Computational Toolkit for Normalizing the Impact of CT Acquisition and Reconstruction on Quantitative Image Features

用于标准化 CT 采集和重建对定量图像特征影响的计算工具包

基本信息

批准号：
10530062
负责人：
William Hsu
金额：
$ 60.36万
依托单位：
UNIVERSITY OF CALIFORNIA LOS ANGELES
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-09-01 至 2026-05-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10530062
关键词：
Academia Address Adopted Adoption Affect Agreement Algorithms Area Characteristics Chest Classification Clinical Clinical Trials Collaborations Collection Communities Coupled Data Data Set Detection Development Diagnosis Diagnostic Disease Disease Progression Dose Ensure Fostering Goals Head High Resolution Computed Tomography Image Image Analysis Industry Industry Collaboration Infarction Institution Interstitial Lung Diseases Link Lung nodule Machine Learning Malignant neoplasm of lung Maps Medical Imaging Methods Modeling Morphology Nodule Outcome Patient-Focused Outcomes Patients Performance Photons Physics Play Process Protocols documentation Publications Pulmonary Emphysema Radiation Dose Unit Reproducibility Research Resources Role Scanning Seminal Severity of illness Slice Software Tools Source Standardization Stroke Sum Surrogate Endpoint Techniques Technology Texture Thick Thinness Training Variant Visualization Work X-Ray Computed Tomography base biomarker development biomarker validation brain tissue clinical practice clinical translation computed tomography screening disease phenotype improved innovation large datasets machine learning model multidisciplinary neural network novel open source open source tool predictive modeling prospective quantitative imaging radiomics reconstruction screening tool

项目摘要

Quantitative image features (QIFs) such as radiomic and deep features hold enormous potential to improve the detection, diagnosis, and treatment assessment of a wide range of diseases. Generated from clinically acquired Computed Tomography (CT) scans, QIFs represent small pixel-wise changes that may be early indicators of disease progression. However, detecting these changes is complicated by variations in how CT scans are acquired and reconstructed. Ensuring repeatable and reproducible QIFs is necessary for developing predictive models that achieve consistent performance across different clinical settings. This project's premise is that QIFs are sensitive to CT parameters such as radiation dose level, slice thickness, reconstruction kernel, and reconstruction method. The combined interactions among these parameters result in unique image conditions, each yielding its own QIF value. Moreover, some clinical tasks and algorithms are more sensitive to differences in QIF values than others. We hypothesize that a systematic, task-dependent framework to characterize the impact of variability in CT parameters and effectively mitigate them will result in more consistent QIF values and the performance of prediction models. Three interrelated innovations will be pursued in this work: 1) a novel framework for characterizing the impact of different acquisition and reconstruction parameters on QIFs and ML models using patient scans with known clinical outcomes in multiple domains; 2) a systematic approach for selecting an optimal mitigation technique and evaluating the impact of normalization; and 3) an open-source software toolkit that formalizes the process of CT normalization, addressing real- world use cases developed by academic and industry collaborators. In Aim 1, we will evaluate how multiple CT parameters influence QIF values and model performance. Utilizing metrics of agreement and a heat map- based visualization, we will determine under which image acquisition and reconstruction conditions the QIFs and model performance are consistent. In Aim 2, we will assess and enhance normalization techniques for mitigating the impact of differences in acquisition and reconstruction, targeting the set of imaging conditions that are most relevant to a clinical task. In Aim 3, we will engage a spectrum of external stakeholders to guide the development and adoption of a software toolkit called CT-NORM. Three distinct clinical domains will drive our efforts: lung nodule detection (which relies on identifying small regions of high contrast differences to identify nodules), interstitial lung disease quantification (which depends on characterizing texture differences), and ischemic core assessment (which relies on detecting low contrast differences in brain tissue). CT-NORM will provide the scientific community with an approach and a unified toolkit to characterize and mitigate the impact of reconstruction and acquisition parameters on QIFs and prediction model performance. By addressing critical sources of variability, we will improve the process of generating QIFs and facilitate the discovery of precise and reproducible imaging phenotypes of disease.

定量图像特征（QIF），例如放射组学和深度特征，在改善图像质量方面具有巨大的潜力。多种疾病的检测、诊断和治疗评估。由临床获得的产生计算机断层扫描 (CT) 扫描，QIF 代表微小的像素变化，可能是早期迹象疾病进展。然而，由于 CT 扫描方式的不同，检测这些变化变得复杂。获得并重建。确保可重复和可再现的 QIF 对于开发预测性是必要的模型在不同的临床环境中实现一致的性能。该项目的前提是 QIF 对辐射剂量水平、切片厚度、重建核等 CT 参数敏感重建方法。这些参数之间的组合相互作用产生了独特的图像条件，每个都会产生自己的 QIF 值。此外，一些临床任务和算法对差异更加敏感 QIF 值高于其他值。我们假设有一个系统的、任务相关的框架来描述 CT 参数变异性的影响并有效减轻这些影响将导致更一致的 QIF 值和预测模型的性能。这项工作将追求三个相互关联的创新：1）小说用于表征不同采集和重建参数对 QIF 的影响的框架使用具有多个领域已知临床结果的患者扫描的 ML 模型； 2）系统化选择最佳缓解技术并评估标准化影响的方法；和 3）一个开源软件工具包，可形式化 CT 标准化过程，解决实际问题由学术界和行业合作者开发的世界用例。在目标 1 中，我们将评估多重 CT 参数影响 QIF 值和模型性能。利用协议指标和热图- 基于可视化，我们将确定在哪些图像采集和重建条件下 QIF 和模型性能一致。在目标 2 中，我们将评估和增强标准化技术以缓解采集和重建差异的影响，针对最重要的一组成像条件与临床任务相关。在目标 3 中，我们将吸引一系列外部利益相关者来指导发展并采用名为 CT-NORM 的软件工具包。三个不同的临床领域将推动我们的努力：肺结节检测（依靠识别高对比度差异的小区域来识别结节），间质性肺疾病量化（取决于表征纹理差异）和缺血核心评估（依赖于检测脑组织的低对比度差异）。 CT-NORM 将提供科学界拥有一种方法和统一的工具包来描述和减轻影响 QIF 的重建和采集参数以及预测模型性能。通过解决关键问题变异性来源，我们将改进生成 QIF 的过程，并促进发现精确和疾病的可重复成像表型。