Nonlinear performance analysis and prediction for robust low dose lung CT

鲁棒低剂量肺部 CT 的非线性性能分析和预测

• 批准号: 10570160
• 负责人: Jianan Grace Gang
• 金额: $ 50.07万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10570160
• 关键词: 3D Print; Address; Adoption; Algorithms; Anatomy; Appearance; Beauty; Behavior; Biological Models; Clinic; Clinical; Complex; Data; Databases; Dependence; Derivation procedure; Development; Diagnostic; Dictionary; Digital Libraries; Dimensions; Dose; Ensure; Evaluation; Image; Image Analysis; Imaging Techniques; Lead; Lesion; Libraries; Lung; Lung CAT Scan; Lung nodule; Machine Learning; Measures; Medical Imaging; Methods; Modeling; Nodule; Noise; Non-linear Models; Outcome; Output; Patients; Performance; Play; Predictive Analytics; Property; Protocols documentation; Radiation Dose Unit; Research; Role; Sampling; Scanning; Scheme; Shapes; Signal Transduction; Source; Statistical Models; System; Techniques; Technology; Texture; Training; Transcend; Work; X-Ray Computed Tomography; clinical application; clinical translation; clinically relevant; data-driven model; deep learning; deep learning algorithm; deep neural network; design; flexibility; imaging system; improved; insight; interest; low dose computed tomography; lung cancer screening; lung lesion; machine learning method; neural network; novel; predicting response; public database; quantitative imaging; radiomics; reconstruction; response; screening; shape analysis; simulation; success; targeted imaging

1 PROJECT SUMMARY / ABSTRACT 2 Nonlinear algorithms such as model-based reconstruction (MBR) and deep learning (DL) reconstruction have 3 sparked tremendous research interest in recent years. Compared to traditional linear approaches, the nonline- 4 arity of these algorithm transcends traditional signal-to-noise requirement and offer flexibility to draw information 5 from a variety of sources (e.g., statistical model, prior image, dictionary, training data). MBR has enabled numer- 6 ous advancements including low-dose CT and advanced scanning protocols. Deep learning algorithms are rap- 7 idly emerging and have demonstrated superior dose vs. image quality tradeoffs in research settings. However, 8 widespread clinical adoption of nonlinear algorithms has been impeded by the lack of a lack of systematic, quan- 9 titative methods for performance analysis. Nonlinear methods come with numerous dependencies on the imag- 10 ing techniques, the imaging target, and the prior information, and the data itself. The relationship between these 11 dependencies and image quality is often opaque. Furthermore, improper selection of algorithmic parameters can 12 lead to erroneous features (e.g., smaller lesions, texture) in the reconstruction. Therefore, methods to quantify 13 and predict performance permit efficient and quantifiable performance evaluation to provide the robust control 14 and understanding of imaging output necessary for reliable clinical application and regulatory oversight. 15 We propose to establish a robust, predictive framework for performance assessment and optimization that can 16 be generalized to any reconstruction method. We quantify performance in turns of the perturbation response and 17 covariance as a function of imaging techniques, system configurations, patient anatomy, and, importantly, the 18 perturbation itself. The perturbation response quantifies the appearance (e.g., biases, blurs, distortions), and, 19 together with the covariance, allows the computation of more complex metrics such as task-based performance 20 and radiomic measures including size, shape, and texture information. We illustrate utility of the approach in lung 21 imaging with the following specific aims: Aim 1: Develop a lesion library and generate perturbations encom- 22 passing clinically relevant features. We will extract lesions from public databases and develop methods lesion 23 emulation in for realistic CT simulation and physical data via 3D printing technology. Aim 2: Develop a gener- 24 alized prediction framework for perturbation response and covariance. Using analytical and neural network 25 modeling, we will establish a framework that predicts perturbation response and covariance across imaging 26 scenarios for classes of algorithms with increasing data-dependence including MBR with a Huber penalty, MBR 27 with dictionary regularization, and a deep learning reconstructor. Aim 3: Develop assessment and optimiza- 28 tion strategies to drive robust, low dose lung screening CT methods. We will optimize and adapt nonlinear 29 algorithms and protocols for lung cancer screening to achieve faithful representations of clinical features. This 30 work has the potential to drive much-needed quantitative assessment standards that directly relate image quality 31 to diagnostic performance and optimal strategies for robust, reliable clinical deployment of nonlinear algorithms. 32

1 项目摘要 /摘要 2种非线性算法，例如基于模型的重建（MBR）和深度学习（DL）重建 3近年来引发了极大的研究兴趣。与传统的线性方法相比 4这些算法的Arity超出了传统的信噪要求，并提供了灵活性来绘制信息 5来自各种来源（例如，统计模型，先验图像，字典，培训数据）。 MBR启用了Numer- 6 OUS的进步，包括低剂量CT和高级扫描协议。深度学习算法是说唱 - 7闲散，并在研究环境中表现出了优越的剂量与图像质量折衷。然而， 8由于缺乏系统的，quan- 9个表达分析的代价方法。非线性方法具有许多对想象的依赖性 10 ING技术，成像目标和先前的信息以及数据本身。这些之间的关系 11依赖项和图像质量通常是不透明的。此外，算法参数的不当选择可以 12导致重建中的错误特征（例如，较小的病变，纹理）。因此，量化的方法 13并预测绩效允许有效且可量化的绩效评估以提供强大的控制 14以及对可靠的临床应用和调节监督所需的成像输出的理解。 15我们建议为绩效评估和优化建立一个可靠的预测框架 16被概括为任何重建方法。我们在扰动响应的转弯和 17协方差作为成像技术，系统构型，患者解剖学的函数，重要的是 18扰动本身。扰动响应量化了外观（例如，偏见，模糊，失真），以及 19与协方差一起，允许计算更复杂的指标，例如基于任务的性能 20和放射线措施，包括大小，形状和纹理信息。我们说明了肺中该方法的实用性 21具有以下特定目的的成像：目标1：开发病变库并产生扰动 - 22通过临床相关的特征。我们将从公共数据库中提取病变并开发方法病变 23通过3D打印技术进行现实的CT模拟和物理数据仿真。目标2：开发一个 24摄动响应和协方差的Alized预测框架。使用分析和神经网络 25建模，我们将建立一个框架，以预测成像跨成像的扰动响应和协方差 26个以增加数据依赖性的算法类别的方案 27具有字典的正则化和深度学习重建器。目标3：制定评估和优化 - 28策略，以驱动稳健的低剂量肺筛查CT方法。我们将优化和适应非线性 29算法和肺癌筛查方案，以实现临床特征的忠实表示。这 30工作有可能推动急需的定量评估标准，直接将图像质量关联 31诊断性能和最佳策略，可靠，可靠，可靠的非线性算法临床部署。 32