Neural Regeneration Research ›› 2021, Vol. 16 ›› Issue (5): 830-835.doi: 10.4103/1673-5374.297085

Previous Articles     Next Articles

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

160

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