基于脑部计算机断层扫描的人工智能辅助颅内出血诊断
- 作者: Khoruzhaya A.N.1, Arzamasov K.M.1, Kodenko M.R.1, Kremneva E.I.1,2, Burenchev D.V.1
-
隶属关系:
- Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
- Russian Center of Neurology and Neurosciences
- 期: 卷 6, 编号 2 (2025)
- 页面: 214-228
- 栏目: 原创性科研成果
- URL: https://ogarev-online.ru/DD/article/view/310211
- DOI: https://doi.org/10.17816/DD645364
- EDN: https://elibrary.ru/RFYVMC
- ID: 310211
如何引用文章
全文:
详细
论证。颅内出血具有较高的致死率和致残风险,因此在发病后24小时内实现快速且精准的诊断至关重要。借助人工智能技术分析脑部计算机断层扫描图像,有助于缩短诊断时间并提升诊断质量。本研究的现实背景在于,当前俄罗斯获批用于颅内出血识别的人工智能服务数量有限,且缺乏其长期临床有效性的相关数据,因此亟需通过多中心监测评估其在真实临床条件下的稳定性与诊断准确性。
目的:在18个月多中心临床监测条件下,评估一款人工智能服务在基于原始脑部计算机断层扫描图像诊断颅内出血方面的诊断准确性与稳定性。
方法。分析所用图像为匿名脑部计算机断层扫描图像。该人工智能服务经过三阶段测试,用以评估其在有限数据集上的准确性与临床性能。在18个月内,两位专注于神经影像的放射科医师每月评估80份由人工智能预处理、并从临床流程中随机抽取的脑部计算机断层扫描检查。通过ROC曲线分析评估诊断结果,计算灵敏度、特异度、准确率和曲线下面积等指标。
结果。在临床监测过程中共分析了1200份脑部计算机断层扫描图像,其中在48.3%的病例中检测到颅内出血征象。基于人工智能对是否存在颅内出血的二分类结果,获得的诊断指标为:灵敏度97.4%(95.8–98.5),特异度75.4%(71.8–78.7),准确率86.0%(83.9–87.9),曲线下面积为94%(92.6–95.3)。随着时间的推移,除灵敏度外,大多数诊断指标与时间变量之间呈现统计学显著的中度正相关,这一现象可能与服务版本的更替有关。然而,在人工智能判定为颅内出血的病例中,标注与放射科医生结论完全一致的比例为28.5%,其余71.5%则存在不同差异。在与放射科医生结论完全一致的病例中,修正后诊断指标分别为:灵敏度26.6%、特异度73.8%、准确率50.1%、曲线下面积49.6%。
结论。当前配置下的人工智能服务能够以极高的概率排除颅内出血,可在急诊条件下用于患者的初步分诊。然而,修正后指标数值偏低,反映出人工智能服务在病变细节解读方面与放射科医生的诊断存在显著差异。
作者简介
Anna N. Khoruzhaya
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
编辑信件的主要联系方式.
Email: KhoruzhayaAN@zdrav.mos.ru
ORCID iD: 0000-0003-4857-5404
SPIN 代码: 7948-6427
MD
俄罗斯联邦, MoscowKirill M. Arzamasov
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: ArzamasovK@zdrav.mos.ru
ORCID iD: 0000-0001-7786-0349
SPIN 代码: 3160-8062
MD, Dr. Sci. (Medicine)
俄罗斯联邦, MoscowMaria R. Kodenko
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: KodenkoM@zdrav.mos.ru
ORCID iD: 0000-0002-0166-3768
SPIN 代码: 5789-0319
Cand. Sci. (Engineering)
俄罗斯联邦, MoscowElena I. Kremneva
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies; Russian Center of Neurology and Neurosciences
Email: KremnevaE@zdrav.mos.ru
ORCID iD: 0000-0001-9396-6063
SPIN 代码: 8799-8092
MD, Dr. Sci. (Medicine)
俄罗斯联邦, Moscow; MoscowDmitry V. Burenchev
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Email: BurenchevD@zdrav.mos.ru
ORCID iD: 0000-0003-2894-6255
SPIN 代码: 2411-3959
MD, Dr. Sci. (Medicine)
俄罗斯联邦, Moscow参考
- Li X, Zhang L, Wolfe CDA, Wang Y. Incidence and long-term survival of spontaneous intracerebral hemorrhage over time: a systematic review and meta-analysis. Frontiers in Neurology. 2022;13:819737. doi: 10.3389/fneur.2022.819737 EDN: MLOQRJ
- Hemorrhagic stroke: clinical guidelines. Moscow: Ministry of Health of the Russian Federation; 2022. (In Russ.) [cited 2024 Dec 12]. Available from: https://ruans.org/Text/Guidelines/hemorrhagic-stroke-2022.pdf
- Hostettler IC, Seiffge DJ, Werring DJ. Intracerebral hemorrhage: an update on diagnosis and treatment. Expert Review of Neurotherapeutics. 2019;19(7):679–694. doi: 10.1080/14737175.2019.1623671 EDN: JWSYUZ
- Woo D, Comeau ME, Venema SU, et al. Risk factors associated with mortality and neurologic disability after intracerebral hemorrhage in a racially and ethnically diverse cohort. JAMA Network Open. 2022;5(3):e221103. doi: 10.1001/jamanetworkopen.2022.1103 EDN: BVHNLU
- Yaghi S, Dibu J, Achi E, et al. Hematoma expansion in spontaneous intracerebral hemorrhage: predictors and outcome. International Journal of Neuroscience. 2014;124(12):890–893. doi: 10.3109/00207454.2014.887716
