High-dimensional Modeling of PET for radiomic Biomarker Discovery

用于放射组学生物标志物发现的 PET 高维建模

• 批准号: 10686238
• 负责人: Ani Eloyan
• 金额: $ 70.91万
• 依托单位: BROWN UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10686238
• 关键词: Alzheimer' s Disease; Alzheimer' s disease patient; Amyloid; Atrophic; Bayesian neural network; Binding; Biological; Biological Markers; Brain; Clinical; Clinical Research; Clinical Treatment; Clinical Trials; Cognitive; Complex; Data; Data Analyses; Data Collection; Development; Dimensions; Disease; Disease Progression; Epidemiology; Etiology; Future; Goals; Image; Imaging technology; Impaired cognition; Late Onset Alzheimer Disease; Learning; Magnetic Resonance Imaging; Mathematics; Measurement; Measures; Mediator; Medical Imaging; Methods; Modeling; Morphology; Multimodal Imaging; Noise; Observational Study; Outcome; Output; Participant; Pathology; Patients; Physiological; Population; Positron-Emission Tomography; Research Methodology; Scanning; Severities; Severity of illness; Shapes; Site; Standardization; Statistical Methods; Statistical Models; Structure; Techniques; Technology; Testing; Texture; Time; Tracer; Uncertainty; Visit; Visualization; automated algorithm; biomarker discovery; biomarker identification; biomedical imaging; cerebral atrophy; clinical predictors; cognitive performance; complex data; deep learning; design; disease diagnosis; drug development; early onset; feature extraction; high dimensionality; imaging modality; improved; independent component analysis; insight; interest; learning strategy; longitudinal analysis; longitudinal positron emission tomography; multimodal data; multimodality; nervous system disorder; neural network; neuroimaging; neuroimaging marker; novel; novel strategies; patient biomarkers; predictive modeling; primary outcome; radiological imaging; radiomics; secondary outcome; statistics; success; targeted treatment; tau Proteins; time interval; tool; uptake

Project Summary We propose to develop statistical methods for the analysis of longitudinal positron emission tomography (PET) data for patients with Alzheimer’s disease (AD). Disease biomarkers identified from PET data are necessary for integrating these imaging modalities in observational studies and in clinical trials for drug development for AD. We propose statistical methods for the analysis of PET images including dimension reduction and biomarker extraction from voxel-wise intensity analysis that incorporate disease progression in two observational studies including data on early-onset and late-onset AD participants. Our methods allow for integration of MRI atrophy measures in the analyses to obtain multimodal predictors of disease severity and progression. The proposed methods will utilize the complex data and noise structure for developing powerful tools for biomarker identification that can be used for finding differences of disease progression between populations of interest. Particularly, our proposed biomarkers incorporate information on shape and texture of radiological images for prediction. The proposed methods can be incorporated to analyze data in future studies in most AD data collection centers as well as to apply in radiomics of imaging data in general.

项目摘要 我们建议发展统计方法来分析纵向正电子发射断层扫描(PET)。 阿尔茨海默病(AD)患者的数据。从PET数据中确定的疾病生物标记物对于 在AD药物开发的观察性研究和临床试验中整合这些成像模式。 提出了用于PET图像分析的统计方法，包括降维和生物标记物 从包含两个观察性研究中疾病进展的体素强度分析中提取 包括早发和晚发AD患者的数据。我们的方法允许整合MRI萎缩 分析中的措施，以获得疾病严重程度和进展的多模式预测因子。建议数 方法将利用复杂的数据和噪声结构来开发强大的生物标记物识别工具 这可以用来发现感兴趣人群之间疾病进展的差异。尤其是我们的 建议的生物标志物结合了用于预测的放射图像的形状和纹理信息。这个 建议的方法可以在大多数AD数据收集中心的未来研究中用于分析数据，例如 以及一般应用于成像数据的放射组学。