中国神经再生研究(英文版)

中国神经再生研究(英文版) ›› 2022, Vol. 17 ›› Issue (12): 2743-2749.doi: 10.4103/1673-5374.339493

• 原著:退行性病与再生 • 上一篇    下一篇

多种组织特异性磁共振成像模型诊断帕金森病：基于脑影像学的诊断研究

  

  • 出版日期:2022-12-15 发布日期:2022-05-05
  • 基金资助:
    国家自然科学基金项目（82001767，81971577，82171888）；浙江省自然科学基金项目（LQ21H180008，LQ20H180012）；中国博士后科研基金项目（2021T140599，2019M662082）；国家“十三五”重点研发计划项目（2016YFC1306600）

A multiple-tissue-specific magnetic resonance imaging model for diagnosing Parkinson’s disease: a brain radiomics study

Xiao-Jun Guan1, #, Tao Guo1, #, Cheng Zhou1, Ting Gao2, Jing-Jing Wu1, Victor Han3, Steven Cao3, Hong-Jiang Wei4, Yu-Yao Zhang5, Min Xuan1, Quan-Quan Gu1, Pei-Yu Huang1, Chun-Lei Liu3, 6, Jia-Li Pu2, Bao-Rong Zhang2, Feng Cui7, Xiao-Jun Xu1, *, Min-Ming Zhang1, *   

  1. 1Department of Radiology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang Province, China; 2Department of Neurology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang Province, China; 3Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA; 4Institute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China; 5School of Information Science and Technology, ShanghaiTech University, Shanghai, China; 6Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA; 7Department of Radiology, Hangzhou Hospital of Traditional Chinese Medicine, Hangzhou, Zhejiang Province, China
  • Online:2022-12-15 Published:2022-05-05
  • Contact: Min-Ming Zhang, MD, PhD, zhangminming@zju.edu.cn; Xiao-Jun Xu, MD, xxjmailbox@zju.edu.cn.
  • Supported by:
    This study was supported by the National Natural Science Foundation of China, Nos. 82001767 (to XJG), 81971577 (to MMZ), 82171888 (to XJX); the Natural Science Foundation of Zhejiang Province of China, Nos. LQ21H180008 (to XJG), LQ20H180012 (to MX); the China Postdoctoral Science Foundation, Nos. 2021T140599 (to XJG), 2019M662082 (to XJG) and the 13th Five-year Plan for National Key Research and Development Program of China, No. 2016YFC1306600 (to MMZ). 

PDF

204

摘要：

脑影像学能够反映潜在脑病理生理学的特征，但是在既往的帕金森病研究中T1加权、QSM和R2*图像的诊断价值被低估。为基于脑影像学信息建立帕金森病诊断模型，这项前瞻性诊断研究收集了2014 年 8 月至 2019 年 8 月招募的123例帕金森病患者和121例健康对照者的高分辨率T1加权成像、R2*成像及定量磁敏感成像数据，并从中提取了1408种脑影像学特征，应用数据驱动的特征选择来识别区分帕金森病和和正常对照的有意义的特征，构建了帕金森病诊断模型。该模型共含36种以黑质脑铁沉积为核心的脑影像组学标记物，主要为皮质下铁分布异常（尤其在黑质中）、结构紊乱（颞下回、中央旁回、楔前回、岛叶和中央前回）和皮质下纹理错位细胞核（尾状核、苍白球和丘脑）等，其诊断准确性达81.1±8.0%。进一步以含有帕金森病和对照者共106人的测试集进行模型验证，其结果显示该模型的准确性为78.5 ± 2.1%。同时在鉴别早期和未用药帕金森病患者时预测准确率分别为80.3±7.1%和79.1±6.5%，中晚期和进行药物治疗帕金森病患者的诊断准确率分别为80.4±6.3% 和 82.9±5.8%，震颤主导和非震颤主导帕金森病的预测准确度分别为79.8 ± 6.9%和79.1 ± 6.5%。综上这种基于多种组织特异性的磁共振成像构建的脑影像组学模型具有诊断帕金森病的能力。

https://orcid.org/0000-0003-2313-4477 (Xiao-Jun Guan); https://orcid.org/0000-0003-0145-7558 (Min-Ming Zhang); https://orcid.org/0000-0002-0127-2812 (Xiao-Jun Xu)

关键词: 帕金森病, 脑影像组学, 磁共振成像, 定量磁化率成像, R2*成像, T1加权成像, 神经影像学, 铁, 诊断, 影像学标记物

Abstract: Brain radiomics can reflect the characteristics of brain pathophysiology. However, the value of T1-weighted images, quantitative susceptibility mapping, and R2* mapping in the diagnosis of Parkinson’s disease (PD) was underestimated in previous studies. In this prospective study to establish a model for PD diagnosis based on brain imaging information, we collected high-resolution T1-weighted images, R2* mapping, and quantitative susceptibility imaging data from 171 patients with PD and 179 healthy controls recruited from August 2014 to August 2019. According to the inclusion time, 123 PD patients and 121 healthy controls were assigned to train the diagnostic model, while the remaining 106 subjects were assigned to the external validation dataset. We extracted 1408 radiomics features, and then used data-driven feature selection to identify informative features that were significant for discriminating patients with PD from normal controls on the training dataset. The informative features so identified were then used to construct a diagnostic model for PD. The constructed model contained 36 informative radiomics features, mainly representing abnormal subcortical iron distribution (especially in the substantia nigra), structural disorganization (e.g., in the inferior temporal, paracentral, precuneus, insula, and precentral gyri), and texture misalignment in the subcortical nuclei (e.g., caudate, globus pallidus, and thalamus). The predictive accuracy of the established model was 81.1 ± 8.0% in the training dataset. On the external validation dataset, the established model showed predictive accuracy of 78.5 ± 2.1%. In the tests of identifying early and drug-naïve PD patients from healthy controls, the accuracies of the model constructed on the same 36 informative features were 80.3 ± 7.1% and 79.1 ± 6.5%, respectively, while the accuracies were 80.4 ± 6.3% and 82.9 ± 5.8% for diagnosing middle-to-late PD and those receiving drug management, respectively. The accuracies for predicting tremor-dominant and non-tremor-dominant PD were 79.8 ± 6.9% and 79.1 ± 6.5%, respectively. In conclusion, the multiple-tissue-specific brain radiomics model constructed from magnetic resonance imaging has the ability to discriminate PD and exhibits the advantages for improving PD diagnosis. 

Key words: diagnosis, imaging biomarker, iron, magnetic resonance imaging, neuroimaging, Parkinson’s disease, quantitative susceptibility mapping, R2* mapping, radiomics, T1-weighted imaging