arXiv 2412.112862024-12-15cs.CVcs.AI

检测亨廷顿病舞蹈症中的日常步态：基于基础深度学习模型

Detecting Daily Living Gait Amid Huntington's Disease Chorea using a Foundation Deep Learning Model

Tel Aviv University（特拉维夫大学）；Tel Aviv Sourasky Medical Center（特拉维夫苏拉斯基医疗中心）；Teachers College, Columbia University（哥伦比亚大学教师学院）；Wayne State University（韦恩州立大学）；Stony Brook University（石溪大学）；Rush University Medical Center（拉什大学医学中心）

Dafna Schwartz, Lori Quinn, Nora E. Fritz, Lisa M. Muratori, Jeffery M. Hausdorff, Ran Gilad Bachrach

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对神经退行性疾病中不自主运动干扰步态检测的问题，提出基于U-Net的J-Net模型，利用自监督基础模型微调，在HD和PD数据上显著提升步态检测精度，且与临床评分相关。

摘要：

可穿戴传感器提供了一种非侵入性的方式来收集身体活动（PA）数据，其中步行是关键组成部分。现有模型通常难以检测患有神经退行性疾病（NDDs）且伴有不自主运动的个体的步态发作。我们开发了J-Net，一种受U-Net启发的深度学习模型，它使用预训练的自监督基础模型，并通过亨廷顿病（HD）的实验室数据进行微调，同时配以分割头用于步态检测。J-Net处理腕戴式加速度计数据以检测日常生活中的步态。我们在HD、帕金森病（PD）和对照组的实验室及日常生活数据上评估了J-Net。J-Net在HD上的ROC-AUC比现有方法提高了10个百分点，实验室数据达到0.97。在日常生活环境中，J-Net估计显示HD与对照组之间的每日步行时间中位数无显著差异（p=0.23），而其他模型则显示出反直觉的结果（p<0.005）。J-Net测量的步行时间与UHDRS-TMS临床严重程度评分相关（r=-0.52；p=0.02），证实了其临床相关性。在PD数据上微调J-Net也改善了步态检测效果，优于当前方法。J-Net的架构有效解决了严重舞蹈症中步态检测的挑战，并在日常生活中提供了稳健的性能。数据集和J-Net模型已公开可用，为NDD相关步态障碍的进一步研究提供了资源。

英文摘要：

Wearable sensors offer a non-invasive way to collect physical activity (PA) data, with walking as a key component. Existing models often struggle to detect gait bouts in individuals with neurodegenerative diseases (NDDs) involving involuntary movements. We developed J-Net, a deep learning model inspired by U-Net, which uses a pre-trained self-supervised foundation model fine-tuned with Huntington`s disease (HD) in-lab data and paired with a segmentation head for gait detection. J-Net processes wrist-worn accelerometer data to detect gait during daily living. We evaluated J-Net on in-lab and daily-living data from HD, Parkinson`s disease (PD), and controls. J-Net achieved a 10-percentage point improvement in ROC-AUC for HD over existing methods, reaching 0.97 for in-lab data. In daily-living environments, J-Net estimates showed no significant differences in median daily walking time between HD and controls (p = 0.23), in contrast to other models, which indicated counterintuitive results (p < 0.005). Walking time measured by J-Net correlated with the UHDRS-TMS clinical severity score (r=-0.52; p=0.02), confirming its clinical relevance. Fine-tuning J-Net on PD data also improved gait detection over current methods. J-Net`s architecture effectively addresses the challenges of gait detection in severe chorea and offers robust performance in daily living. The dataset and J-Net model are publicly available, providing a resource for further research into NDD-related gait impairments.

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。