Risk stratifying indeterminate pulmonary nodules with jointly learned features from longitudinal radiologic and clinical big data

利用纵向放射学和临床大数据共同学习的特征对不确定的肺结节进行风险分层

• 批准号: 10678264
• 负责人: Thomas Zhihe Li
• 金额: $ 3.28万
• 依托单位: VANDERBILT UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10678264
• 关键词: Advanced Malignant Neoplasm; Algorithms; Anxiety; Aptitude; Archives; Area; Artificial Intelligence; Award; Benign; Big Data; Biometry; Cessation of life; Characteristics; Classification; Clinical; Clinical Informatics; Clinical Management; Clinical/Radiologic; Data; Decision Making; Diagnosis; Diagnostic; Diagnostic Errors; Diagnostic Procedure; Disease; Early Diagnosis; Engineering; Environment; Epidemic; Evaluation; Exhibits; Fellowship; Future; Goals; Growth; Health Care Costs; Healthcare Systems; Histologic; Histology; Histopathology; Image; Image Analysis; Incidence; Indolent; Institution; Intervention; Joints; Laboratories; Language; Learning; Lung; Lung Adenocarcinoma; Lung nodule; Machine Learning; Malignant - descriptor; Malignant Neoplasms; Malignant neoplasm of lung; Measurement; Measures; Medical; Medical History; Medical Imaging; Mentors; Metastatic Neoplasm to the Lung; Methods; Modality; Modeling; Modernization; Morbidity - disease rate; Nodule; Oncology; Outcome; Pathway interactions; Patient-Focused Outcomes; Patients; Pattern; Performance; Phenotype; Physicians; Positioning Attribute; Predictive Value; Probability; Prospective cohort; Public Health; Radiation; Radiologic Finding; Radiology Specialty; Recording of previous events; Records; Research; Resources; Retrospective cohort; Risk; Risk Reduction; Scientist; Smoking; Smoking History; Standardization; Subgroup; Techniques; Time; Training; Universities; Vision; Work; X-Ray Computed Tomography; anxiety reduction; artificial intelligence method; biomedical informatics; cancer imaging; cancer subtypes; career; chest computed tomography; clinical phenotype; clinical predictive model; clinically actionable; cohort; cost efficient; deep learning; design; electronic health data; health record; high dimensionality; high risk; improved; innovation; learning strategy; lens; low dose computed tomography; lung cancer screening; mortality; multimodal data; multimodality; noninvasive diagnosis; novel; novel strategies; personalized approach; precision oncology; predictive modeling; prospective; radiomics; risk stratification; screening; segregation; serial imaging; standard of care; success; symposium; tumor; Advanced Malignant Neoplasm; Algorithms; Anxiety; Aptitude; Archives; Area; Artificial Intelligence; Award; Benign; Big Data; Biometry; Cessation of life; Characteristics; Classification; Clinical; Clinical Informatics; Clinical Management; Clinical/Radiologic; Data; Decision Making; Diagnosis; Diagnostic; Diagnostic Errors; Diagnostic Procedure; Disease; Early Diagnosis; Engineering; Environment; Epidemic; Evaluation; Exhibits; Fellowship; Future; Goals; Growth; Health Care Costs; Healthcare Systems; Histologic; Histology; Histopathology; Image; Image Analysis; Incidence; Indolent; Institution; Intervention; Joints; Laboratories; Language; Learning; Lung; Lung Adenocarcinoma; Lung nodule; Machine Learning; Malignant - descriptor; Malignant Neoplasms; Malignant neoplasm of lung; Measurement; Measures; Medical; Medical History; Medical Imaging; Mentors; Metastatic Neoplasm to the Lung; Methods; Modality; Modeling; Modernization; Morbidity - disease rate; Nodule; Oncology; Outcome; Pathway interactions; Patient-Focused Outcomes; Patients; Pattern; Performance; Phenotype; Physicians; Positioning Attribute; Predictive Value; Probability; Prospective cohort; Public Health; Radiation; Radiologic Finding; Radiology Specialty; Recording of previous events; Records; Research; Resources; Retrospective cohort; Risk; Risk Reduction; Scientist; Smoking; Smoking History; Standardization; Subgroup; Techniques; Time; Training; Universities; Vision; Work; X-Ray Computed Tomography; anxiety reduction; artificial intelligence method; biomedical informatics; cancer imaging; cancer subtypes; career; chest computed tomography; clinical phenotype; clinical predictive model; clinically actionable; cohort; cost efficient; deep learning; design; electronic health data; health record; high dimensionality; high risk; improved; innovation; learning strategy; lens; low dose computed tomography; lung cancer screening; mortality; multimodal data; multimodality; noninvasive diagnosis; novel; novel strategies; personalized approach; precision oncology; predictive modeling; prospective; radiomics; risk stratification; screening; segregation; serial imaging; standard of care; success; symposium; tumor

