Development and Validation of Prognostic Radiomic Markers of Response and Recurrence for Patients with Colorectal Liver Metastases

结直肠肝转移患者反应和复发的预后放射学标志物的开发和验证

• 批准号: 9761718
• 负责人: Yun Shin Chun
• 金额: $ 74.41万
• 依托单位: SLOAN-KETTERING INST CAN RESEARCH
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-03-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9761718
• 关键词: Address; Affect; Algorithms; Biological Markers; Biometry; Cancer Center; Cancer Etiology; Cessation of life; Clinical; Clinical Trials; Collaborations; Colorectal; Colorectal Cancer; Computer software; Data; Data Set; Decision Making; Development; Diagnostic; Disease; Disease Progression; Ensure; Excision; Eye; Goals; Hepatic; Human; Image; Image Analysis; Infusion procedures; Institutes; Institution; Link; Malignant Neoplasms; Malignant neoplasm of liver; Manufacturer Name; Medical Oncology; Medical center; Metastatic Neoplasm to the Liver; Methods; Modeling; Network-based; Operative Surgical Procedures; Outcome; Pathology; Pathway interactions; Patient Selection; Patients; Pattern; Performance; Phase; Phase I/II Trial; Prognostic Marker; Prospective Studies; Publications; Radiology Specialty; Recurrence; Regional Chemotherapy; Reproducibility; Research; Resolution; Scanning; Series; Specificity; Standardization; System; Technology; Testing; Therapeutic; Training; United States; University of Texas M D Anderson Cancer Center; Update; Validation; Venous; Western World; X-Ray Computed Tomography; base; cancer care; cancer diagnosis; cancer imaging; chemotherapy; clinical care; colon cancer patients; comparative; contrast enhanced; convolutional neural network; cost; design; efficacy trial; experience; high risk; image archival system; imaging biomarker; imaging modality; improved; indexing; individualized medicine; innovation; mortality; novel; novel marker; personalized cancer therapy; personalized medicine; phantom model; precision medicine; predicting response; prediction algorithm; prevent; prognostic; programs; prospective; quantitative imaging; radiomics; reconstruction; response; response biomarker; specific biomarkers; tool

SUMMARY Colorectal cancer is the second leading cause of cancer-related mortality in the United States. More than 50% of patients with colorectal cancer will develop liver metastases in their lifetime with a dismal <10% surviving past three years. A major therapeutic problem in this disease is that no markers prognostic of hepatic recurrence or predictive of response prior to treatment are known. The goal of this research is to fill this gap by providing non-invasive and objective prognostic quantitative imaging markers for personalized treatment of colorectal liver metastases (CRLM). Our single-institution data support that quantitative imaging features extracted from routine CT scans predict volumetric response to systemic and regional chemotherapy and identify patients at high risk of hepatic recurrence and poor survival. Progress in developing these novel markers is limited by a lack of optimization, standardization, and validation, all critical barriers to clinical use. The objectives of this application are to develop and validate robust imaging features by standardizing image acquisition, to improve automated tools for clinical trial use, and to validate the predictive power of imaging features with external data. We have partnered with University of Texas MD Anderson Cancer Center, Rensselaer Polytechnic Institute, and GE Research, facilitating the widespread integration of the proposed technology into medical centers worldwide. Our central hypothesis is that quantitative CT-based imaging features provide novel and robust indices for predicting response, hepatic recurrence, and survival in CRLM patients. Specifically, we will (1) validate predictive and prognostic imaging features with external data, (2) prospectively assess repeatability and reproducibility of contrast-enhanced CT imaging features, and (3) develop an integrated rawdiomics pipeline by fully utilizing sinogram data. We have assembled a critical mass of experts in surgery, medical oncology, pathology, radiology, biostatistics, and image analysis. Combined with the largest clinical experience in CRLM in the western world, this application is a unique and unrivaled opportunity to define radiomics of CRLM. Integration into existing clinical workflows means that small medical centers without highly specialized radiology groups would benefit from predictive algorithms developed at two high-volume centers via a low-cost software update. Successful completion of our aims will provide validated prognostic imaging markers with a pathway to routine clinical use, which are of paramount importance to improving patient survival of this deadly disease.

总结