A Machine Learning Approach to Classifying Time Since Stroke using Medical Imaging

使用医学成像对中风后时间进行分类的机器学习方法

• 批准号: 10363751
• 负责人: Corey Wells Arnold
• 金额: $ 42.99万
• 依托单位: UNIVERSITY OF CALIFORNIA LOS ANGELES
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-05-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10363751
• 关键词: Adverse event; Affect; Agreement; Algorithms; Alteplase; American; Area; Attenuated; Blood flow; Brain; California; Cause of Death; Characteristics; Classification; Clinical; Collaborations; Complex; Computer Analysis; Computing Methodologies; Data; Decision Making; Diffusion Magnetic Resonance Imaging; Eligibility Determination; Engineering; Environment; Foundations; Functional disorder; Goals; Guidelines; Hemorrhage; Hour; Image; Image Analysis; Imaging Device; Imaging Techniques; Individual; Infarction; Intravenous; Learning; Liquid substance; Location; Machine Learning; Magnetic Resonance; Maps; Medical Imaging; Methods; Modeling; Morbidity - disease rate; Multimodal Imaging; Neurologist; Patient imaging; Patients; Perfusion; Phenotype; Physicians; Physiological; Play; Process; Publishing; Recovery; Recurrence; Reperfusion Therapy; Research; Risk; Role; Savings; Secondary to; Shapes; Signal Transduction; Spectrum Analysis; Stroke; Techniques; Thrombolytic Therapy; Time; Tissues; Training; United States; Universities; Visualization; Visualization software; Work; X-Ray Computed Tomography; acute stroke; artery occlusion; autoencoder; base; clinical imaging; cohort; deep learning; diffusion weighted; experience; improved; interest; learning strategy; machine learning framework; machine learning method; machine learning model; mortality; multimodality; novel; outcome prediction; patient population; perfusion imaging; prevent; prospective; radiologist; spatiotemporal; spectrograph; stroke patient; stroke symptom; tool

PROJECT SUMMARY/ABSTRACT Stroke is a leading cause of mortality and morbidity in the United States, with approximately 795,000 Americans experiencing a new or recurrent stroke each year. Intravenous tissue plasminogen activator (IV tPA) is the dominant and most proven treatment option, but its use is only indicated within 4.5 hours following a stroke. Unfortunately, up to 30% of stroke patients present with an unknown time since stroke (TSS) symptom onset, which makes them ineligible to receive IV tPA. Many of these individuals could be spared severe morbidity or mortality if there existed an alternative method for establishing TSS, allowing them to be identified and treated. This proposal will develop machine learning methods to create a physiologically grounded method for predicting TSS based on multiparametric magnetic resonance (MR) and computed tomography (CT) imaging data. We believe our proposed techniques will outperform state-of-the-art methods that are based on subjective image interpretation, and have the potential to provide an objective data point that may be used in conjunction with the subjective assessments of experts, or in clinical environments that lack expertise in stroke imaging Research has established that MR and CT imaging captures information that correlates with TSS. However, existing methods for extracting this information are based on a physician subjectively interpreting the images and delineating regions of interest, processes that have been documented to have only weak to moderate agreement across trained expert reviewers. An automated approach that comprehensively analyzes the spectrum of imaging data could identify complex relationships across channels that more accurately classify TSS. For example, in MR, diffusion-weighted, perfusion-weighted, and fluid attenuated inversion recovery imaging all play important roles in characterizing a stroke, but a deep understanding of how each channel may be combined to describe TSS is unknown. We propose to establish new deep learning methods for fusing this information. Specifically, we will: 1) develop a machine learning framework for classifying TSS; 2) develop a deep convolutional autoencoder to generate novel multimodal image representations from MR and CT to improve classification; and 3) implement visualization techniques that elucidate the relationship between deep features and pathophysiological stroke processes. Under this project, we will use data from the UCLA and UCI Stroke Centers, allowing us to study different patient populations and imaging techniques. The successful completion of this research will provide a new method for estimating TSS from imaging, leading to new prospective trials for providing therapy to patients with unknown TSS.

项目概要/摘要 中风是美国大约 795,000 人死亡和发病的主要原因 美国人每年都会经历新发或复发性中风。静脉注射组织纤溶酶原激活剂（IV tPA）是主要且最行之有效的治疗选择，但仅在治疗后 4.5 小时内才表明使用。 中风。不幸的是，高达 30% 的中风患者出现中风后时间未知 (TSS) 症状 发病，这使得他们没有资格接受 IV tPA。其中许多人可以免受严重的 发病率或死亡率（如果存在建立 TSS 的替代方法，以便能够识别它们） 并进行治疗。该提案将开发机器学习方法来创建基于生理学的方法 用于基于多参数磁共振 (MR) 和计算机断层扫描 (CT) 预测 TSS 成像数据。我们相信我们提出的技术将优于基于 主观图像解释，并有可能提供可用于 结合专家的主观评估，或在缺乏卒中专业知识的临床环境中 成像 研究表明，MR 和 CT 成像可捕获与 TSS 相关的信息。然而， 提取此信息的现有方法基于医生主观解释图像 并描绘感兴趣的区域，已被记录为只有弱到中等的过程 训练有素的专家评审员之间达成一致。全面分析的自动化方法 成像数据谱可以识别跨渠道的复杂关系，从而更准确地进行分类 TSS。例如，在 MR 中，扩散加权、灌注加权和液体衰减反转恢复 成像在表征中风方面都发挥着重要作用，但深入了解每个通道如何发挥作用 是否组合来描述 TSS 尚不清楚。我们建议建立新的深度学习方法来融合这一点 信息。具体来说，我们将：1）开发一个用于分类TSS的机器学习框架； 2）开发一个 深度卷积自动编码器从 MR 和 CT 生成新颖的多模态图像表示 改进分类； 3）实施可视化技术来阐明深层之间的关系 中风的特征和病理生理过程。在这个项目中，我们将使用来自 UCLA 和 UCI 的数据 中风中心，使我们能够研究不同的患者群体和成像技术。成功者 这项研究的完成将提供一种从成像估算 TSS 的新方法，从而产生新的结果 为未知 TSS 患者提供治疗的前瞻性试验。

项目成果

A Machine Learning Approach to Predict Acute Ischemic Stroke Thrombectomy Reperfusion using Discriminative MR Image Features.

• DOI: 10.1109/bhi50953.2021.9508597
• 发表时间: 2021-07
• 期刊: ... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics
• 作者: Zhang, Haoyue;Polson, Jennifer;Nael, Kambiz;Salamon, Noriko;Yoo, Bryan;Speier, William;Arnold, Corey
• 通讯作者: Arnold, Corey