Histopathology correlated quantitative analysis of lung nodules with LDCT for early detection of lung cancer

肺结节的组织病理学相关定量分析与 LDCT 早期发现肺癌

• 批准号: 10398181
• 负责人: CHUAN ZHOU
• 金额: $ 30.5万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-05-01 至 2024-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10398181
• 关键词: Advocate; Anxiety; Archives; Benign; Biological Markers; Biopsy; Cause of Death; Characteristics; Collection; Computer Vision Systems; Data; Database Management Systems; Databases; Decision Aid; Decision Making; Decision Support Systems; Descriptor; Development; Diagnosis; Disease; Early Diagnosis; Early treatment; Effectiveness; Evaluation; Excision; Foundations; Goals; Health Care Costs; Histologic; Histopathology; Image; Individual; Indolent; Institutes; Joints; Judgment; Knowledge; Lobectomy; Lung; Lung nodule; Machine Learning; Malignant neoplasm of lung; Maps; Methods; Morbidity - disease rate; Nodule; Pathologic; Pathology; Patient risk; Patients; Performance; Property; Radiation exposure; Radiology Specialty; Reference Standards; Reporting; Reproducibility; Risk Factors; Scanning; Screening Result; Solid; Structure of parenchyma of lung; Techniques; Testing; Thoracic Radiography; United States; Visual; Woman; X-Ray Computed Tomography; attenuation; automated image analysis; automated segmentation; base; cancer diagnosis; clinically translatable; computed tomography screening; cost; diagnostic biomarker; effectiveness validation; follow-up; high risk; imaging biomarker; improved; large datasets; low dose computed tomography; lung cancer screening; men; mortality; novel; pathology imaging; personalized medicine; radiologist; radiomics; screening; screening program; treatment optimization; treatment strategy; unnecessary treatment

Lung cancer is a leading cause of death in the United States. The National Lung Screening Trial (NLST) showed that more lung cancers can be detected at an early stage with low dose CT screening. However, over-diagnosis of indolent lung cancer and benign nodules is one of the major limitations of screening, resulting in unnecessary treatment, biopsy, follow-up, increased radiation exposure, patient anxiety, and cost. Due to a lack of in-depth knowledge of the correlation of structural image features and histologic findings of lung nodules and the absence of validated diagnostic biomarkers for accurate disease categorization, the current diagnosis and management of the screen-detected nodules remains challenging. The goal of this proposed project is to develop a decision support system (DSS) based on quantitative histopathology correlated CT descriptor (q-PCD) of pulmonary nodules using advanced computer vision and machine learning techniques to characterize the histopathologic features of nodules and analyze their correlations with CT image features for improvement of early detection of lung cancer. We hypothesize that the proposed q-PCD analysis will have strong association with histopathologic characterization, and therefore will be a more effective biomarker for differentiation of invasive, pre-invasive, and benign nodules than conventional image-based features or radiologists' visual judgement. Accurate characterization of the nodule types will assist radiologists in making decision for management of the detected nodules; e.g., enabling early detection and treatment of invasive lung cancer, safe surveillance or replacing lobectomy with limited sublobar resection for pre-invasive lung cancer, and sparing biopsy of benign nodules, thereby reducing morbidity and costs in lung cancer screening programs. Our major specific aims are to 1) collect a large database of LDCT screening cases from NLST project and our institute to develop automated image analysis methods, 2) to develop a new DSS based on quantitative pathologic correlated CT descriptors (q-PCD) of lung nodules, 3) validate the effectiveness of DSS in lung cancer diagnosis. To achieve these aims, we will collect a large data set from the National Lung Screening Trial (NLST) and our institute. The collected database will include the baseline and follow up scans, pathology data, demographic information and other information provided by NLST. We will develop automated segmentation methods to extract the volumes of the solid and sub-solid components of detected lung nodules, develop quantitative methods to characterize the radiologic and pathologic features of lung nodules as well as the surrounding lung parenchyma, develop a novel radiopathomics strategy to correlate pathomics with radiomics, and to identify new imaging biomarkers. We will develop a clinically-translatable DSS with a joint biomarker combining both image and patient information, and evaluate its performance in lung cancer diagnosis, including its effectiveness in baseline screening CT exams and in follow up exams.

