Department of Neurology, Neuroscience Center, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou 310016, China.
Department of Radiology, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou 310016, China.
Artif Intell Med. 2020 Mar;103:101794. doi: 10.1016/j.artmed.2020.101794. Epub 2020 Jan 7.
Deep learning has always been at the forefront of scientific research. It has also been applied to medical research. Hereditary spinocerebellar ataxia (SCA) is characterized by gait abnormalities and is usually evaluated semi-quantitatively by scales. However, more detailed gait characteristics of SCA and related objective methods have not yet been established. Therefore, the purpose of this study was to evaluate the gait characteristics of SCA patients, as well as to analyze the correlation between gait parameters, clinical scales, and imaging on deep learning.
Twenty SCA patients diagnosed by genetic detection were included in the study. Ten patients who were tested via functional magnetic resonance imaging (fMRI) were included in the SCA imaging subgroup. All SCA patients were evaluated with the International Cooperative Ataxia Rating Scale (ICARS) and Scale for the Assessment and Rating of Ataxia (SARA) clinical scales. The gait control group included 16 healthy subjects, and the imaging control group included seven healthy subjects. Gait data consisting of 10 m of free walking of each individual in the SCA group and the gait control group were detected by wearable gait-detection equipment. Stride length, stride time, velocity, supporting-phase percentage, and swinging-phase percentage were extracted as gait parameters. Cerebellar volume and the midsagittal cerebellar proportion in the posterior fossa (MRVD) were calculated according to MR.
There were significant differences in stride length, velocity, supporting-phase percentage, and swinging-phase percentage between the SCA group and the gait control group. The stride length and stride velocity of SCA groups were lower while supporting phase was longer than those of the gait control group. SCA group's velocity was negatively correlated with both the ICARS and SARA scores. The cerebellar volume and MRVD of the SCA imaging subgroup were significantly smaller than those of the imaging control group. MRVD was significantly correlated with ICARS and SARA scores, as well as stride velocity variability.
SCA gait parameters were characterized by a reduced stride length, slower walking velocity, and longer supporting phase. Additionally, a smaller cerebellar volume correlated with an increased irregularity in gait. Gait characteristics exhibited considerable clinical relevance to hereditary SCA. We conclude that a combination of gait parameters, ataxia scales, and MRVD may represent more objective markers for clinical evaluations of SCA.
深度学习一直处于科学研究的前沿。它也被应用于医学研究。遗传性小脑共济失调（SCA）的特征是步态异常，通常通过量表进行半定量评估。然而，SCA 的更详细步态特征以及相关的客观方法尚未建立。因此，本研究旨在评估 SCA 患者的步态特征，并分析步态参数、临床量表和深度学习成像之间的相关性。
本研究纳入了 20 名经基因检测诊断为 SCA 的患者。其中 10 名接受功能磁共振成像（fMRI）检测的患者被纳入 SCA 影像学亚组。所有 SCA 患者均接受国际合作共济失调评分量表（ICARS）和共济失调评估和评分量表（SARA）临床量表评估。步态对照组包括 16 名健康受试者，影像学对照组包括 7 名健康受试者。使用可穿戴步态检测设备检测 SCA 组和步态对照组中每位个体的 10m 自由行走步态数据。提取步长、步时、速度、支撑相百分比和摆动相百分比作为步态参数。根据磁共振成像（MRI）计算小脑体积和小脑后颅窝中矢状位比例（MRVD）。
SCA 组与步态对照组在步长、速度、支撑相百分比和摆动相百分比方面存在显著差异。SCA 组的步长和速度较低，而支撑相较长。SCA 组的速度与 ICARS 和 SARA 评分均呈负相关。SCA 影像学亚组的小脑体积和 MRVD 明显小于影像学对照组。MRVD 与 ICARS 和 SARA 评分以及步速变异性显著相关。
SCA 步态参数的特征是步长减小、行走速度减慢和支撑相延长。此外，小脑体积减小与步态不规则性增加相关。步态特征与遗传性 SCA 具有显著的临床相关性。我们得出结论，步态参数、共济失调量表和 MRVD 的结合可能代表 SCA 临床评估的更客观标志物。
