AF:Small: Novel Geometric Techniques for Several Biomedical Problems

AF:Small：解决多个生物医学问题的新颖几何技术

基本信息

批准号：
1716400
负责人：
Jinhui Xu
金额：
$ 45.18万
依托单位：
SUNY at Buffalo
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-09-15 至 2021-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1716400&HistoricalAwards=false
关键词：
AF Small Novel Geometric Techniques

项目摘要

Recent progress in biomedicine has relied heavily on computer science technology. As the territory of biomedicine is rapidly enlarging, more powerful computational techniques are needed to foster its continuous growth. This project develops efficient computer algorithms for three fundamental geometric problems arising in several biomedical applications: (1) Truth Discovery, (2) Abnormal Clusters Detection, and (3) Resource Allocation Voronoi Diagram. Problem (1) develops quality-guaranteed polynomial time solutions to a key problem in data crowdsourcing, finding trustworthy information from multiple data sources, which is also motivated by the biomedical problem of learning critical information for improving treatment planning of endovascular intervention. Problem (2) detects extremely small-sized abnormal clusters from large datasets, which is motivated by detecting genomic structure variants from large populations. Problem (3) investigates new generalizations of the classical Voronoi diagram, which are motivated by a segmentation problem of biological images. This project will provide educational and research opportunities to undergraduate and graduate students (including those from under-represented groups), and develop a teaching evaluation tool for improving the quality of education. This project uses computational geometry techniques to develop novel algorithms for the proposed problems. It will introduce several general algorithmic techniques to the area of computational geometry, enriching and prodding its further development. These algorithmic techniques are also likely to be used in other areas, such as machine learning, computer vision, data mining, and pattern recognition, and bring new ideas to these areas. This project could lead to several long term impacts. It could potentially improve the quality of endovascular intervention, help identifying potential genomic structural variants in some genetic disorders, and provide more accurate quantitative information for medical image analysis.

生物医学的最新进展严重依赖计算机科学技术。由于生物医学领域正在迅速扩大，因此需要更强大的计算技术来促进其持续增长。该项目为在几种生物医学应用中产生的三个基本几何问题开发有效的计算机算法：（1）真实发现，（2）异常簇检测，以及（3）资源分配Voronoi图。问题（1）开发了质量保证的多项式时间解决方案，以解决数据众包的关键问题，从多个数据源中找到值得信赖的信息，这也是由学习关键信息的生物医学问题所激发的，用于改善血管内干预的治疗计划。问题（2）检测到大型数据集的极小尺寸的异常簇，这是通过检测大量人群的基因组结构变体而动机的。问题（3）研究了经典Voronoi图的新概括，这些图是由生物图像的分割问题动机。该项目将为本科和研究生（包括来自代表性不足的小组的研究生）提供教育和研究机会，并开发一种教学评估工具来提高教育质量。该项目使用计算几何技术来开发针对拟议问题的新算法。它将将几种一般算法技术引入计算几何形状领域，丰富和促进其进一步的发展。这些算法技术也可能在其他领域（例如机器学习，计算机视觉，数据挖掘和模式识别）中使用，并将新想法带到这些领域。该项目可能会导致几种长期影响。它可能会提高血管内干预的质量，有助于识别某些遗传疾病中潜在的基因组结构变异，并为医学图像分析提供更准确的定量信息。