Optimization of diagnostic accuracy, radiation dose, and patient throughput for cardiac SPECT via advanced and clinically practical cardiac-respiratory motion correction and deep learning

通过先进且临床实用的心肺运动校正和深度学习，优化心脏 SPECT 的诊断准确性、辐射剂量和患者吞吐量

• 批准号: 10685488
• 负责人: Michael A King
• 金额: $ 77.33万
• 依托单位: ILLINOIS INSTITUTE OF TECHNOLOGY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-01 至 2025-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10685488
• 关键词: 3-Dimensional; 4D Imaging; Accounting; Address; Advocate; Algorithms; American; Cardiac; Clinic; Clinical; Compensation; Computer software; Coronary Arteriosclerosis; Data; Defect; Development; Diagnosis; Diagnostic; Disease; Dose; Effectiveness; Elderly; Electromagnetic Energy; Evaluation; Exposure to; Functional Imaging; Goals; Health Care Costs; Image; Imaging Techniques; Institution; Left Ventricular Function; Life Expectancy; Measures; Mechanics; Medical Imaging; Methods; Modality; Morphologic artifacts; Motion; Myocardial perfusion; Noise; Nuclear; Obesity; Patients; Performance; Perfusion; Photons; Play; Population; Prevalence; Protocols documentation; Radiation Dose Unit; Radiation exposure; Reader; Recommendation; Resolution; Risk; Role; Scanning; Signal Transduction; Societies; System; Task Performances; Techniques; Technology; Time; Translating; Validation; Visualization; Work; X-Ray Computed Tomography; attenuation; base; cardiac single photon emission computed tomography; clinical care; cost; deep learning; denoising; denoising deep learning; diagnostic accuracy; heart motion; hemodynamics; image processing; image reconstruction; imaging modality; imaging system; improved; innovation; obese patients; perfusion imaging; preservation; prognostic; quantum; radiation risk; radiologist; reconstruction; respiratory; single photon emission computed tomography; tool; visual tracking

Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is widely used to detect and evaluate coronary artery disease. The goal of this project is to reduce the radiation dose and/or scan time of SPECT MPI by a combined factor of 16x, while maintaining or increasing diagnostic accuracy. This would enable SPECT MPI to be performed, e.g., with 4x reduced radiation dose and 4x shorter scan time (~2.5 minutes) than typical protocols. Radiation dose in SPECT MPI has been recognized as an important issue, accounting for ~25% of all radiation exposure to patients in medical imaging. Dose reduction particularly addresses the increased prevalence of obese patients (who receive higher dose) and younger cardiac patients (whose radiation risk is higher due to longer life expectancy). Reduction in scan time would improve comfort for elderly and infirm cardiac patients, while mitigating body-motion image artifacts and reducing healthcare costs by increasing clinical throughput. We will reduce dose and scan time through innovative image reconstruction methods that involve little or no cost and require no additional patient setup steps. We will employ new respiratory and cardiac motion compensation to reduce image artifacts, as well as new deep learning techniques, which will be used for both respiratory-signal estimation and high-performance denoising. We will methodically optimize these techniques and then validate our algorithms in multicenter clinical reader studies. SA1: Develop clinically practical respiratory motion surrogates for low-count studies. T1: Perfect data- driven respiratory surrogate estimation; T2: Optimize data-driven surrogate estimation at reduced counts; T3: Develop and clinically validate depth-sensing cameras for respiratory and body-motion surrogate estimation; T4: Generalization of data-driven surrogate estimation to SPECT systems not having a CT. SA2: Develop deep-learning reconstruction methods and optimize for diagnostic accuracy and dose/scan time. T1: Post-reconstruction DL denoising algorithms for 3D perfusion images for reduced-count and standard- count studies; T2: DL denoising algorithms for 4D cardiac-gated studies; T3: 4D reconstruction with embedded DL denoising, cardiac motion estimation and correction; and T4: DL reconstruction methods with both RMC and CMC, with projection data binned using respiratory surrogate signals derived in SA1. SA3: Perform multicenter clinical reader studies (6 clinicians, 3 institutions) to validate the new algorithms and compare to current clinically-available methods based on diagnostic performance and repeatability in assessing both perfusion and wall motion defects. T1: In comparison to baseline clinical reconstruction, evaluate added benefit of: a) including attenuation and scatter correction, and b) additionally including RMC; T2: Validate DL for improvement of perfusion and function (wall motion) task performance at full-count levels; and T3: Validate DL for improvement of task performance at reduced counts.

