Phase 1 IUCRC Rutgers-New Brunswick: Center for Accelerated Real Time Analytics (CARTA)

第一阶段 IUCRC 罗格斯-新不伦瑞克：加速实时分析中心 (CARTA)

• 批准号: 1747778
• 负责人: Dimitris Metaxas
• 金额: $ 75万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-06-01 至 2024-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1747778&HistoricalAwards=false
• 关键词: Phase; IUCRC; Rutgers; New; Brunswick

Nearly every research field and industry sector is struggling with extracting useful information from massive and dynamic data in a timely way. Developing tools and technologies in this realm of real-time and accelerated analytics contributes to promoting the progress of science and to advancing the national prosperity and welfare. Success in this realm hinges on balancing fundamental research, technological know-how, and commercial market intelligence. To address this challenge, this project joins industry members with academic centers to conduct multidisciplinary science and research towards extracting value from massive and moving data and enabling better decision making of complex, dynamic data.The Center of Accelerated Real Time Analytics (CARTA) project explores the ways in which relatively-high-risk fundamental developments can be leveraged to help organizations that have longer-term, more complex analytic needs. The focus of CARTA is on horizontal foundational technologies that would create an infrastructure capable of powering applications of national significance. In this context, at Rutgers-New Brunswick (RU-NB), the CARTA/RU-NB site will enable new application domains through innovative machine learning, statistical, modeling methods and technologies for accelerated and real-time analytics. Having these technologies and tools will be key in achieving the goals of the overall CARTA center. The broader impact of the work of the CARTA center will be in addressing the future advanced, real-time analytics needs of the industry and society. The techniques developed by CARTA can be applied across industry sectors, including national security, healthcare, manufacturing, energy, and business intelligence. The fundamental research done at CARTA will be translated into technology developments, delivering practical solutions to hard problems. The ultimate success of this paradigm shift by the analytics industry will rest on the ability of CARTA universities to prepare experts to take advantage of the science and technologies to solve a variety of real-life applications. CARTA research may involve sensitive academic and industrial data along with public domain data. This data and resulting research outputs will be maintained using appropriate best practices for each type of data for a period of three years after the closing of CARTA. A central repository, suitably tagged for appropriate referencing and documentation, will be set up at https://carta.umbc.edu for maintaining the acquired and generated data from Center projects. Access to all models and project results will be stored on line and made available for downloading in near real time to respond to approved user requests.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

几乎每个研究领域和行业部门都在努力从海量动态数据中及时提取有用信息。在实时和加速分析领域开发工具和技术有助于促进科学进步并促进国家繁荣和福利。这一领域的成功取决于平衡基础研究、技术知识和商业市场情报。为了应对这一挑战，该项目联合行业成员和学术中心开展多学科科学研究，旨在从海量移动数据中提取价值，并能够对复杂的动态数据做出更好的决策。加速实时分析中心 (CARTA) 项目探索如何利用相对高风险的基本面发展来帮助具有长期、更复杂分析需求的组织。 CARTA 的重点是横向基础技术，这些技术将创建能够为具有国家意义的应用程序提供动力的基础设施。在此背景下，罗格斯大学新不伦瑞克分校 (RU-NB) 的 CARTA/RU-NB 站点将通过创新的机器学习、统计、建模方法和技术来实现新的应用领域，以实现加速和实时分析。拥有这些技术和工具将是实现整个 CARTA 中心目标的关键。 CARTA 中心工作的更广泛影响将在于满足行业和社会未来先进的实时分析需求。 CARTA 开发的技术可应用于各个行业领域，包括国家安全、医疗保健、制造、能源和商业智能。 CARTA 所做的基础研究将转化为技术开发，为难题提供实用的解决方案。分析行业这一范式转变的最终成功将取决于 CARTA 大学培养专家利用科学和技术解决各种现实应用的能力。 CARTA 研究可能涉及敏感的学术和工业数据以及公共领域数据。 这些数据和由此产生的研究成果将在 CARTA 结束后三年内使用每种类型数据的适当最佳实践进行维护。将在 https://carta.umbc.edu 建立一个中央存储库，并适当标记以供适当的参考和文档，用于维护从中心项目获取和生成的数据。对所有模型和项目结果的访问将在线存储并可供近实时下载，以响应批准的用户请求。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优势和更广泛的评估进行评估，被认为值得支持影响审查标准。

项目成果

Attentive Neural Cell Instance Segmentation

专注的神经细胞实例分割

• 发表时间: 2019-04
• 期刊: Medical image analysis
• 影响因子: 10.9
• 作者: Yi, J.;Wu, P.;Jiang, M.;Huang, Q.;Hoeppner, D. J.;Metaxas, D.
• 通讯作者: Metaxas, D.

Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning

基于深度学习的乳腺癌全切片图像的基因突变和生物通路预测

• DOI: 10.1038/s41698-021-00225-9
• 发表时间: 2021-09-23
• 期刊: NPJ Precision Oncology
• 影响因子: 7.9
• 作者: Qu H;Zhou M;Yan Z;Wang H;Rustgi VK;Zhang S;Gevaert O;Metaxas DN
• 通讯作者: Metaxas DN

CONTEXT-REFINED NEURAL CELL INSTANCE SEGMENTATION

上下文细化的神经细胞实例分割

• 发表时间: 2019-04
• 期刊: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019
• 作者: Yi, J.;Wu, P.;Huang, Q.;Qu, H.;Hoeppner, D. J.;Metaxas, D.
• 通讯作者: Metaxas, D.

JOINT SEGMENTATION AND FINE-GRAINED CLASSIFICATION OF NUCLEI IN HISTOPATHOLOGY IMAGES

组织病理学图像中细胞核的联合分割和细粒度分类

• 发表时间: 2019-04
• 期刊: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019
• 作者: Qu, H.;Riedlinger, G.;Wu, P.;Huang, Q.;Yi, J.;De, S.;Metaxas, D.
• 通讯作者: Metaxas, D.

Interactive Architectural Design with Diverse Solution Exploration

互动架构设计与多元化解决方案探索

• DOI: 10.1109/tvcg.2019.2938961
• 发表时间: 2019-09
• 期刊: IEEE Transactions on Visualization and Computer Graphics
• 影响因子: 5.2
• 作者: Berseth, Glen;Haworth, Brandon;Usman, Muhammad;Schaumann, Davide;Khayatkhoei, Mahyar;Kapadia, Mubbasir Turab;Faloutsos, Petros
• 通讯作者: Faloutsos, Petros