IMAGE ANNOTATION FOR NCI CLINICAL RESEARCH DATABASES

NCI 临床研究数据库的图像注释

• 批准号: 10281351
• 负责人: MATTHEW DESANTIS
• 金额: $ 367.36万
• 依托单位: LEIDOS BIOMEDICAL RESEARCH, INC.
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-22 至 2025-09-21
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10281351
• 关键词: Address; Advanced Malignant Neoplasm; Cancer Detection; Classification; Clinical; Clinical Data; Clinical Research; Clinical Trials Network; Communities; Data; Data Commons; Data Set; Data Sources; Databases; Diagnosis; Funding; Genomics; Grant; Histopathology; Image; Label; Lesion; Malignant Neoplasms; Metadata; Phase II Clinical Trials; Phase III Clinical Trials; Proteomics; Research; Research Personnel; Semantics; Technology; The Cancer Imaging Archive; anticancer research; biobank; cancer imaging; imaging program; radiomics

The Cancer Imaging Program is hosting anonymized and de-identified image data sets on the Cancer Imaging Archive (TCIA) from select completed NCI’s Clinical Trials Network (NCTN) Phase II and III clinical trials and data collected through the NCI-funded projects such as CPTAC and Cancer Moonshot Biobank, and NCI grant-funded research. The clinical metadata on all these cases along with histopathology images, genomics and proteomic data (CPTAC) will also be made available for researchers via the Cancer Research Data Commons (CRDC). Additional primary data for the datasets are collected and hosted by NCI. These data have been widely leveraged to advance cancer imaging analysis technology and understanding. Increasingly, researchers leverage these data for radiomics and AI analysis which has shown promising potential of increasing the value of these data contribution to cancer detection, diagnosis and treatment workflow.

癌症成像计划正在癌症成像档案馆（TCIA）上托管匿名和去识别的图像数据集，这些数据来自选定的已完成的NCI临床试验网络（NCTN）II期和III期临床试验以及通过NCI资助的项目（如CPTAC和Cancer Moonshot Biobank）和NCI资助的研究收集的数据。所有这些病例的临床元数据沿着组织病理学图像，基因组学和蛋白质组学数据（CPTAC）也将通过癌症研究数据共享（CRDC）提供给研究人员。数据集的其他主要数据由NCI收集和托管。这些数据已被广泛用于推进癌症成像分析技术和理解。研究人员越来越多地利用这些数据进行放射组学和人工智能分析，这表明这些数据对癌症检测，诊断和治疗工作流程的价值有很大的潜力。