单光子发射计算机断层扫描（SPECT）心肌灌注成像（MPI）广泛应用 检测和评估冠状动脉疾病。该项目的目标是减少辐射剂量和/或 SPECT MPI 的扫描时间缩短了 16 倍，同时保持或提高了诊断准确性。这 将使 SPECT MPI 能够执行，例如，辐射剂量减少 4 倍，扫描时间缩短 4 倍（~2.5 分钟）比典型协议。 SPECT MPI 中的辐射剂量已被认为是重要的 问题，约占医学成像中患者所有辐射暴露的 25%。减少剂量 特别解决了肥胖患者（接受较高剂量）和年轻人患病率增加的问题 心脏病患者（由于预期寿命较长，其辐射风险较高）。减少扫描时间 将提高老年和体弱心脏病患者的舒适度，同时减轻身体运动图像 通过提高临床吞吐量来减少人工制品并降低医疗成本。我们将减少剂量和扫描时间 通过创新的图像重建方法，成本很少或没有成本，并且不需要额外的 患者设置步骤。我们将采用新的呼吸和心脏运动补偿来减少图像 伪影以及新的深度学习技术，将用于呼吸信号估计 和高性能去噪。我们将有条不紊地优化这些技术，然后验证我们的 多中心临床读者研究中的算法。 SA1：为低计数研究开发临床实用的呼吸运动替代指标。 T1：完美数据- 驱动呼吸替代估计； T2：以减少的计数优化数据驱动的替代估计； T3： 开发并临床验证用于呼吸和身体运动替代估计的深度传感相机； T4：将数据驱动的替代估计推广到没有 CT 的 SPECT 系统。 SA2：开发深度学习重建方法并优化诊断准确性和剂量/扫描 时间。 T1：用于减少计数和标准的 3D 灌注图像的重建后 DL 去噪算法 计数研究； T2：用于 4D 心脏门控研究的 DL 去噪算法； T3：嵌入的 4D 重建 DL去噪、心脏运动估计与校正； T4：使用 RMC 的 DL 重建方法 和 CMC，使用 SA1 中导出的呼吸替代信号对投影数据进行分箱。 SA3：进行多中心临床读者研究（6 名临床医生，3 个机构）以验证新的 算法并根据诊断性能与当前临床可用的方法进行比较 评估灌注和室壁运动缺陷的可重复性。 T1：与基线临床相比 重建，评估以下附加好处：a) 包括衰减和散射校正，以及 b) 另外 包括RMC； T2：验证深度学习以改善灌注和功能（室壁运动）任务表现 全计数级别； T3：验证深度学习以减少数量来提高任务性能。

项目成果

Improving detection accuracy of perfusion defect in standard dose SPECT-myocardial perfusion imaging by deep-learning denoising.

通过深度学习去噪提高标准剂量SPECT心肌灌注成像中灌注缺损的检测精度。

• 发表时间: 2022-10
• 作者: Liu, Junchi;Yang, Yongyi;Wernick, Miles N;Pretorius, P Hendrik;Slomka, Piotr J;King, Michael A
• 通讯作者: King, Michael A

Data-driven respiratory signal estimation from temporally finely sampled projection data in conventional cardiac perfusion SPECT imaging.

根据传统心脏灌注 SPECT 成像中时间精细采样的投影数据进行数据驱动的呼吸信号估计。

• 发表时间: 2022-01
• 影响因子: 3.8
• 作者: Pretorius, P Hendrik;King, Michael A
• 通讯作者: King, Michael A

Observer studies of image quality of denoising reduced-count cardiac single photon emission computed tomography myocardial perfusion imaging by three-dimensional Gaussian post-reconstruction filtering and deep learning.

通过三维高斯重建后滤波和深度学习对去噪减数心脏单光子发射计算机断层扫描心肌灌注成像图像质量的观察者研究。

• 发表时间: 2023-12
• 作者: Pretorius, P Hendrik;Liu, Junchi;Kalluri, Kesava S;Jiang, Yulei;Leppo, Jeffery A;Dahlberg, Seth T;Kikut, Janusz;Parker, Matthew W;Keating, Friederike K;Licho, Robert;Auer, Benjamin;Lindsay, Clifford;Konik, Arda;Yang, Yongyi;Wernick, Miles N
• 通讯作者: Wernick, Miles N

A cadaveric breast cancer tissue phantom for phase-contrast X-ray imaging applications.

用于相衬 X 射线成像应用的尸体乳腺癌组织模型。

• 发表时间: 2023-10
• 作者: Rounds, Cody C;Li, Chengyue;Zhou, Wei;Tichauer, Kenneth M;Brankov, Jovan G
• 通讯作者: Brankov, Jovan G

Respiratory signal estimation for cardiac perfusion SPECT using deep learning.

使用深度学习估计心脏灌注 SPECT 的呼吸信号。

• DOI: 10.1002/mp.16653
• 发表时间: 2023-07-31
• 期刊: Medical physics
• 影响因子: 3.8
• 作者: Yuan Chen;P. Pretorius;C. Lindsay;Yongyi Yang;Matt A. King
• 通讯作者: Matt A. King