肺癌是美国的首要死因。全国肺部筛查试验 （NLST）表明，通过低剂量 CT 筛查可以在早期发现更多的肺癌。 然而，惰性肺癌和良性结节的过度诊断是该技术的主要局限性之一。 筛查，导致不必要的治疗、活检、随访、辐射暴露增加、患者焦虑， 和成本。由于缺乏对结构图像特征和组织学相关性的深入了解 肺结节的发现以及缺乏用于准确疾病的经过验证的诊断生物标志物 分类，目前对屏幕检测到的结节的诊断和管理仍然具有挑战性。 该项目的目标是开发一个基于定量分析的决策支持系统（DSS） 使用先进的计算机视觉和肺结节的组织病理学相关 CT 描述符 (q-PCD) 机器学习技术来表征结节的组织病理学特征并分析其 与CT图像特征的相关性以改善肺癌的早期检测。我们假设 所提出的 q-PCD 分析将与组织病理学特征密切相关，因此 将成为区分侵袭性结节、侵袭前结节和良性结节的更有效的生物标志物 传统的基于图像的特征或放射科医生的视觉判断。结节的准确表征 类型将协助放射科医生做出对检测到的结节的管理决策；例如，尽早启用 浸润性肺癌的检测和治疗、安全监测或用有限的亚肺叶切除术替代肺叶切除术 切除浸润前肺癌，并保留良性结节的活检，从而降低发病率和 肺癌筛查项目的费用。我们主要的具体目标是 1) 收集 LDCT 的大型数据库 筛选NLST项目和我院的案例，开发自动化图像分析方法，2) 开发一种基于肺结节定量病理相关 CT 描述符 (q-PCD) 的新 DSS，3) 验证DSS在肺癌诊断中的有效性。为了实现这些目标，我们将收集大量数据 由国家肺部筛查试验 (NLST) 和我们研究所提供。收集的数据库将包括 基线和后续扫描、病理数据、人口统计信息和其他信息提供 NLST。我们将开发自动分割方法来提取固体和次固体的体积 检测到的肺结节的成分，开发定量方法来表征放射学和 肺结节及其周围肺实质的病理特征，开发出一种新的方法 放射病理组学策略将病理组学与放射组学相关联，并识别新的成像生物标志物。我们将 开发具有结合图像和患者信息的联合生物标志物的临床可翻译 DSS，以及 评估其在肺癌诊断中的表现，包括其在基线筛查 CT 检查中的有效性 以及后续考试中。

项目成果

Recursive Training Strategy for a Deep Learning Network for Segmentation of Pathology Nuclei With Incomplete Annotation.

• DOI: 10.1109/access.2022.3172958
• 发表时间: 2022
• 期刊: IEEE ACCESS
• 影响因子: 3.9
• 作者: Zhou, Chuan;Chan, Heang-Ping;Hadjiiski, Lubomir M.;Chughtai, Aamer
• 通讯作者: Chughtai, Aamer

Pathologic categorization of lung nodules: Radiomic descriptors of CT attenuation distribution patterns of solid and subsolid nodules in low-dose CT.

• DOI: 10.1016/j.ejrad.2020.109106
• 发表时间: 2020-08
• 期刊: EUROPEAN JOURNAL OF RADIOLOGY
• 影响因子: 3.3
• 作者: Zhou, Chuan;Chan, Heang-Ping;Chughtai, Aamer;Hadjiiski, Lubomir M.;Kazerooni, Ella A.;Wei, Jun
• 通讯作者: Wei, Jun

Hybrid U-Net-based deep learning model for volume segmentation of lung nodules in CT images.

基于混合U-NET的深度学习模型，用于CT图像中肺结节的体积分割。

• DOI: 10.1002/mp.15810
• 发表时间: 2022-11
• 期刊: MEDICAL PHYSICS
• 影响因子: 3.8
• 作者: Wang, Yifan;Zhou, Chuan;Chan, Heang-Ping;Hadjiiski, Lubomir M.;Chughtai, Aamer;Kazerooni, Ella A.
• 通讯作者: Kazerooni, Ella A.