用预训练模型自动识别异常脑电图，效果优于传统深度学习方法。
Automatic detection of abnormal clinical EEG: comparison of a finetuned foundation model with two deep learning models
- 用微调的Foundation模型BioSerenity-E1对比CNN-LSTM与Transformer
- 在多中心数据集上最高达89.19%准确率，跨数据集验证仍超82%
- 适合医疗AI开发者或脑电分析研究者快速部署高效模型
脑电图（EEG）广泛用于神经系统疾病诊断。由于需要解读的脑电图数量庞大且专业性强，人工智能工具正被开发以辅助视觉分析。本文比较了两种深度学习模型（CNN-LSTM与基于Transformer的模型）与近期提出的Foundation模型BioSerenity-E1在分类完整脑电图是否正常任务上的表现。三个模型均在2,500条脑电图上训练或微调，并在两个私有数据集和一个公开数据集上评估：一个由单位专家标注的大规模多中心数据集（数据集A，n=4,480），一个小规模多中心数据集（数据集B，n=198，由三位专家标注），以及Temple University Abnormal (TUAB) EEG语料库评估数据集（n=276）。在数据集A上，三者平衡准确率均不低于86%，其中微调后的BioSerenity-E1达到最高89.19% [88.36–90.41]。在数据集B上，其平衡准确率为94.63% [92.32–98.12]。随后在未用于训练的TUAB评估数据集上验证，三者准确率均不低于76%，其中微调后的BioSerenity-E1达到82.25% [78.27–87.48]。结果表明，利用预训练模型可实现更鲁棒、高效的脑电图自动判读，减少资源消耗并提升泛化能力。
原文摘要 · Abstract (English)
Electroencephalography (EEG) is commonly used by physicians for the diagnosis of numerous neurological disorders. Due to the large volume of EEGs requiring interpretation and the specific expertise involved, artificial intelligence-based tools are being developed to assist in their visual analysis. In this paper, we compare two deep learning models (CNN-LSTM and Transformer-based) with BioSerenity-E1, a recently proposed foundation model, in the task of classifying entire EEG recordings as normal or abnormal. The three models were trained or finetuned on 2,500 EEG recordings and their performances were evaluated on two private and one public datasets: a large multicenter dataset annotated by a single specialist (dataset A composed of n = 4,480 recordings), a small multicenter dataset annotated by three specialists (dataset B, n = 198), and the Temple University Abnormal (TUAB) EEG corpus evaluation dataset (n = 276). On dataset A, the three models achieved at least 86% balanced accuracy, with BioSerenity-E1 finetuned achieving the highest balanced accuracy (89.19% [88.36-90.41]). BioSerenity-E1 finetuned also achieved the best performance on dataset B, with 94.63% [92.32-98.12] balanced accuracy. The models were then validated on TUAB evaluation dataset, whose corresponding training set was not used during training, where they achieved at least 76% accuracy. Specifically, BioSerenity-E1 finetuned outperformed the other two models, reaching an accuracy of 82.25% [78.27-87.48]. Our results highlight the usefulness of leveraging pre-trained models for automatic EEG classification: enabling robust and efficient interpretation of EEG data with fewer resources and broader applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。