Project 4: Risk stratification for pulmonary nodules detected by CT imaging using plasma and imaging biomarkers

项目 4：使用血浆和成像生物标志物通过 CT 成像检测肺结节的风险分层

基本信息

批准号：
10700904
负责人：
PAUL D. LAMPE
金额：
$ 51.62万
依托单位：
FRED HUTCHINSON CANCER CENTER
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-08-01 至 2025-05-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10700904
关键词：
Age Age Years Antibodies Antigens Area Autoantibodies Benign Biological Markers Biopsy Cancer Etiology Cancerous Cessation of life Chest imaging Classification Clinical Colorado Complex Detection Diagnosis Diagnostic Evaluation Fred Hutchinson Cancer Research Center Goals Guidelines Image Lung Lung nodule Malignant - descriptor Malignant neoplasm of lung Measures Methods Military Personnel Modeling Nodule Patient Care Patients Plasma Procedures Proteomics Quality of life ROC Curve Sampling Semantics Smoker Smoking Testing Texture Universities Validation X-Ray Computed Tomography aged biomarker panel care costs clinical biomarkers cohort cost high risk population imaging biomarker improved low dose computed tomography lung cancer screening machine learning algorithm mortality novel novel strategies radiologist radiomics risk stratification screening shape analysis standard care

项目摘要

Project Summary/Abstract – Project 4 Lung cancer is the leading cause of cancer deaths worldwide with >159,000 deaths annually in the US alone. The National Lung Screening Trial (NLST) employed low-dose Computed Tomography (CT) imaging of the chest to screen for lung cancer in a high-risk population (smokers aged 55-74). This study demonstrated a 20% reduction in mortality in the group receiving CTs when compared to standard care and has led to generalized acceptance of lung cancer screening in heavy smokers. Unfortunately, pulmonary nodules are a relatively common finding with 25-56% of smokers >50 years of age having CT identifiable pulmonary nodules but less than 2.5% of these actually were cancerous. For diagnosis of incidentally detected pulmonary nodules, current guidelines call for additional imaging and/or invasive biopsy procedures. For both of these scenarios we propose to combine two novel approaches to improve risk stratification for subjects with pulmonary modules. The first involves an antibody array platform for proteomic, glycomic, and autoantibody-antigen complex interrogation that has yielded a four-marker panel with an area under the ROC curve (AUC) of 0.82 in prediagnostic samples and 0.83 in a validation diagnostic set of malignant and benign nodules. The second novel component is the analysis of quantitative nodule features extracted from CT images using the methods of 'radiomics'. We have developed a validated radiomics pipeline that used machine learning algorithms for image texture features that when combined with radiologist-described shape, or semantic features yielded an AUC of 0.82 using the same diagnostic sample set described above. We have created a rule that combines clinical factors (age, smoking etc.), plasma biomarkers, radiomic CT image semantic and texture features for classification of CT-detected nodules as malignant or benign. The addition of both radiomic and biomarkers to the rule significantly increase the AUC (p<0.005) over clinical and semantic CT measures alone. This rule will be tested first in a Vanderbilt CVC incidental/diagnostic cohort, then fixed and tested in the Detection of Early lung Cancer Among Military Personnel Study 1 (DECAMP-1) cohort (Aim 1) with the goal of improving nodule evaluation. We will also test the rule in the NLST screening cohort (Aim 2) to create a final rule that models lung cancer early detection. In Aim 3 we will test the fixed rules from aims 1 and 2 in University of Colorado diagnostic and DECAMP-2 (prediagnostic) cohorts, respectively.

项目总结/摘要 – 项目 4 肺癌是全球癌症死亡的主要原因，仅在美国每年就有超过 159,000 人死亡。国家肺部筛查试验 (NLST) 采用低剂量计算机断层扫描 (CT) 成像胸部筛查可在高危人群（55-74 岁的吸烟者）中筛查肺癌。与标准护理相比，接受 CT 治疗的患者死亡率降低了 20% 不幸的是，肺结节是重度吸烟者肺癌筛查的普遍接受。相对常见的发现，25-56% 的 50 岁以上吸烟者患有 CT 可识别的肺部结节但其中只有不到 2.5% 实际上是癌性的。目前的指南要求针对这两种情况进行额外的成像和/或侵入性活检程序。我们建议结合两种新方法来改善肺结核患者的风险分层第一个模块涉及蛋白质组、糖组和自身抗体-抗原的抗体阵列平台。复杂的询问，产生了 ROC 曲线下面积 (AUC) 为 0.82 英寸的四标记物组诊断前样本和恶性和良性结节验证诊断集中的 0.83 第二个。新颖的部分是使用以下方法对从 CT 图像中提取的定量结节特征进行分析我们开发了一种经过验证的放射组学流程，该流程使用机器学习算法来进行图像纹理特征与放射科医生描述的形状或语义特征相结合产生了使用上述相同的诊断样本集，AUC 为 0.82 我们创建了一个结合的规则。临床因素（年龄、吸烟等）、血浆生物标志物、放射组学 CT 图像语义和纹理特征将 CT 检测到的结节分类为恶性或良性添加放射学和生物标志物。与单独的临床和语义 CT 测量相比，该规则显着增加了 AUC (p<0.005)。首先在 Vanderbilt CVC 偶然/诊断队列中进行测试，然后在早期检测中进行修复和测试军事人员肺癌研究 1 (DECAMP-1) 队列（目标 1），目标是改善结节我们还将在 NLST 筛选队列中测试该规则（目标 2），以创建建模的最终规则。在目标 3 中，我们将在科罗拉多大学测试目标 1 和 2 的固定规则。分别为诊断队列和 DECAMP-2（诊断前）队列。