Automated Assessment of White Matter Integrity in TBI Using Machine Learning

使用机器学习自动评估 TBI 中白质完整性

• 批准号: 9281656
• 负责人: Brian Allen Taylor
• 金额: --
• 依托单位: MICHAEL E DEBAKEY VA MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-07-01 至 2017-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9281656
• 关键词: Address; Affect; Afghanistan; Algorithms; Alzheimer' s Disease; Anisotropy; Behavioral; Biological Markers; Blast Cell; Blast Injuries; Brain; Brain Injuries; Brain region; Chronic; Classification; Cognitive; Computer software; Conflict (Psychology); Data; Detection; Development; Diagnosis; Diffuse; Diffusion Magnetic Resonance Imaging; Disease; Extracellular Space; Fiber; Freedom; Goals; Head and neck structure; Image; Individual; Injury; Intervention; Iraq; Joints; Link; Machine Learning; Magnetic Resonance Imaging; Measures; Military Personnel; Mission; Morbidity - disease rate; Myelin; Nature; Nerve; Nervous System Trauma; Neurons; Neuropsychology; Outcome; Outcome Measure; Output; Participant; Pathologic Processes; Pathology; Pathway interactions; Patients; Pattern; Performance; Population; Principal Component Analysis; Probability; Procedures; Process; Questionnaires; Radial; Recording of previous events; Regression Analysis; Reporting; Retrospective Studies; Sampling; Scanning; Sensitivity and Specificity; Severities; Site; Skeleton; Swelling; System; Training; Training Support; Trauma; Traumatic Brain Injury; Validation; Veterans; War; Weight; Work; accurate diagnosis; base; cognitive testing; cohort; combat; cost; daily functioning; depressive symptoms; design; disability; experience; functional outcomes; health administration; imaging detection; imaging study; improved; indexing; mild traumatic brain injury; mind control; neuroimaging; neuropathology; operation; outcome forecast; post-traumatic stress; public health relevance; rehabilitation service; rehabilitation strategy; service member; statistics; stress symptom; tool; validation studies; white matter; white matter change; white matter injury

DESCRIPTION (provided by applicant): Mild traumatic brain injury (mTBI) is the signature injury of the wars in Afghanistan and Iraq. Recent statistics indicate that 60% of blast injuries result in TBI and approximately 20% of returning OEF/OIF Veterans have sustained a TBI, with the majority classified as mTBI. Although many sequelae of mTBI resolve within a few months, a substantial portion of patients experience difficulties for years. Diagnosis of mTBI in the chronic stage is a frequent referral fo the Veterans Health Administration. Conventional MRI and CT are typically normal months after civilian and military mTBI making it difficult to accurately diagnose and to determine rehabilitation strategies. Diffusion tensor imaging (DTI) can be used to characterize and quantify WM pathways in the living brain. Specific to brain injury, pathological processes causing loss or disorganization of fibers associated with breakdown of myelin and downstream nerve terminals, neuronal swelling or shrinkage, and increased or decreased extracellular space, could affect the quantitative scalar metrics like mean diffusivity (MD), fractional anisotropy (FA), radial diffusivity (RD), and/or axial diffusivity (AD). Recent studies have reported that FA was reduced in chronic civilian mTBI. Evidence from military cohorts also suggests important changes in DTI metrics across several brain regions. Machine learning (ML) algorithms are particularly sensitive to distributed changes caused by disease as observed in several structural and functional studies. This particular class of algorithms is specifically designed to identify patterns in temporal or spatial data to distinguish between groups. While several ML algorithms exists, one particular multivariate algorithm known as a Support Vector Machine (SVM) has been successfully applied to Alzheimer's Disease studies as well as a recent study in a group of TBI patients through the use of DTI data. In addition, the incorporation of principal component analysis (PCA) to SVM showed robust automated detection of WM degradation in Alzheimer's Disease over several sites and MR scanner platforms. This ability to evaluate this across platforms is particularly attractive to multi-center imaging studies that are performed in the VHA system. At present, the automated detection of biomarkers is scarce in the diagnosis and prognosis of mTBI in our Veteran population. This work will tailor an imaging and detection strategy that can possibly be used to not only identify Veterans with mTBI more objectively but also predict cognitive outcome to help facilitate appropriate rehabilitation strategies. Aim 1 will consist of a retrospective study of 70 subjects and controls to train the SVM algorithm to differentiate between mTBI pathology and uninjured military controls that were also deployed in the OIF/OEF/OND conflicts. DTI skeletons will be processed using Tract-Based Spatial Statistics (TBSS) software and will be used as inputs into the SVM algorithm. Using this data, parameters such as the cost function will be determined to optimize the algorithm. We will measure the accuracy, sensitivity and specificity of the algorithm by using a cross-validation approach. Finally for this first aim, we will use a sensitivity analysis techniqueto identify regions the algorithm weights more in determining if an mTBI has taken place. This will identify pathways that are vulnerable to injury. In Aim 2, we will use the SVM classifier on DTI scans to output possibility indices of mTBI. Regression analysis will be used to relate these indices to outcome measures. In conclusion, this work will provide a robust tool to not only better diagnose and characterize mTBI but also stratify more personalized rehabilitation strategies through the improved characterization of mTBI.

