An AI/ML-ready Dataset for Investigating the Effect of Variations in CT Acquisition and Reconstruction

用于研究 CT 采集和重建变化影响的 AI/ML 数据集

基本信息

批准号：
10842635
负责人：
William Hsu
金额：
$ 28.86万
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 2025-05-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10842635
关键词：
Abdomen Algorithms Anatomy Appearance Area Artificial Intelligence Benchmarking Characteristics Chest Classification Clinic Clinical Clinical Data Coffee Common Data Element Communities Complement Computed Tomography Scanners Data Data Collection Data Set Detection Diagnosis Digital Imaging and Communications in Medicine Disease Disease Progression Dose Engineering FAIR principles Head Healthcare Heterogeneity Image Informatics Investigation Ischemia Link Lung nodule MRI Scans Machine Learning Magnetic Resonance Imaging Malignant neoplasm of lung Medical Medical Imaging Methods Modeling Multicenter Studies Nodule Output Parents Pathology Patients Performance Physics Privacy Process ROC Curve Radiation Dose Unit Radiation exposure Readiness Reproducibility Research Personnel Risk Factors Sample Size Scanning Severity of illness Slice Stroke Technology Testing Texture The Cancer Imaging Archive Thick Training Trust United States National Institutes of Health Variant Vendor Visualization Work X-Ray Computed Tomography artificial intelligence algorithm cancer diagnosis chest computed tomography clinical risk clinical translation cohort comorbidity data sharing data standards demographics denoising diverse data experience image reconstruction imaging biomarker imaging modality improved low dose computed tomography lung cancer screening machine learning algorithm machine learning method machine learning model neural network novel quantitative imaging radiomics reconstruction restoration trustworthiness

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 various diseases. When extracting QIFs from computed tomography (CT) scans, computed values can vary based on differences in CT acquisition and reconstruction parameters, including radiation dose level, slice thickness, reconstruction kernel, and reconstruction method. The performance of artificial intelligence (AI) and machine learning (ML) models depends on the diversity of data on which the model was trained. Previous studies have shown the negative impact that differences in CT acquisition and reconstruction have on the reproducibility of radiomic feature values and the performance of AI/ML models. However, there is a dearth of real-world datasets that enable AI/ML developers and researchers can easily leverage to train and validate models that are robust to these differences. The objective of this supplement is to improve the AI/ML-readiness of real-world patient CT datasets, facilitating investigations into characterizing and mitigating the effect of variations in CT acquisition and reconstruction parameters. This project builds upon our parent R01 project (R01 EB031993, Computational Toolkit for Normalizing the Impact of CT Acquisition and Reconstruction on Quantitative Image Features), which aims to understand the effect of these variations on downstream AI/ML models and clinical tasks (e.g., nodule detection, stroke characterization) and develop effective methods for image harmonization. This project will bring together expertise in informatics, medical physics, and data/model sharing standards. In Aim 1, we will release an AI/ML-ready CT dataset of 200 chest CT scans of patients who underwent lung cancer screening and 100 non-contrast head CTs of patients with suspected stroke. Each scan will be reconstructed by varying dose, slice thickness, and kernel, resulting in over 30 different versions of the same scan. Scans will also be annotated (e.g., outlined nodule boundaries) and linked with clinical information (e.g., nodule characteristics, pathology-confirmed lung cancer diagnosis). Following FAIR principles, clinical data, scans, and annotations will be released using established common data elements and standards such as DICOM segmentation objects. In Aim 2, we will demonstrate the utility of this dataset as a benchmark for assessing the reliability and robustness of AI/ML algorithms. We will use the benchmark CT dataset to evaluate the performance of publicly available algorithms for lung nodule detection and characterization and ischemic volume estimation. We will assess the robustness of these algorithms’ performance using metrics such as sensitivity and false positives/scan (nodule detection), area under the receiver operating characteristic curve (nodule classification), and mean absolute error (stroke quantification) across different scans. Successful completion of this project will result in a unique dataset that would double the available real-world patient data that can be used to improve AI/ML algorithms related to image reconstruction, restoration/harmonization, and downstream tasks.

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。从计算中提取 QIF 时，对各种疾病进行检测、诊断和治疗评估。断层扫描 (CT) 扫描，计算值可能会根据 CT 采集和重建的差异而变化参数，包括辐射剂量水平、切片厚度、重建核和重建方法。人工智能 (AI) 和机器学习 (ML) 模型的性能取决于数据的多样性之前的研究表明 CT 差异会产生负面影响。采集和重建对放射组学特征值的再现性和性能有影响然而，AI/ML 模型缺乏支持 AI/ML 开发人员和研究人员的现实数据集。可以轻松地利用来训练和验证对这些差异具有鲁棒性的模型。补充是为了提高现实世界患者 CT 数据集的 AI/ML 就绪性，促进对以下问题的调查该项目描述并减轻 CT 采集和重建参数变化的影响。建立在我们的父 R01 项目（R01 EB031993，用于标准化 CT 影响的计算工具包定量图像特征的获取和重建），旨在了解这些特征的效果下游 AI/ML 模型和临床任务（例如结节检测、中风特征）的变化以及开发图像协调的有效方法该项目将汇集信息学方面的专业知识，在目标 1 中，我们将发布一个包含 200 个 AI/ML 的 CT 数据集。接受肺癌筛查的患者的胸部 CT 扫描和 100 例患者的非增强头部 CT 扫描每次扫描都将通过不同的剂量、切片厚度和内核进行重建，从而产生同一扫描的 30 多个不同版本也将被注释（例如，概述的结节边界）和与临床信息（例如结节特征、病理证实的肺癌诊断）相关联。遵循 FAIR 原则，临床数据、扫描和注释将使用已建立的通用数据发布元素和标准，例如 DICOM 分割对象，在目标 2 中，我们将演示其实用性。我们将使用数据集作为评估 AI/ML 算法的可靠性和鲁棒性的基准。基准 CT 数据集，用于评估公开可用的肺结节检测算法的性能我们将评估这些算法的稳健性。使用灵敏度和误报/扫描（结节检测）、区域下面积等指标来衡量性能受试者工作特征曲线（结节分类）和平均绝对误差（中风量化）成功完成该项目将产生一个独特的数据集，该数据集将翻倍。可用的真实世界患者数据，可用于改进与图像重建相关的 AI/ML 算法，恢复/协调和下游任务。

项目成果

期刊论文数量（2）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Assessing variability in non-contrast CT for the evaluation of stroke: the effect of CT image reconstruction conditions on AI-based CAD measurements of ASPECTS value and hypodense volume

评估用于评估中风的非对比 CT 变异性：CT 图像重建条件对基于 AI 的 ASPECTS 值和低密度体积 CAD 测量的影响

DOI：
10.1117/12.3006582
发表时间：
2024-02-01
期刊：
影响因子：
0
作者：
Spencer Well;G. H. J. Kim;Anil Yadav;John M. Hoffman;William Hsu;Matthew S. Brown;E. Tavakkol;K. Nael;M. McNitt
通讯作者：
M. McNitt

Expanding Role of Advanced Image Analysis in CT-detected Indeterminate Pulmonary Nodules and Early Lung Cancer Characterization.

先进图像分析在 CT 检测不确定肺结节和早期肺癌表征中的扩大作用。