Machine Learning-based Imaging Biomarkers for Metabolic and Age-related Diseases

基于机器学习的代谢和年龄相关疾病的成像生物标志物

• 批准号: 10707354
• 负责人: Sokratis Makrogiannis
• 金额: $ 33.11万
• 依托单位: DELAWARE STATE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-20 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10707354
• 关键词: 3-Dimensional; Abdomen; Acceleration; Address; Adipose tissue; Adult; Advanced Development; Affect; Age; Aging; Agreement; Anatomy; Architecture; Area; Artificial Intelligence; Atlases; Baltimore; Biological; Black race; Body Composition; Body Regions; Bone Density; Bone structure; Cardiovascular Diseases; Classification; Clinical Data; Clinical Trials; Communities; Computer Assisted; Computer software; Coronary Arteriosclerosis; Data; Data Set; Degenerative polyarthritis; Descriptor; Deterioration; Development; Diabetes Mellitus; Diagnosis; Diagnostic; Dictionary; Disease; Epidemic; Female; Health Care Costs; Hispanic; Human; Human body; Image; Image Analysis; Imaging technology; Infiltration; Intervention; Joints; Link; Longitudinal Studies; Lower Extremity; Machine Learning; Magnetic Resonance Imaging; Manuals; Measures; Medical Imaging; Metabolic; Metabolic Diseases; Metabolic dysfunction; Metabolic syndrome; Methods; Microscopic; Minority Access; Minority Groups; Modernization; Monitor; Morphology; Muscle; Non-Insulin-Dependent Diabetes Mellitus; Not Hispanic or Latino; Obesity; Osteoporosis; Participant; Pathologist; Pathology; Pattern; Persons; Phenotype; Physiological; Prevalence; Principal Investigator; Process; Prognosis; Property; Quality of life; Reader; Research; Risk; Risk Factors; Risk Reduction; Skeletal Muscle; Software Tools; Source Code; Stroke; Techniques; Testing; Therapeutic; Time; Tissues; Training; Underserved Population; United States; Visualization; Work; X-Ray Computed Tomography; age related; automated image analysis; bone; clinical decision-making; clinical imaging; cost effective; deep learning; design; diabetes control; disease diagnosis; epidemiology study; ethnic minority; health care quality; health equity; imaging biomarker; imaging study; improved; in vivo; innovation; interest; learning strategy; machine learning method; male; mathematical methods; metabolic rate; morphometry; muscle form; muscle strength; novel; open source; pharmacologic; preservation; programs; quantitative imaging; racial minority; radiological imaging; radiologist; radiomics; research and development; sarcopenia; statistical learning; substantia spongiosa

Machine Learning-based Imaging Biomarkers for Metabolic and Age-related Diseases Specific Aims Age-related and metabolic diseases such as type-2 diabetes mellitus (T2DM), cardiovascular disease (CVD), obesity, osteoporosis and sarcopenia have become a worldwide epidemic that affects the quality of life of millions. To give a global perspective, roughly 343.8 million people in the world have type-2 diabetes today, and 175 million do not know they have diabetes at all. Metabolic diseases, such as diabetes and obesity, are strongly linked to longitudinal changes in body composition, morphology and function. Changes in skeletal muscle composition are strongly linked to loss in muscle strength and mass, frequently termed as sarcopenia, leading to decreased mobility and function. The accumulation of adipose tissue in the human body and changes of its regional distribution are associated with type-2 diabetes, cardiovascular disease and the metabolic syndrome. Contemporary imaging studies that are performed in vivo on a large number of participants have enabled cross sectional and longitudinal studies of age-related and metabolic diseases, and effects of pharmacological interventions. The emergence of advanced imaging technologies has also created the need for automated image analysis techniques for identification and quantification of morphological patterns of anatomies and tissues and their changes with increasing age. This project will contribute novel and non-invasive medical image analysis techniques for studying the human body composition to achieve timely diagnosis of these pathologies. Our research interests will concentrate on identification of morphological patterns in the lower extremity that will eventually lead to development of imaging biomarkers. We will use imaging and clinical data collected by the Baltimore Longitudinal Study of Aging (BLSA) that is the longest ongoing epidemiology study in the US, as well as publicly available datasets. We will build on recent advances in medical image analysis to contribute novel and non-invasive techniques for studying the human body composition and its changes (aim 1). Then we will develop machine learning methods for timely diagnosis and prognosis of metabolic and age-related diseases (aim 2). We will implement these techniques as open-source software for further use and development by the research community (aim 3).

基于机器学习的代谢和代谢相关疾病的成像生物标志物 具体目标 糖尿病相关和代谢性疾病，如2型糖尿病（T2DM）， 心血管疾病（CVD）、肥胖症、骨质疏松症和肌肉减少症已经成为世界范围内的 这是一种影响数百万人生活质量的流行病。从全球角度来看，大约343.8 今天，世界上有100万人患有2型糖尿病，1.75亿人根本不知道自己患有糖尿病。代谢 疾病，如糖尿病和肥胖症，与身体组成、形态和 功能骨骼肌组成的变化与肌肉力量和质量的损失密切相关， 称为肌肉减少症，导致活动性和功能下降。人体内脂肪组织的堆积 其区域分布的变化与2型糖尿病、心血管疾病和代谢紊乱有关。 综合征 在大量参与者体内进行的当代成像研究使得能够进行交叉成像。 年龄相关和代谢性疾病的横断面和纵向研究，以及药物干预的效果。 先进成像技术的出现也产生了对自动化图像分析技术的需求， 解剖结构和组织的形态学模式的识别和量化，以及它们随着 年龄 该项目将为研究人类提供新颖的非侵入性医学图像分析技术 身体组成，以实现这些病理的及时诊断。我们的研究兴趣将集中在 下肢形态模式的识别，最终将导致成像的发展 生物标志物。我们将使用巴尔的摩老龄化纵向研究（BLSA）收集的成像和临床数据， 是美国持续时间最长的流行病学研究，以及公开可用的数据集。我们将建立在最近 医学图像分析的进展，为研究人体提供新的非侵入性技术 其组成及其变化（目标1）。然后我们将开发机器学习方法，用于及时诊断和预后 代谢和年龄相关疾病（目标2）。我们将把这些技术作为开源软件来实现， 研究界的使用和发展（目标3）。