Comprehensive Training program in Imaging Science and Informatics

影像科学和信息学综合培训计划

基本信息

批准号：
10838206
负责人：
Mia K Markey
金额：
$ 9.14万
依托单位：
UNIVERSITY OF TEXAS AT AUSTIN
依托单位国家：
美国
项目类别：
财政年份：
2009
资助国家：
美国
起止时间：
2009-08-01 至 2025-07-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10838206
关键词：
Training Programs imaging informatics imaging science

项目摘要

7. Project Summary/Abstract The over-arching theme of this proposal is to train “comprehensive imaging scientists” in the skills necessary to identify clinically relevant problems; develop instrumentation, sensors, and contrast agents to form images appropriate for the problem; and analyze the resulting imaging data using signal processing, mathematical modeling, visualization, and informatics techniques to improve the prevention, detection, diagnosis, and treatment of human diseases. The program spans from molecular to cellular to tissue to organ. In order for imaging scientists to be knowledgeable of the full trajectory from image formation to analysis and decision-making, they must be trained in four core areas: Instrumentation, Devices, and Contrast Agents; Image processing; Modeling and Visualization; and Data Mining and Informatics. All students in the program are trained in the core concepts of these areas. The current training program is a two-year pre-doctoral portfolio program. A total of 41 students have been admitted to the program. The proposed renewal will train another 20 students. The program includes off-campus externship research experiences; in-depth clinical engagement; and a wide-ranging professional development component. Imaging Science is an integral element of basic science research and clinical medicine. Imaging cell trafficking and receptor pharmacology in vivo have already led to targeted drug and gene therapies and an understanding of cellular biochemical pathways will contribute to new advances in medicine. Individualized medicine relies heavily on imaging techniques to select the best therapies and monitor progress. Although structural in situ human imaging is already a critical component of clinical medicine, many advances are needed in functional imaging of the brain and other organs to improve healthcare. Brain mapping which is a core focus of NIH research relies heavily on imaging. We have identified a critical need for imaging scientists to develop new imaging instrumentation and apply that instrumentation with appropriate methods from image processing; modeling and visualization; and informatics and data mining. In recognition of the potential of artificial intelligence to transform medical imaging, our program emphasizes applications of machine learning. This training program fills a critical niche by providing highly skilled scientists who are trained in the broad trajectory of imaging science. Understanding the interplay between instrumentation and image analysis, including machine learning methods, is important for designing the next generation of hardware and software tools for quantifying complex biological systems and providing robust clinical tools. A key outcome of the program is that trainees gain the skills necessary to identify clinically relevant problems.

7。项目摘要/摘要该提案的整理主题是在技能上培训“全面成像科学家” 确定临床相关问题所必需的；开发仪器，传感器和对比度代理形成适合问题的图像；并使用信号处理，数学建模，可视化和信息信息技术以改进预防，检测，诊断和治疗人类疾病。该程序从分子到细胞到组织的组织。为了使成像科学家了解图像的完整轨迹进行分析和决策，必须在四个核心领域进行培训：仪器，设备，和对比剂；图像处理；建模和可视化；以及数据挖掘和信息学。该计划中的所有学生都接受了这些领域的核心概念的培训。当前的培训计划是两年的博士前投资组合计划。总共有41名学生被录取了该计划。这拟议的更新将培训另外20名学生。该计划包括校外研究经验；深入的临床参与；以及大型专业发展组成部分。成像科学是基础科学研究和临床医学的组成部分。成像细胞运输体内的受体药理学已经导致了靶向药物和基因疗法，并且有了理解细胞生化途径将有助于医学的新进展。个性化医学依赖大量的成像技术选择最佳疗法并监测进度。虽然原地结构性人体成像已经是临床医学的关键组成部分，功能中需要许多进步大脑和其他器官的成像以改善医疗保健。大脑图是NIH的核心重点研究严重依赖成像。我们已经确定了成像科学家发展新的需要的迫切需求成像仪器，并使用图像处理中适当的方法应用该仪器；建模和可视化；以及信息和数据挖掘。认识人造的潜力智力改变了医学成像，我们的计划强调了机器学习的应用。该培训计划通过提供在广泛的培训中的高技能科学家来填补关键的利基市场成像科学的轨迹。了解仪器和图像分析之间的相互作用，包括机器学习方法，对于设计下一代硬件和软件很重要量化复杂生物系统并提供强大临床工具的工具。一个关键结果计划是，学员获得了确定临床相关问题所需的技能。

项目成果

期刊论文数量（124）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Deep Tissue Imaging with Multiphoton Fluorescence Microscopy.

DOI：
10.1016/j.cobme.2017.09.004
发表时间：
2017-12
期刊：
Current opinion in biomedical engineering
影响因子：
3.9
作者：
Miller DR;Jarrett JW;Hassan AM;Dunn AK
通讯作者：
Dunn AK

Evaluating patient-specific neoadjuvant regimens for breast cancer via a mathematical model constrained by quantitative magnetic resonance imaging data.

DOI：
10.1016/j.neo.2020.10.011
发表时间：
2020-12
期刊：
Neoplasia (New York, N.Y.)
影响因子：
0
作者：
Jarrett AM;Hormuth DA 2nd;Wu C;Kazerouni AS;Ekrut DA;Virostko J;Sorace AG;DiCarlo JC;Kowalski J;Patt D;Goodgame B;Avery S;Yankeelov TE
通讯作者：
Yankeelov TE

Using pressure-driven flow systems to evaluate laser speckle contrast imaging.