描述（由申请人提供）： 轻度创伤性脑损伤（mTBI）是阿富汗和伊拉克战争的标志性损伤。最近的统计数据表明，60% 的爆炸伤会导致 TBI，大约 20% 回国的 OEF/OIF 退伍军人遭受过 TBI，其中大多数被归类为 mTBI。尽管 mTBI 的许多后遗症会在几个月内消失，但相当一部分患者会经历数年的困难。慢性阶段 mTBI 的诊断经常转诊给退伍军人健康管理局。传统的 MRI 和 CT 通常在民用和军用 mTBI 几个月后显示正​​常，因此很难准确诊断和确定康复策略。 弥散张量成像 (DTI) 可用于表征和量化活体大脑中的 WM 通路。具体到脑损伤，导致与髓磷脂和下游神经末梢分解、神经元肿胀或收缩以及细胞外空间增加或减少相关的纤维损失或紊乱的病理过程可能会影响定量标量指标，例如平均扩散率（MD）、分数各向异性（FA）、径向扩散率（RD）和/或轴向扩散率 （公元）。最近的研究表明，慢性平民 mTBI 中 FA 减少。来自军事群体的证据还表明，几个大脑区域的 DTI 指标发生了重要变化。 正如多项结构和功能研究中观察到的那样，机器学习 (ML) 算法对疾病引起的分布式变化特别敏感。此类特殊算法专门用于识别时间或空间数据中的模式以区分不同的组。虽然存在多种 ML 算法，但一种称为支持向量机 (SVM) 的特殊多变量算法已成功应用于阿尔茨海默病研究以及最近通过使用 DTI 数据对一组 TBI 患者进行的研究。此外，并入 主成分分析 (PCA) 与 SVM 的结合表明，在多个站点和 MR 扫描仪平台上，可以对阿尔茨海默病中的 WM 降解进行强大的自动检测。这种跨平台评估的能力对于在 VHA 系统中进行的多中心成像研究特别有吸引力。目前，生物标志物的自动检测在退伍军人群体中 mTBI 的诊断和预后方面还很缺乏。这项工作将定制一种成像和检测策略，不仅可以用来更客观地识别患有 mTBI 的退伍军人，还可以预测认知结果，以帮助促进适当的康复策略。 目标 1 将包括对 70 名受试者和对照进行回顾性研究，以训练 SVM 算法来区分 mTBI 病理学和未受伤的军事控制，这些控制也部署在 OIF/OEF/OND 冲突中。 DTI 骨架将使用基于区域的空间统计 (TBSS) 软件进行处理，并将用作 SVM 算法的输入。使用这些数据，将确定成本函数等参数来优化算法。我们将使用交叉验证方法来衡量算法的准确性、敏感性和特异性。最后，为了实现第一个目标，我们将使用敏感性分析技术来识别算法在确定是否发生 mTBI 时权重更大的区域。这将确定容易受伤的途径。在目标 2 中，我们将在 DTI 扫描上使用 SVM 分类器来输出 mTBI 的可能性指数。回归分析将用于将这些指数与结果指标联系起来。总之，这项工作将提供一个强大的工具，不仅可以更好地诊断和表征 mTBI，而且可以通过改进 mTBI 的表征来分层更个性化的康复策略。