急性缺血性卒中组织命运特征的深度学习
Deep Learning of Tissue Fate Features in Acute Ischemic Stroke.
作者信息
Stier Noah, Vincent Nicholas, Liebeskind David, Scalzo Fabien
机构信息
Neurovascular Imaging Research Core, Department of Neurology, Univerisity of California, Los Angeles (UCLA).
出版信息
Proceedings (IEEE Int Conf Bioinformatics Biomed). 2015 Nov;2015:1316-1321. doi: 10.1109/BIBM.2015.7359869. Epub 2015 Dec 17.
Abstract
In acute ischemic stroke treatment, prediction of tissue survival outcome plays a fundamental role in the clinical decision-making process, as it can be used to assess the balance of risk vs. possible benefit when considering endovascular clot-retrieval intervention. For the first time, we construct a deep learning model of tissue fate based on randomly sampled local patches from the hypoperfusion (Tmax) feature observed in MRI immediately after symptom onset. We evaluate the model with respect to the ground truth established by an expert neurologist four days after intervention. Experiments on 19 acute stroke patients evaluated the accuracy of the model in predicting tissue fate. Results show the superiority of the proposed regional learning framework versus a single-voxel-based regression model.
摘要
在急性缺血性中风治疗中，组织存活结果的预测在临床决策过程中起着基础性作用，因为在考虑血管内血栓清除干预时，它可用于评估风险与潜在益处之间的平衡。我们首次基于症状发作后立即在MRI中观察到的低灌注（Tmax）特征的随机采样局部斑块构建了组织命运的深度学习模型。我们根据干预后四天由专家神经科医生确定的地面真值对模型进行评估。对19名急性中风患者的实验评估了该模型预测组织命运的准确性。结果表明，所提出的区域学习框架优于基于单像素的回归模型。
相似文献
1
Deep Learning of Tissue Fate Features in Acute Ischemic Stroke.急性缺血性卒中组织命运特征的深度学习
Proceedings (IEEE Int Conf Bioinformatics Biomed). 2015 Nov;2015:1316-1321. doi: 10.1109/BIBM.2015.7359869. Epub 2015 Dec 17.
2
Regional prediction of tissue fate in acute ischemic stroke.急性缺血性脑卒中组织命运的区域性预测。
Ann Biomed Eng. 2012 Oct;40(10):2177-87. doi: 10.1007/s10439-012-0591-7. Epub 2012 May 17.
3
OEDL: an optimized ensemble deep learning method for the prediction of acute ischemic stroke prognoses using union features.OEDL：一种使用联合特征预测急性缺血性中风预后的优化集成深度学习方法。
Front Neurol. 2023 Jun 21;14:1158555. doi: 10.3389/fneur.2023.1158555. eCollection 2023.
4
Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging.利用深度学习从初始磁共振成像预测最终缺血性卒中病灶。
JAMA Netw Open. 2020 Mar 2;3(3):e200772. doi: 10.1001/jamanetworkopen.2020.0772.
5
Identifying patients with acute ischemic stroke within a 6-h window for the treatment of endovascular thrombectomy using deep learning and perfusion imaging.利用深度学习和灌注成像在6小时时间窗内识别适合进行血管内血栓切除术治疗的急性缺血性中风患者。
Front Med (Lausanne). 2023 Feb 22;10:1085437. doi: 10.3389/fmed.2023.1085437. eCollection 2023.
6
Deep Learning Detection of Penumbral Tissue on Arterial Spin Labeling in Stroke.深度学习检测脑卒中动脉自旋标记中的半影组织。
Stroke. 2020 Feb;51(2):489-497. doi: 10.1161/STROKEAHA.119.027457. Epub 2019 Dec 30.
7
Data-efficient deep learning of radiological image data for outcome prediction after endovascular treatment of patients with acute ischemic stroke.基于深度学习的医学影像数据的高效利用用于预测急性缺血性脑卒中患者血管内治疗后的结局。
Comput Biol Med. 2019 Dec;115:103516. doi: 10.1016/j.compbiomed.2019.103516. Epub 2019 Oct 22.
8
Association of Multiple Passes during Mechanical Thrombectomy with Incomplete Reperfusion and Lesion Growth.机械取栓术中多次操作与再灌注不完全及病变进展的相关性
Cerebrovasc Dis. 2022;51(3):394-402. doi: 10.1159/000519796. Epub 2021 Dec 13.
9
Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning.利用深度学习预测急性缺血性脑卒中的组织结局和评估治疗效果。
Stroke. 2018 Jun;49(6):1394-1401. doi: 10.1161/STROKEAHA.117.019740. Epub 2018 May 2.
10
Trial design and reporting standards for intra-arterial cerebral thrombolysis for acute ischemic stroke.急性缺血性脑卒中动脉内脑溶栓的试验设计与报告标准。
Stroke. 2003 Aug;34(8):e109-37. doi: 10.1161/01.STR.0000082721.62796.09. Epub 2003 Jul 17.
引用本文的文献
1
Automatic prediction of stroke treatment outcomes: latest advances and perspectives.中风治疗结果的自动预测：最新进展与展望。
Biomed Eng Lett. 2025 Feb 17;15(3):467-488. doi: 10.1007/s13534-025-00462-y. eCollection 2025 May.
2
Automatic identification of early ischemic lesions on non-contrast CT with deep learning approach.采用深度学习方法在非增强CT上自动识别早期缺血性病变。
Sci Rep. 2022 Oct 27;12(1):18054. doi: 10.1038/s41598-022-22939-x.
