基于深度学习算法和CT影像构建自发性脑出血早期神经功能恶化的智能预估系统

doi:10.3760/cma.j.cn441417-20250326-22010

国际医药卫生导报 ›› 2025, Vol. 31 ›› Issue (22): 3747-3751.DOI: 10.3760/cma.j.cn441417-20250326-22010

基于深度学习算法和CT影像构建自发性脑出血早期神经功能恶化的智能预估系统

赵英俊¹ 陈霄² 任小军¹ 关荣¹ 罗婷¹ 李妮¹ 常正伟¹

¹西安中医脑病医院医学影像中心，西安 710032；²西安中医脑病医院脑病九科，西安 710032

收稿日期:2025-03-26 出版日期:2025-11-01 发布日期:2025-11-19
通讯作者: 常正伟，Email：changzhengwei000@163.com
基金资助:
陕西省高水平中医药重点学科建设项目（SX2YY2DXK-2021008）

Constructing an intelligent prediction system for early neurological function deterioration in spontaneous cerebral hemorrhage based on deep learning algorithms and CT images

Zhao Yingjun¹, Chen Xiao², Ren Xiaojun¹, Guan Rong¹, Luo Ting¹, Li Ni¹, Chang Zhengwei¹

¹Department of Medical Imaging Center, Xi'an TCM Hospital of Encephalopathy, Xi'an 710032, China; ²NinthDepartment of Brain Diseases, Xi'an TCM Hospital of Encephalopathy, Xi'an 710032, China

Received:2025-03-26 Online:2025-11-01 Published:2025-11-19
Contact: Chang Zhengwei, Email: changzhengwei000@163.com
Supported by:
Shaanxi Province High Level Key Discipline Construction Project of Traditional Chinese Medicine (SX2YY2DXK-2021008)

摘要/Abstract

摘要： 目的　基于深度学习算法和计算机断层扫描（CT）影像构建自发性脑出血（SICH）患者早期神经功能恶化（END）的智能预估系统。方法　回顾性分析，收集2022年1月至2024年10月于西安中医脑病医院进行治疗的369例SICH患者临床资料，入院后均行CT平扫，按照2∶1比例将患者随机分为试验集（246例，采用五折交叉验证分5个子集）和验证集（123例）。试验集男135例、女111例，年龄（56.79±8.82）岁；验证集男70例、女53例，年龄（57.85±9.12）岁。基于深度学习算法和试验集CT影像资料构建SICH患者END的智能预估系统，利用验证集分析该智能预估系统的诊断效能。结果　SICH患者END发生率为21.14%（78/369），其中试验集246例患者中END发生51例，验证集123例患者中END发生27例。试验集五折交叉验证的模型平均灵敏度、特异度、准确度分别为96.18%、97.44%、97.16%；经验证集测评，基于深度学习算法和CT影像构建SICH患者END的智能预估系统预测灵敏度、特异度及准确度分别为96.30%、97.92%、97.56%，且与END实际发生情况的一致性较高（Kappa=0.930，P<0.001）。结论　基于深度学习算法和CT影像构建SICH患者END的智能预估系统对END具有较好的诊断效能，有一定的临床推广意义。

关键词: 计算机断层扫描, 深度学习算法, 自发性脑出血, 早期神经功能恶化, 智能系统

Abstract: Objective　To construct an intelligent prediction system for early neurological function deterioration (END) in patients with spontaneous intracerebral hemorrhage (SICH) based on deep learning algorithms and computed tomography (CT) images. Methods　The clinical data of 369 patients with SICH who were treated in Xi 'an Encephalopathy Hospital of Traditional Chinese Medicine from January 2022 to October 2024 were retrospectively analyzed. All the patients underwent CT plain scan after admission. According to the ratio of 2:1, the patients were randomly divided into an experimental set (246 cases, 5 subsets by five-fold cross-validation) and a validation set (123 cases). There were 135 males and 111 females in the evperimental set, aged (56.79±8.82) years. There were 70 males and 53 females in the validation set, aged (57.85±9.12) years. The intelligent prediction system for END in the SICH patient was constructed based on deep learning algorithms and experimental CT image data, and the diagnostic performance of the intelligent prediction system was analyzed by the validation set. Results　The incidence rate of END in the SICH patients was 21.14% (78/369), with 51 cases occurring in the experimental group of 246 patients, and 27 cases occurring in the validation group of 123 patients. The average sensitivity, specificity, and accuracy of the model validated by 5-fold cross validation in the experimental set were 96.18%, 97.44%, and 97.16% respectively. According to the validation set evaluation, the diagnostic sensitivity, specificity, and accuracy of the intelligent prediction system for END in the SICH patient based on deep learning algorithms and CT images were 96.30%, 97.92%, and 97.56%, respectively, and the consistency with the actual occurrence of END was high (Kappa=0.930, P<0.001). Conclusion　The intelligent prediction system for END of SICH patients based on deep learning algorithms and CT images has good diagnostic performance for END, and it has a certain clinical promotion significance.

