arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2605.21852cs.CV

癫痫半相学套件（S3）：一个临床多模态数据集、基准和模型用于癫痫半相学理解

Seizure-Semiology-Suite (S3): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding

University of California, Los Angeles（加州大学洛杉矶分校）；University of Pittsburgh（匹兹堡大学）；Fudan University（复旦大学）；University of California, Riverside（加州大学河滨分校）；Hong Kong University of Science（香港科学大学）；Maharishi International University（玛希拉国际大学）
Lina Zhang, Tonmoy Monsoor, Peizheng Li, Jiarui Cui, Xinyi Peng, Chong Han, Prateik Sinha, Siyuan Dai, Jessica Nichole Pasqua, Colin M McCrimmon, Weiting Liu, H… 展开作者

Lina Zhang, Tonmoy Monsoor, Peizheng Li, Jiarui Cui, Xinyi Peng, Chong Han, Prateik Sinha, Siyuan Dai, Jessica Nichole Pasqua, Colin M McCrimmon, Weiting Liu, Hailey Marie Miranda, Bing Hu, Xiangting Wu, Tengyou Xu, Chunhan Li, Jiaye Tian, Jiarui Tang, Detao Ma, Lingye Kong, Junnan Lyu, Jungang Li, Yan Zan, Junhua Huang, Rajarshi Mazumder, Vwani Roychowdhury

备注：
Accepted to ICML 2026 as a Spotlight presentation
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出S3数据集和基准，用于细粒度、结构化的癫痫半相学理解，通过评估多模态大语言模型在低级视觉感知、时间序列处理、叙述报告生成和癫痫诊断中的能力，揭示了现有模型在左右脑推理、时间定位、症状序列和临床忠实报告方面的系统性弱点，并展示了针对癫痫的微调和双阶段神经符号框架在癫痫与非癫痫癫痫分类中的高F1分数。

摘要：

尽管多模态大语言模型（MLLMs）在一般视频理解方面表现出色，但其解释非自主、时空演变的病理运动行为如癫痫半相学的能力仍鲜有研究。为此，我们引入癫痫半相学套件（S3），一个临床导向的数据集和基准，用于细粒度、结构化的癫痫半相学理解。数据集包含438个癫痫视频，标注超过35,000个密集标签，涵盖20个ILAE定义的半相学特征。基于此数据集，我们提出了一个七任务分层基准，系统评估MLLMs从低级视觉感知到时间序列处理、叙述报告生成和癫痫诊断的能力。为进一步评估生成报告的临床意义，我们引入了癫痫半相学报告质量指数（Seizure-RQI）。在11个开放权重MLLMs上的广泛基线揭示了在左右脑推理、时间定位、症状序列和临床忠实报告方面的系统性弱点。我们展示，针对癫痫的微调显著提高了各任务的性能，而双阶段神经符号框架在癫痫与非癫痫癫痫分类中的F1分数达到0.96。S3数据集为评估多模态模型在安全关键医疗视频理解中的严谨基准，并指导开发临床可靠、领域适应的多模态智能。

英文摘要：

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in general video understanding, their capacity to interpret involuntary, and spatio-temporally evolving pathologic motor behaviors such as seizure semiology remains largely untested. To address this gap, we introduce Seizure-Semiology-Suite, a clinically grounded dataset and benchmark for fine-grained, structured seizure semiology understanding. The dataset includes 438 seizure videos annotated with over 35,000 dense labels covering 20 ILAE-defined semiological features. Building on this dataset, we propose a seven-task hierarchical benchmark that systematically evaluates MLLMs from low-level visual perception to temporal sequencing, narrative report generation, and seizure diagnosis. To enable clinically meaningful evaluation of generated reports, we further introduce the Report Quality Index for Seizure Semiology (Seizure-RQI). Extensive baselines across 11 open-weight MLLMs reveal systematic weaknesses in laterality reasoning, temporal localization, symptom sequencing, and clinically faithful reporting. We show that seizure-specific fine-tuning substantially improves performance across tasks, and that a two-stage neuro-symbolic framework achieves an F1 score of 0.96 on epileptic versus non-epileptic seizure classification. Seizure-Semiology-Suite establishes a rigorous benchmark for evaluating multimodal models in safety-critical medical video understanding and guides the development of clinically reliable, domain-adaptive multimodal intelligence.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