- Gong B, Khalvati F, Ertl-Wagner BB, Patlas MN. Artificial intelligence in emergency neuroradiology: current applications and perspectives. Diagnostic and Interventional Imaging. 2025;106(4):135–142. doi: 10.1016/j.diii.2024.11.002 EDN: DHXSGS
- Arbabshirani MR, Fornwalt BK, Mongelluzzo GJ, et al. Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. npj Digital Medicine. 2018;1(1):9. doi: 10.1038/s41746-017-0015-z EDN: BORIWC
- Seyam M, Weikert T, Sauter A, et al. Utilization of artificial intelligence–based intracranial hemorrhage detection on emergent noncontrast CT images in clinical workflow. Radiology: Artificial Intelligence. 2022;4(2):e210168. doi: 10.1148/ryai.210168 EDN: HEPSBX
- Davis MA, Rao B, Cedeno PA, et al. machine learning and improved quality metrics in acute intracranial hemorrhage by noncontrast computed tomography. Current Problems in Diagnostic Radiology. 2022;51(4):556–561. doi: 10.1067/j.cpradiol.2020.10.007 EDN: NHQFYC
- O’Neill TJ, Xi Y, Stehel E, et al. Active reprioritization of the reading worklist using artificial intelligence has a beneficial effect on the turnaround time for interpretation of head CT with intracranial hemorrhage. Radiology: Artificial Intelligence. 2021;3(2):e200024. doi: 10.1148/ryai.2020200024 EDN: LCDGTM
- Smorchkova AK, Khoruzhaya AN, Kremneva EI, Petryaikin AV. Machine learning technologies in CT-based diagnostics and classification of intracranial hemorrhages. Burdenko's Journal of Neurosurgery. 2023;87(2):85. doi: 10.17116/neiro20238702185EDN: JVZDST
- Yu KH, Kohane IS. Framing the challenges of artificial intelligence in medicine. BMJ Quality & Safety. 2018;28(3):238–241. doi: 10.1136/bmjqs-2018-008551
- Allen B, Dreyer K, Stibolt R, et al. Evaluation and real-world performance monitoring of artificial intelligence models in clinical practice: try it, buy it, check it. Journal of the American College of Radiology. 2021;18(11):1489–1496. doi: 10.1016/j.jacr.2021.08.022 EDN: NMKGVD
- Recht MP, Dewey M, Dreyer K, et al. Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations. European Radiology. 2020;30(6):3576–3584. doi: 10.1007/s00330-020-06672-5 EDN: WWDEXB
- Vasiliev YuA, Vlazimirskyy AV, Omelyanskaya OV, et al. Methodology for testing and monitoring artificial intelligence-based software for medical diagnostics. Digital Diagnostics. 2023;4(3):252–267. doi: 10.17816/DD321971 EDN: UEDORU
- Morozov SP, Vladzimirsky AV, Klyashtornyy VG, et al. Clinical acceptance of software based on artificial intelligence technologies (radiology). Moscow: Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies; 2019. EDN: GWJIMI
- Morozov SP, Vladzimirsky AV, Andreychenko AE, et al. Regulations for the preparation of data sets with a description of approaches to the formation of a representative data sample. Moscow: Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies; 2022. (In Russ.) EDN: XENAJE
- Chetverikov SF, Arzamasov KM, Andreichenko AE, et al. Approaches to sampling for quality control of artificial intelligence in biomedical research. Sovremennye tehnologii v medicine. 2023;15(2):19. doi: 10.17691/stm2023.15.2.02 EDN: FUKXYC
- Kodenko MR, Bobrovskaya TM, Reshetnikov RV, et al. Empirical approach to sample size estimation for testing of AI algorithms. Doklady Mathematics. 2024;110(S1):S62–S74. doi: 10.1134/S1064562424602063 EDN: VJHJRD
- Salehinejad H, Kitamura J, Ditkofsky N, et al. A real-world demonstration of machine learning generalizability in the detection of intracranial hemorrhage on head computerized tomography. Scientific Reports. 2021;11(1):17051. doi: 10.1038/s41598-021-95533-2 EDN: SXLMCH
