TCIA Sustainment and Scalability - Platforms for Quantitative Imaging Informatics in Precision Medicine

TCIA 持续性和可扩展性 - 精准医学中的定量成像信息学平台

• 批准号: 10013134
• 负责人: Imon Banerjee
• 金额: $ 158.49万
• 依托单位: UNIV OF ARKANSAS FOR MED SCIS
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-22 至 2022-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10013134
• 关键词: Advisory Committees; Algorithms; Area; Big Data; Biology; Cancer Biology; Characteristics; Clinical; Clinical Trials; Collaborations; Collection; Communities; Computer software; Coupled; Data; Data Collection; Data Set; Diagnostic Imaging; Disease; Ensure; Fostering; Funding; Goals; Image; Individual; Information Resources; Malignant Neoplasms; Manuals; Medical Research; Morphologic artifacts; National Research Council; Pathology; Patients; Phenotype; Play; Predisposition; Process; Publications; Reproducibility; Research; Resource Informatics; Resources; Semantics; Targeted Research; Techniques; Technology; Testing; The Cancer Imaging Archive; Training; Translational Research; United States National Institutes of Health; Validation; Visual; anticancer research; base; cancer imaging; cancer therapy; cohort; cost; data exploration; data format; data resource; data reuse; data sharing; experience; image archival system; imaging informatics; improved; individual variation; individualized medicine; innovation; interest; knowledge base; meetings; multimodality; new technology; open data; operation; outcome forecast; pathology imaging; precision medicine; precision oncology; quantitative imaging; radiological imaging; radiomics; repository; research study; resource guides; response; tool; treatment planning; validation studies; wiki

Project Summary The National Research Council has defined Precision Medicine as “the tailoring of medical treatments to individual characteristics of each patient.” This requires the ability to classify patients into specialized cohorts that differ in their susceptibility to a particular disease, in the biology and/or prognosis of the diseases they may develop, or in their response to a specific treatment. Identifying quantitative imaging phenotypes across scale through the use of radiomic/pathomic analyses is an evolving approach to cohort identification and to improving our understanding of cancer biology. These analytic techniques require large collections of well-curated data for algorithm testing and validation. Additional big data collections are required to test new hypotheses relating to cancer biology, prognosis and therapy response. Since 2011 the Cancer Imaging Archive (TCIA) has encouraged and supported cancer-related open science research by acquiring, curating, hosting and managing collections of multi-modal information. To remain relevant to its current research community and ready to support future research initiatives TCIA must undergo continuous improvement and expansion of it capabilities guided by the research community. The TCIA user community has identified four critical areas for improvement: expanded resources for integrative Image-Omics studies, enhanced capacity to acquire high quality data collections, resources to support validation studies and Research Reproducibility, and increased community engagement. The sustainment of TCIA and research community directed expansion of its capabilities will ensure this valuable resource continues to support its rapidly growing user community and continue to promote research reproducibility and data reuse in cancer precision medical research.

项目总结