中国神经再生研究(英文版)

中国神经再生研究(英文版) ›› 2021, Vol. 16 ›› Issue (5): 830-835.doi: 10.4103/1673-5374.297085

• 原著:脑损伤修复保护与再生 • 上一篇    下一篇

基于深度学习算法识别烟雾病并预测颅内出血风险：源自回顾性研究的数据

  


  • 出版日期:2021-05-15 发布日期:2020-12-29
  • 基金资助:

    中国国家自然科学基金（81801155，81771237；上海市科学技术创新行动计划新技术项目（18511102800）；上海市科技重大专项和之江实验室项目（2018SHZDZX01）；上海市卫计委项目（2017BR022）

Recognition of moyamoya disease and its hemorrhagic risk using deep learning algorithms: sourced from retrospective studies

Yu Lei1, Xin Zhang1, Wei Ni1, Heng Yang1, Jia-Bin Su1, Bin Xu1, Liang Chen1, Jin-Hua Yu2, Yu-Xiang Gu1, * , Ying Mao1, * #br#   

  1. 1 Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China;  2 Department of Electronic Engineering, Fudan University, Shanghai, China
  • Online:2021-05-15 Published:2020-12-29
  • Contact: Yu-Xiang Gu, MD, PhD, guyuxiang1972@126.com; Ying Mao, MD, PhD, maoying@fudan.edu.cn.
  • Supported by:
    This study was supported by the National Natural Science Foundation of China, Nos. 81801155 (to YL), 81771237 (to YXG); the New Technology Projects of Shanghai Science and Technology Innovation Action Plan, China, No. 18511102800 (to YXG); the Shanghai Municipal Science and Technology Major Project and ZJLab, China, No. 2018SHZDZX01 (to YM); and the Shanghai Health and Family Planning Commission, China, No. 2017BR022 (to YXG).

PDF

99

摘要：

烟雾病中的颅内出血可能反复发生，且很难预测。近年来深度学习算法的快速发展，为识别隐藏的危险因素、评估不同因素的权重、为定量评价风险提供了新思路。为探讨是否可利用卷积神经网络算法识别烟雾病及其出血的可能性，试验回顾性收集了460例成年烟雾病患者，含418 烟雾病和42烟雾病综合征，作为阳性样本进行诊断建模。另外选择500例具有正常血管外观的大脑半球作为阴性样品。试验首先以ResNet-152算法显示利用脑血管造影颈内动脉动态图像构建了烟雾血管自动识别模型，其准确度、灵敏度和特异度分别达到97.64±0.87%，96.55±3.44%和98.29±0.98%，其受试者工作特征曲线下面积达0.990。随后利用多视图卷积神经网络及决策树算法，将年龄、性别、血管危险因素与全脑血管造影动态图像相结合，构建出一种新型烟雾病出血风险预测模型，其准确度、灵敏度和特异度分别达到90.69±1.58%，94.12±2.75%和89.86±3.64%。试验提出的深度学习算法可辅助烟雾病的诊断并及时识别其再出血风险。试验于2015年1月12日经复旦大学华山医院伦理委员会批准，批准号2014-278。

https://orcid.org/0000-0002-4580-2205 (Yu-Xiang Gu); 

https://orcid.org/0000-0001-8055-115X (Ying Mao)

关键词: 中枢神经系统, 脑, 烟雾病, 烟雾综合征, 出血, 再出血, 诊断, 深度学习, 机器学习, 预测

Abstract: Although intracranial hemorrhage in moyamoya disease can occur repeatedly, predicting the disease is difficult. Deep learning algorithms developed in recent years provide a new angle for identifying hidden risk factors, evaluating the weight of different factors, and quantitatively evaluating the risk of intracranial hemorrhage in moyamoya disease. To investigate whether convolutional neural network algorithms can be used to recognize moyamoya disease and predict hemorrhagic episodes, we retrospectively selected 460 adult unilateral hemispheres with moyamoya vasculopathy as positive samples for diagnosis modeling, including 418 hemispheres with moyamoya disease and 42 hemispheres with moyamoya syndromes. Another 500 hemispheres with normal vessel appearance were selected as negative samples. We used deep residual neural network (ResNet-152) algorithms to extract features from raw data obtained from digital subtraction angiography of the internal carotid artery, then trained and validated the model. The accuracy, sensitivity, and specificity of the model in identifying unilateral moyamoya vasculopathy were 97.64 ± 0.87%, 96.55 ± 3.44%, and 98.29 ± 0.98%, respectively. The area under the receiver operating characteristic curve was 0.990. We used a combined multi-view conventional neural network algorithm to integrate age, sex, and hemorrhagic factors with features of the digital subtraction angiography. The accuracy of the model in predicting unilateral hemorrhagic risk was 90.69 ± 1.58% and the sensitivity and specificity were 94.12 ± 2.75% and 89.86 ± 3.64%, respectively. The deep learning algorithms we proposed were valuable and might assist in the automatic diagnosis of moyamoya disease and timely recognition of the risk for re-hemorrhage. This study was approved by the Institutional Review Board of Huashan Hospital, Fudan University, China (approved No. 2014-278) on January 12, 2015.

Key words: brain, central nervous system, deep learning, diagnosis, hemorrhage, machine learning, moyamoya disease, moyamoya syndrome, prediction, rebleeding