PROJECT SUMMARY Indeterminate pulmonary nodules (IPNs) are highly prevalent radiologic findings that represent a substantial burden to patients and the national health care system because of the diagnostic challenge they present. There is a dire need to accurately stratify IPNs into low and high malignancy risk subgroups which are associated with clinical management pathways that are standardized and well validated. Clinical prediction models have the potential to do so in a scalable, cost-efficient, automated, and noninvasive manner, but advances in predictive accuracy must be made before they can make a substantial impact in medical practice. An unexplored direction in this area is integrating repeated measures of computed tomography (CT) studies and clinically-collected information within the same prediction model. This joint learning strategy has advantage of potentially modeling how dynamic radiologic changes like nodule growth rate vary with the trajectory of clinical variables such as smoking patterns and laboratory abnormalities. This perspective motivates the hypothesis that integrating information from longitudinal imaging and longitudinal clinical records will improve personalized IPN risk stratification and lung cancer subclassification From a clinician’s lens, this finding would not be surprising given the many time-varying modalities that are involved in diagnosis and decision making. This project leverages artificial intelligence (AI) and radiomic methods to analyze three retrospective cohorts with the possible addition of a large prospective cohort. The proposed work in Aim 1 will extend upon existing deep learning techniques to train a joint learning model on longitudinal images and clinical records to estimate the malignancy probability across time in patients with IPNs in a combined cohort exceeding 2000 subjects. This novel strategy will be evaluated against single-modality models and convention models that are used in practice. The evaluation will compare the models’ performance in stratifying IPNs into the low and high risk subgroups as a measure of clinical utility. Aim 2 asks if longitudinal change in radiomic features can distinguish between indolent and aggressive lung adenocarcinoma, other lung cancer subtypes, and pulmonary metastases. The proposed study will be the first to comprehensively characterize longitudinal radiomics across lung cancer subtypes and has the potential to identify novel longitudinal radiomic features that will aid early IPN evaluation and noninvasive lung cancer subclassification in patients with repeated imaging. In summary, the proposed research asks if clever integration of longitudinal information across different modalities can be leveraged to advance IPN risk stratification and lung cancer subclassification. This fellowship will be conducted at Vanderbilt University in a highly collaborative training environment with mentors in medical imaging AI, pulmonary oncology, biomedical informatics, radiology, and biostatistics. The proposed research and training plans are synergistically designed to ultimately prepare the candidate for a physician scientist career at the intersection of engineering innovation and precision oncology.

项目摘要 不确定的肺结节（IPN）是高度普遍的放射学发现，代表了实质性 由于他们提出的诊断挑战，患者和国家医疗保健系统负担负担。 迫切需要将IPN准确地分为低和高恶性风险亚组 与标准化且经过良好验证的临床管理途径相关。临床预测 模型有可能以可扩展，成本效益，自动化和无创的方式这样做，但是 必须提高预测精度，然后才能对医学实践产生重大影响。 该领域的意外方向是重复进行计算机断层扫描（CT）研究的测量 以及相同预测模型中临床收集的信息。这种联合学习策略有优势 潜在建模动态放射学如何随结节生长速率（如结节生长速率）的变化而变化 临床变量，例如吸烟模式和实验室异常。这种观点激发了 假设将纵向成像和纵向临床记录的信息整合 改善临床医生镜头的个性化IPN风险分层和肺癌亚分类， 鉴于诊断和诊断和 决策。该项目利用人工智能（AI）和放射线方法分析三个 回顾性队列，可能会增加大型前瞻性队列。 AIM 1中的拟议工作将 扩展现有的深度学习技术，以在纵向图像上训练联合学习模型和 临床记录以估计联合队列中IPN患者的时间跨时间的恶性肿瘤概率 超过2000名受试者。这种新颖的策略将根据单模式模型和惯例进行评估 实践中使用的模型。评估将比较模型在将IPN分类为 低风险亚组作为临床效用的量度。 AIM 2询问放射线纵向变化是否变化 特征可以区分懒惰和侵略性肺腺癌，其他肺癌亚型， 和肺转移。拟议的研究将是第一个全面表征纵向的研究 整个肺癌亚型的放射素学有潜力鉴定新的纵向放射素特征 这将有助于早期IPN评估和反复重复患者的无创肺癌亚分类 成像。总而言之，拟议的研究询问是否巧妙地整合纵向信息 可以利用不同的方式来提高IPN风险分层和肺癌亚分类。这 奖学金将在范德比尔特大学（Vanderbilt University）与导师的高度协作培训环境进行 在医学成像AI中，肺肿瘤学，生物医学信息，放射学和生物统计学。提议 研究和培训计划是协同设计的，旨在最终为候选人做好准备 在工程创新和精确肿瘤学交汇处的科学家职业。