Key words: Computed tomography imaging, Deep learning algorithms, Spontaneous cerebral hemorrhage, Early deterioration of neurological function, Intelligent system

赵英俊陈霄任小军关荣罗婷李妮常正伟. 基于深度学习算法和CT影像构建自发性脑出血早期神经功能恶化的智能预估系统[J]. 国际医药卫生导报, 2025, 31(22): 3747-3751.

Zhao Yingjun, Chen Xiao, Ren Xiaojun, Guan Rong, Luo Ting, Li Ni, Chang Zhengwei. Constructing an intelligent prediction system for early neurological function deterioration in spontaneous cerebral hemorrhage based on deep learning algorithms and CT images[J]. International Medicine and Health Guidance News, 2025, 31(22): 3747-3751.

参考文献

[1] Sterba A, Sedova P, Brown RD, et al. Predictors of spontaneous intracerebral hemorrhage mortality: a community-based study in Brno, Czech Republic[J].Acta Neurol Belg,2024,124(6):1945-1958.DOI:10.1007/s13760-024-02612-y.
[2] Amer HA, El-Jaafary SIM, Sadek HMAE, et al. Clinical and paraclinical predictors of early neurological deterioration and poor outcome in spontaneous intracerebral hemorrhage[J]. Egypt J Neurol Psychiatr Neurosurg, 2023,59(1):74. DOI: 10.1186/s41983-023-00675-x.
[3] Lin K, Gao C, Lin Z, et al. Characteristics, predictors and outcomes of early postoperative cerebral infarction on computed tomography in spontaneous intracerebral hemorrhage[J]. Sci Rep, 2024, 14(1):19526. DOI: 10.1038/s41598-024-69571-5.
[4] Harrison P, Hasan R, Park K. State-of-the-art of breast cancer diagnosis in medical images via convolutional neural networks (CNNs)[J]. J Healthc Inform Res, 2023, 7(4):387-432. DOI: 10.1007/s41666-023-00144-3.
[5] Tanioka S, Aydin OU, Hilbert A, et al. Prediction of hematoma expansion in spontaneous intracerebral hemorrhage using a multimodal neural network[J]. Sci Rep, 2024, 14(1):16465. DOI: 10.1038/s41598-024-67365-3.
[6] Lu M, Wang Y, Tian J, et al. Application of deep learning and radiomics in the prediction of hematoma expansion in intracerebral hemorrhage: a fully automated hybrid approach[J]. Diagn Interv Radiol, 2024, 30(5):299-312. DOI: 10.4274/dir.2024.222088.
[7] 李光波,王新港,张旭伟. 自发性脑出血患者血清microRNA-130a、microRNA-210表达水平及与早期神经功能恶化的关系[J]. 中国现代医学杂志,2022,32(8):79-84. DOI:10.3969/j.issn.1005-8982.2022.08.015.
[8] 詹戈里.自发性脑出血早期神经功能恶化危险因素的病例对照研究[D].长春:吉林大学,2023.DOI:10.27162/d.cnki.gjlin.2023.003994.
[9] 中华医学会神经外科学分会,中国医师协会急诊医师分会,国家卫生和计划生育委员会脑卒中筛查与防治工程委员会. 自发性脑出血诊断治疗中国多学科专家共识[J]. 中华急诊医学杂志,2015,24(12):1319-1323. DOI:10.3760/cma.j.issn.1671-0282.2015.12.003.
[10] 张磊, 刘建民. 美国国立卫生研究院卒中量表[J]. 中华神经外科杂志, 2014, 30(1):79-79.
[11] Sterenstein A, Garg R. The impact of sex on epidemiology, management, and outcome of spontaneous intracerebral hemorrhage (sICH)[J]. J Stroke Cerebrovasc Dis, 2024,33(7):107755. DOI: 10.1016/j.jstrokecerebrovasdis.2024.107755.
[12] Deng L, Li ZQ, Yang WS, et al. Prehospital ultra-early neurological deterioration in intracerebral hemorrhage: definition, prevalence, and association with outcomes[J]. Cerebrovasc Dis, 2023, 52(4):471-479. DOI: 10.1159/000527545.
[13] 卢万俊,彭剑,袁梦轩,等. 基于平扫CT多维度影像组学对无传统影像学特征的自发性脑出血患者早期血肿扩大的预测作用[J]. 中国脑血管病杂志,2023,20(9):597-608. DOI:10.3969/j.issn.1672-5921.2023.09.003.
[14] Feng C, Ding Z, Lao Q, et al. Prediction of early hematoma expansion of spontaneous intracerebral hemorrhage based on deep learning radiomics features of noncontrast computed tomography[J]. Eur Radiol, 2024, 34(5):2908-2920. DOI: 10.1007/s00330-023-10410-y.
[15] Wang M, Liang Y, Li H, et al. Hybrid clinical-radiomics model based on fully automatic segmentation for predicting the early expansion of spontaneous intracerebral hemorrhage: a multi-center study[J]. J Stroke Cerebrovasc Dis, 2024, 33(11):107979. DOI: 10.1016/j.jstrokecerebrovasdis.2024.107979.
[16] Zhao X, Zhou B, Luo Y, et al. CT-based deep learning model for predicting hospital discharge outcome in spontaneous intracerebral hemorrhage[J]. Eur Radiol, 2024, 34(7):4417-4426. DOI: 10.1007/s00330-023-10505-6.
[17] Zhang H, Yang YF, Song XL, et al. An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study[J]. BMC Med Imaging, 2024, 24(1):170. DOI: 10.1186/s12880-024-01352-y.