- Zia A, Fletcher C, Bigwood S, et al. Retrospective analysis and prospective validation of an AI-based software for intracranial haemorrhage detection at a high-volume trauma centre. Scientific Reports. 2022;12(1):19885. doi: 10.1038/s41598-022-24504-y EDN: IWNBET
- Ginat DT. Analysis of head CT scans flagged by deep learning software for acute intracranial hemorrhage. Neuroradiology. 2019;62(3):335–340. doi: 10.1007/s00234-019-02330-w EDN: WTOITQ
- Voter AF, Meram E, Garrett JW, Yu JPJ. Diagnostic accuracy and failure mode analysis of a deep learning algorithm for the detection of intracranial hemorrhage. Journal of the American College of Radiology. 2021;18(8):1143–1152. doi: 10.1016/j.jacr.2021.03.005 EDN: GPJYDS
- McLouth J, Elstrott S, Chaibi Y, et al. Validation of a deep learning tool in the detection of intracranial hemorrhage and large vessel occlusion. Frontiers in Neurology. 2021;12:656112. doi: 10.3389/fneur.2021.656112 EDN: FFIXVV
- Kundisch A, Hönning A, Mutze S, et al. Deep learning algorithm in detecting intracranial hemorrhages on emergency computed tomographies. PLOS ONE. 2021;16(11):e0260560. doi: 10.1371/journal.pone.0260560 EDN: QPACKZ
- Del Gaizo AJ, Osborne TF, Shahoumian T, Sherrier R. Deep learning to detect intracranial hemorrhage in a national teleradiology program and the impact on interpretation time. Radiology: Artificial Intelligence. 2024;6(5):e240067. doi: 10.1148/ryai.240067 EDN: EHHAOO
- Pettet G, West J, Robert D, et al. A retrospective audit of an artificial intelligence software for the detection of intracranial haemorrhage used by a teleradiology company in the United Kingdom. BJR|Open. 2023;6(1):tzae033. doi: 10.1093/bjro/tzae033 EDN: DWNYCF
- Mäenpää SM, Korja M. Diagnostic test accuracy of externally validated convolutional neural network (CNN) artificial intelligence (AI) models for emergency head CT scans – A systematic review. International Journal of Medical Informatics. 2024;189:105523. doi: 10.1016/j.ijmedinf.2024.105523 EDN: HLVVYQ
- Eldaya RW, Kansagra AP, Zei M, et al. Performance of automated RAPID intracranial hemorrhage detection in real-world practice: a single-institution experience. Journal of Computer Assisted Tomography. 2022;46(5):770–774. doi: 10.1097/rct.0000000000001335 EDN: GRDZTF
- Schmitt N, Mokli Y, Weyland CS, et al. Automated detection and segmentation of intracranial hemorrhage suspect hyperdensities in non-contrast-enhanced CT scans of acute stroke patients. European Radiology. 2021;32(4):2246–2254. doi: 10.1007/s00330-021-08352-4 EDN: OLFWXI
- Warman R, Warman A, Warman P, et al. Deep learning system boosts radiologist detection of intracranial hemorrhage. Cureus. 2022;undefined:. doi: 10.7759/cureus.30264 EDN: IRZKDY
- Buchlak QD, Tang CHM, Seah JCY, et al. Effects of a comprehensive brain computed tomography deep learning model on radiologist detection accuracy. European Radiology. 2023;34(2):810–822. doi: 10.1007/s00330-023-10074-8 EDN: ZHIFOG
- Ngiam KY, Khor IW. Big data and machine learning algorithms for health-care delivery. The Lancet Oncology. 2019;20(5):e262–e273. doi: 10.1016/S1470-2045(19)30149-4
- Kiefer J, Kopp M, Ruettinger T, et al. Diagnostic accuracy and performance analysis of a scanner-integrated artificial intelligence model for the detection of intracranial hemorrhages in a traumatology emergency department. Bioengineering. 2023;10(12):1362. doi: 10.3390/bioengineering10121362 EDN: EPLIBY
补充文件