3
A Review on Computer Aided Diagnosis of Acute Brain Stroke.急性脑卒中专研综述
Sensors (Basel). 2021 Dec 20;21(24):8507. doi: 10.3390/s21248507.
4
Tissue outcome prediction in hyperacute ischemic stroke: Comparison of machine learning models.超急性缺血性脑卒中组织结局预测：机器学习模型的比较。
J Cereb Blood Flow Metab. 2021 Nov;41(11):3085-3096. doi: 10.1177/0271678X211024371. Epub 2021 Jun 23.
5
Deep learning-based identification of acute ischemic core and deficit from non-contrast CT and CTA.基于深度学习的非对比 CT 和 CTA 急性缺血核心和缺损的识别。
J Cereb Blood Flow Metab. 2021 Nov;41(11):3028-3038. doi: 10.1177/0271678X211023660. Epub 2021 Jun 8.
6
Artificial Intelligence and Acute Stroke Imaging.人工智能与急性脑卒中影像。
AJNR Am J Neuroradiol. 2021 Jan;42(1):2-11. doi: 10.3174/ajnr.A6883. Epub 2020 Nov 26.
7
The outcome in patients with brain stroke: A deep learning neural network modeling.脑卒患者的预后：深度学习神经网络建模
J Res Med Sci. 2020 Aug 24;25:78. doi: 10.4103/jrms.JRMS_268_20. eCollection 2020.
8
Functional Outcome Prediction in Ischemic Stroke: A Comparison of Machine Learning Algorithms and Regression Models.缺血性中风的功能预后预测：机器学习算法与回归模型的比较
Front Neurol. 2020 Aug 25;11:889. doi: 10.3389/fneur.2020.00889. eCollection 2020.
9
Noninvasive model for predicting future ischemic strokes in patients with silent lacunar infarction using radiomics.基于放射组学的影像学方法预测无症状腔隙性脑梗死患者未来发生缺血性脑卒中的模型。
BMC Med Imaging. 2020 Jul 8;20(1):77. doi: 10.1186/s12880-020-00470-7.
10
Primary Categorizing and Masking Cerebral Small Vessel Disease Based on "Deep Learning System".基于“深度学习系统”对脑小血管病进行初步分类和掩蔽
Front Neuroinform. 2020 May 25;14:17. doi: 10.3389/fninf.2020.00017. eCollection 2020.
本文引用的文献
1
A randomized trial of intraarterial treatment for acute ischemic stroke.急性缺血性脑卒中的动脉内治疗随机试验。
N Engl J Med. 2015 Jan 1;372(1):11-20. doi: 10.1056/NEJMoa1411587. Epub 2014 Dec 17.
2
Deep learning for neuroimaging: a validation study.深度学习在神经影像学中的应用：一项验证性研究。
Front Neurosci. 2014 Aug 20;8:229. doi: 10.3389/fnins.2014.00229. eCollection 2014.
3
Using longitudinal metamorphosis to examine ischemic stroke lesion dynamics on perfusion-weighted images and in relation to final outcome on T2-w images.利用纵向蜕变来研究灌注加权图像上的缺血性脑卒中病变动态变化，并与 T2 加权图像上的最终结果相关联。
Neuroimage Clin. 2014 Aug 1;5:332-40. doi: 10.1016/j.nicl.2014.07.009. eCollection 2014.
4
Regional prediction of tissue fate in acute ischemic stroke.急性缺血性脑卒中组织命运的区域性预测。
Ann Biomed Eng. 2012 Oct;40(10):2177-87. doi: 10.1007/s10439-012-0591-7. Epub 2012 May 17.
5
3D convolutional neural networks for human action recognition.三维卷积神经网络的人体动作识别。
IEEE Trans Pattern Anal Mach Intell. 2013 Jan;35(1):221-31. doi: 10.1109/TPAMI.2012.59.
6
Combining acute diffusion-weighted imaging and mean transmit time lesion volumes with National Institutes of Health Stroke Scale Score improves the prediction of acute stroke outcome.联合急性弥散加权成像和平均传输时间病变体积与国立卫生研究院卒中量表评分可提高急性卒中结局的预测。
Stroke. 2010 Aug;41(8):1728-35. doi: 10.1161/STROKEAHA.110.582874. Epub 2010 Jul 1.
7
Artificial neural network prediction of ischemic tissue fate in acute stroke imaging.急性中风成像中缺血组织转归的人工神经网络预测
J Cereb Blood Flow Metab. 2010 Sep;30(9):1661-70. doi: 10.1038/jcbfm.2010.56. Epub 2010 Apr 28.
8
The physiological significance of the time-to-maximum (Tmax) parameter in perfusion MRI.灌注 MRI 中达峰时间（Tmax）参数的生理学意义。
Stroke. 2010 Jun;41(6):1169-74. doi: 10.1161/STROKEAHA.110.580670. Epub 2010 Apr 22.
9
Quantitative prediction of ischemic stroke tissue fate.缺血性中风组织转归的定量预测
NMR Biomed. 2008 Oct;21(8):839-48. doi: 10.1002/nbm.1264.
10
Comparing two methods for assessment of perfusion-diffusion mismatch in a rodent model of ischaemic stroke: a pilot study.比较两种评估缺血性中风啮齿动物模型中灌注-扩散不匹配的方法：一项初步研究。
Br J Radiol. 2008 Mar;81(963):192-8. doi: 10.1259/bjr/70940134. Epub 2008 Jan 7.
Zotero 插件