection in mouse models. This system integrates self-supervised EEG learning with spatio-temporal video encoding, utilizing optimal-transport alignment and bidirectional cross-attention to combine neural and behavioral data. The framework achieved a balanced accuracy of 0.9957 in random-session splits and 0.9718 in held-out-subject evaluations, significantly reducing false alarms while maintaining perfect event sensitivity. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Enhances preclinical epilepsy research by improving the accuracy and efficiency of seizure detection in animal models.

RANK_REASON This is a research paper detailing a new multimodal framework for seizure detection.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Tong Lu, Ke Xu, Zimo Zhang, Zitong Zhao, Danwei Weng, Ruiyu Wang, Miao Liu, Zizuo Zhang, Jingyi Yao, Yixuan Zhao, Wenchao Zhang, Min Wang, Guoming Luan, Minmin Luo, Zhifeng Yue ·

    A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection

    arXiv:2604.26379v1 Announce Type: new Abstract: Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is labor-intensive and single-modality systems fail for complementary reasons: video-b…

  2. arXiv cs.CV TIER_1 · Zhifeng Yue ·

    A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection

    Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is labor-intensive and single-modality systems fail for complementary reasons: video-based methods are easily confounded by benign beh…