Qin Yuzhen, Zhang Haowei, Qing Linbo, Liu Qinghua, Jiang Hua, Xu Shen, Liu Yixin, He Xiaohai
College of Electronics and Information Engineering, Sichuan University, Chengdu, China.
West China School of Medicine, Sichuan University, Chengdu, China.
Front Aging Neurosci. 2024 Jun 26;16:1341227. doi: 10.3389/fnagi.2024.1341227. eCollection 2024.
Early identification of cognitive impairment in older adults could reduce the burden of age-related disabilities. Gait parameters are associated with and predictive of cognitive decline. Although a variety of sensors and machine learning analysis methods have been used in cognitive studies, a deep optimized machine vision-based method for analyzing gait to identify cognitive decline is needed.
This study used a walking footage dataset of 158 adults named West China Hospital Elderly Gait, which was labelled by performance on the Short Portable Mental Status Questionnaire. We proposed a novel recognition network, Deep Optimized GaitPart (DO-GaitPart), based on silhouette and skeleton gait images. Three improvements were applied: short-term temporal template generator (STTG) in the template generation stage to decrease computational cost and minimize loss of temporal information; depth-wise spatial feature extractor (DSFE) to extract both global and local fine-grained spatial features from gait images; and multi-scale temporal aggregation (MTA), a temporal modeling method based on attention mechanism, to improve the distinguishability of gait patterns.
An ablation test showed that each component of DO-GaitPart was essential. DO-GaitPart excels in backpack walking scene on CASIA-B dataset, outperforming comparison methods, which were GaitSet, GaitPart, MT3D, 3D Local, TransGait, CSTL, GLN, GaitGL and SMPLGait on Gait3D dataset. The proposed machine vision gait feature identification method achieved a receiver operating characteristic/area under the curve (ROCAUC) of 0.876 (0.852-0.900) on the cognitive state classification task.
The proposed method performed well identifying cognitive decline from the gait video datasets, making it a prospective prototype tool in cognitive assessment.
早期识别老年人的认知障碍可减轻与年龄相关的残疾负担。步态参数与认知衰退相关且具有预测性。尽管在认知研究中已使用了多种传感器和机器学习分析方法，但仍需要一种基于深度优化的机器视觉方法来分析步态以识别认知衰退。
本研究使用了一个名为华西医院老年步态的158名成年人的步行视频数据集，该数据集根据简易便携式精神状态问卷的表现进行了标注。我们基于轮廓和骨架步态图像提出了一种新颖的识别网络，即深度优化步态部件（DO-GaitPart）。应用了三项改进：在模板生成阶段使用短期时间模板生成器（STTG）以降低计算成本并最小化时间信息的损失；深度空间特征提取器（DSFE）从步态图像中提取全局和局部细粒度空间特征；以及多尺度时间聚合（MTA），一种基于注意力机制的时间建模方法，以提高步态模式的可区分性。
消融测试表明DO-GaitPart的每个组件都是必不可少的。DO-GaitPart在CASIA-B数据集的背包行走场景中表现出色，优于比较方法，这些比较方法在Gait3D数据集上分别是GaitSet、GaitPart、MT3D、3D Local、TransGait、CSTL、GLN、GaitGL和SMPLGait。所提出的机器视觉步态特征识别方法在认知状态分类任务上的受试者工作特征曲线下面积（ROCAUC）为0.876（0.852 - 0.900）。
所提出的方法在从步态视频数据集中识别认知衰退方面表现良好，使其成为认知评估中有前景的原型工具。