基于深度学习算法和CT影像构建自发性脑出血早期神经功能恶化的智能预估系统

Constructing an intelligent prediction system for early neurological function deterioration in spontaneous cerebral hemorrhage based on deep learning algorithms and CT images

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

[1]	葛强李建宜闫晓红. MSCT检查联合血清CA125、SCC、ProGRP、NSE诊断肺癌的准确性 [J]. 国际医药卫生导报, 2025, 31(5): 810-814.
[2]	马旭阳蒋小锋苏美俊郑琦李政和黄燕杨宁丽唐敏丽杨全新. CT纹理分析及形态学特征对肺磨玻璃结节良恶性的诊断价值 [J]. 国际医药卫生导报, 2025, 31(3): 458-462.
[3]	孙利慧李亚俊陈建婷王军艳张鸣. MSCT联合血清PRSS2、EFNA1诊断胃癌患者淋巴结转移的价值 [J]. 国际医药卫生导报, 2025, 31(17): 2818-2822.
[4]	李建军蒋锋刘小丽. AIS大脑中动脉闭塞患者血清清蛋白、miR-134及mCTA侧支循环评分的临床意义 [J]. 国际医药卫生导报, 2025, 31(12): 1943-1947.
[5]	张前陈亮杨冉. 3D-CTBA精准定位应用于胸腔镜肺段切除术患者的临床价值 [J]. 国际医药卫生导报, 2024, 30(6): 923-927.
[6]	张志飞陈瑞曹宗华张权武高瑜王志永. MDR-PTB患者CT征象及治疗转归的危险因素分析 [J]. 国际医药卫生导报, 2024, 30(22): 3790-3795.
[7]	卓雪峰刘建伟黄秉韬张敬敬张靖雨. 脏层胸膜浸润术前评估方法的研究进展 [J]. 国际医药卫生导报, 2024, 30(2): 187-191.
[8]	顾君玲倪敏宗海燕何平张燕鲁晓杰. ICU自发性脑出血患者再出血的风险预测列线图模型构建 [J]. 国际医药卫生导报, 2024, 30(2): 228-234.
[9]	王文娟王世峰陈鹏曹雪. 穿支动脉粥样硬化病静脉溶栓后发生早期神经功能恶化的危险因素分析 [J]. 国际医药卫生导报, 2024, 30(17): 2916-2921.
[10]	童琳李巍高速李威威杨俊丽. 可溶性肿瘤坏死因子样凋亡微弱诱导剂对急性脑梗死早期神经功能恶化的诊断价值研究[J]. 国际医药卫生导报, 2022, 28(21): 2974-2979.
[11]	惠培泉, 乜全民, 宋磊, 秦时强, 王增武, 陈冰, 庞春晓. 层析征在预测脑出血血肿稳定性及预后中的应用价值[J]. 国际医药卫生导报, 2022, 28(1): 112-116.