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

基于机器学习的代谢性和老年性疾病成像生物标志物 具体目标 与年龄有关的代谢性疾病，如2型糖尿病(T2 DM)， 心血管疾病、肥胖、骨质疏松症和骨质疏松症已成为世界性的 影响数百万人生活质量的流行病。从全球的角度来看，大约有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。新陈代谢 疾病，如糖尿病和肥胖症，与身体成分、形态和性别的纵向变化密切相关 功能。骨骼肌成分的变化经常与肌肉力量和质量的丧失密切相关 称为骨质疏松症，导致活动能力和功能下降。脂肪组织在人体内的蓄积 其区域分布的改变与2型糖尿病、心血管疾病及代谢有关。 综合症。 在体内对大量参与者进行的当代成像研究使交叉成为可能 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图像分析技术的需求 解剖和组织形态模式的识别和量化及其随生长发育的变化 年龄。 本项目将为人类研究提供新的、无创的医学图像分析技术。 身体成分以实现对这些病理的及时诊断。我们的研究兴趣将集中在 最终将导致成像发展的下肢形态模式的识别 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 是美国正在进行的时间最长的流行病学研究，以及公开可用的数据集。我们将在最近的基础上 医学图像分析的进展为人体研究贡献新的非侵入性技术 组成及其变化(目标1)。然后我们将开发机器学习方法来及时诊断和预测 代谢性疾病和年龄相关疾病(目标2)。我们将以开源软件的形式实现这些技术，以便进一步 研究界的使用和开发(目标3)。

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).