Deep Learning Reconstruction for Improved TOF PET Using Histo-Image Partitioning

使用组织图像分区进行深度学习重建以改进 TOF PET

基本信息

批准号：
10610950
负责人：
SAMUEL MATEJ
金额：
$ 59.85万
依托单位：
UNIVERSITY OF PENNSYLVANIA
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-07-01 至 2025-03-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10610950
关键词：
3-Dimensional Address Algorithms Application procedure Archives Area Breast Case Study Clinical Clinical Data Data Dedications Detection Development Diagnostic Diagnostic Imaging Discipline of Nuclear Medicine Disease Dose Evaluation Explosion Geometry Goals Half-Life Image Imaging Techniques Intervention Interventional Imaging Investigation Isotopes Label Lung Methods Modeling Modernization Monitor Morphologic artifacts Motion Organ Patients Performance Physics Positron Positron-Emission Tomography Procedures Property Protocols documentation Psychological Transfer Public Health Radiation Dose Unit Research Resolution Running Scanning System Techniques Testing Time Tracer Training Training Technics Validation Work accurate diagnosis assessment application breast imaging cellular imaging chimeric antigen receptor T cells clinical efficacy clinically relevant convolutional neural network data modeling deep learning denoising detector disease diagnosis efficacy evaluation heart motion improved innovation instrumentation learning network loss of function molecular imaging neural network neural network architecture novel novel strategies personalized medicine proton therapy radiotracer reconstruction response solid state statistics success tomography tool treatment response

项目摘要

Project Summary Clinical and research applications of the PET imaging are rapidly expanding from ever improving diagnostic and treatment assessment applications to guidance of personalized treatments, ultra-low dose imaging, and even interventional imaging procedures. Supporting these developments, reconstruction tools that are able to reliably handle both typical and (ultra-)low count situations, imperfect data, and data from specialized imaging geometries, with fast (near real-time) reconstruction performance are of crucial importance. The overall goal of this project is to develop and investigate robust and efficacious Deep Learning (DL) reconstruction approaches addressing these needs. A unique and innovative feature of the proposed approaches (compared to alternative DL applications) is the utilization of list-mode data histogrammed into a very efficient histo-image format. TOF data partitioned into the histo-image format are characterized by strong local properties, thus perfectly fitting convolutional neural network formalism and making DL training and reconstruction directly from realistic clinical data (in size and character) highly feasible and practical. The clinical utility of PET systems has significantly improved over the years thanks to advances in instrumentation, data corrections, and reconstruction approaches. Nevertheless, full utilization of their potential through robust and fast quantitative reconstruction remains a challenge especially for the cases of very low count data, such as in low-count temporal (motion and dynamic) frames, delayed studies, longitudinal low-dose studies, and studies using new isotopes with long half-life and low positron fraction rates (e.g. in 89Zr-labeled CAR-T cell imaging), as well as in specialized PET systems with partial angular coverage, for which exact, artifact-free, reconstruction does not exist. These are the situations for which the developed DL approaches promise great potential due to the demonstrated success of the DL networks to be trained for imperfect and very low count data without reliance on accurate data models. Furthermore, pre-trained networks can provide ultra- fast, near real-time, performance in practical use. Specific Aim 1 will develop tools for DL PET reconstruction using histo-image partitioning along with procedures for training of the proposed DL approaches, including novel approaches advancing the state-of-the- art of DL reconstruction directly from acquired PET data. Specific Aim 2 is directed towards study and evaluation of the performance of the investigated DL approaches for whole-body and long axial FOV scanner data for the wide range of counts from applications such as typical FDG, low dose, delayed, low activity isotope scans, and ultra-short frames in motion correction and dynamic studies. Specific Aim 3 will develop and apply motion correction protocols involving the proposed DL reconstruction tools and test and study their efficacy for clinically realistic situations involving non-rigid lung and heart motions. And finally, Specific Aim 4 is dedicated to an application and study of the developed DL approaches to specialized PET systems with partial angular coverage. 1

项目概要 PET 成像的临床和研究应用随着诊断的不断改进而迅速扩展和治疗评估应用程序，以指导个性化治疗、超低剂量成像和甚至介入成像程序。支持这些发展的重建工具能够可靠地处理典型和（超）低计数情况、不完美数据以及来自专业成像的数据具有快速（近实时）重建性能的几何图形至关重要。总体目标为该项目旨在开发和研究稳健且有效的深度学习 (DL) 重建方法解决这些需求。所提出的方法的独特和创新特征（与替代方法相比）深度学习应用程序）是利用列表模式数据直方图绘制成非常有效的组织图像格式。飞行时间划分为 histo-image 格式的数据具有很强的局部属性，因此完美拟合卷积神经网络形式主义，直接从现实临床进行深度学习训练和重建数据（大小和特征）高度可行和实用。多年来，由于技术进步，PET 系统的临床实用性得到了显着提高。仪器、数据校正和重建方法。尽管如此，充分发挥他们的潜力通过稳健和快速的定量重建仍然是一个挑战，特别是对于计数非常低的情况数据，例如低计数时间（运动和动态）帧、延迟研究、纵向低剂量研究，以及使用具有长半衰期和低正电子分数率的新同位素的研究（例如 89Zr 标记的同位素） CAR-T 细胞成像），以及具有部分角度覆盖的专用 PET 系统，为此，无伪影，重建不存在。这些是开发的深度学习方法所针对的情况由于 DL 网络已被证明能够成功地针对不完美和非常严重的问题进行训练，因此有望带来巨大的潜力低计数数据，不依赖准确的数据模型。此外，预训练网络可以提供超快速、接近实时、实际使用中的性能。具体目标 1 将开发使用组织图像分区进行 DL PET 重建的工具拟议的深度学习方法的培训程序，包括推进现状的新方法直接从采集的 PET 数据进行 DL 重建的艺术。具体目标 2 旨在研究和评估所研究的 DL 方法针对全身和长轴 FOV 扫描仪数据的性能典型 FDG、低剂量、延迟、低活性同位素扫描等应用的广泛计数运动校正和动态研究中的超短帧。具体目标 3 将开发和应用运动涉及所提出的 DL 重建工具的校正方案，并测试和研究其临床功效涉及非刚性肺和心脏运动的现实情况。最后，具体目标 4 致力于将已开发的深度学习方法应用于具有部分角度覆盖的专用 PET 系统。 1