SCH: EXP: Cost Efficient Osteoporosis Analysis using Dental Data

该项目研究低成本的骨质疏松症预筛选方法，使用牙科数据，这是在常规牙科检查，因此在没有额外的费用收集。特别地，当老年人到牙科诊所进行常规治疗时，所提出的方法基于所收集的数据（例如牙科X光照片）来评估骨质疏松症的证据。为实现这一目标，该项目开展了三项主要研究活动，包括系统验证牙科数据与骨质量测量之间的关系，基于牙科图像的骨质疏松症分析，以及整合纵向和分类信息进行骨质疏松症预筛选。在美国，骨骼质量下降导致主要的健康问题。特别是，据估计，骨质疏松症困扰着55%的50岁及以上的美国人。骨质疏松症的早期诊断需要常规检查，因为在严重后果之前没有明显的症状与诊断相关，例如，发生骨折。这种常规检查可能会造成很大的经济负担，因为目前的金本位中使用的数据（即，双能X射线吸收测量法）的收集成本效益不高。该项目开发了图像分析和机器学习方法，用于使用牙科数据的低成本骨质疏松症预筛选方法。这项研究推动了计算和临床领域的科学发展。特别是，它可以作为使用常规收集的牙科数据进行低成本智能健康评估的示例性模型。此外，本项目中开发或发明的特定技术可以很容易地推广到其他相关的临床和非临床领域。此外，数据分析算法可以在许多科学和工程领域，如计算机视觉，医学图像分析，数据挖掘，气候演变等，该项目的教育活动与研究活动紧密结合，通过培训和教学不同层次的学生，向普通观众传播研究成果，并让代表性不足的学生参与研究。

This project investigates low-cost osteoporosis prescreening methods using dental data, which are collected during routine dental examination and thus at no additional cost. In particular, when a senior citizen attends the dental office for routine treatment, the proposed methods assess the evidence of osteoporosis based on collected data such as dental radiographs. The senior citizen is referred to a formal osteoporotic examination if high risk is found. Towards this goal, the project conducts three major research activities including systematical validation of the relation between dental data and bone quality measurement, dental image-based osteoporosis analysis, and integration of longitudinal and categorical information for osteoporosis prescreening. Decrease in bone quality causes major health problems in the United States. In particular, it has been estimated that osteoporosis afflicts 55% of Americans aged 50 and above. Early diagnosis of osteoporosis requires routine examination since no obvious symptom is associated with diagnosis before serious consequences, e.g., bone fracture, happen. Such routine examination can cause a big economic burden, since the data used in the current gold standard (i.e., dual energy X-ray absorptiometry) is not cost efficient to collect. This project develops image analysis and machine learning methods for low-cost osteoporosis prescreening methods using dental data. The research advances science in both computational and clinical fields. In particular, it serves as an exemplary model of using routinely collected dental data for low-cost smart health assessment. Moreover, the specific techniques exploited or invented in this project can be easily generalized to other related clinical and non-clinical domains. In addition, the data analytics algorithms can be of general interest in many areas of science and engineering such as computer vision, medical image analysis, data mining, climate evolution, etc. The education activities of the project are tightly integrated with the research activities, by training and teaching students of different levels, disseminating research results to general audience, and involving under-represented students in research.