Brain phantom generation by generative adversarial net (GAN) for AI-based emission tomography

通过生成对抗网络 (GAN) 生成脑模型，用于基于人工智能的发射断层扫描

基本信息

批准号：
10466967
负责人：
Wenyi Shao
金额：
$ 8.19万
依托单位：
JOHNS HOPKINS UNIVERSITY
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：
2021-08-10 至 2023-05-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10466967
关键词：
Abdomen Address Affect Artificial Intelligence Biological Markers Brain Cancer Biology Cardiac Cerebrum Classification Collimator Computer Analysis Computer Vision Systems Corpus striatum structure Data Development Diagnosis Discipline of Nuclear Medicine Disease Educational Status Effectiveness Future Generations Goals Human Image Imaging Techniques Intervention Investigation Label Learning Limb structure Machine Learning Magnetic Resonance Imaging Maps Medical Medical Imaging Medical Research Methods Monitor Morphologic artifacts Nerve Degeneration Noise Organ Output Parkinson Disease Patients Performance Perfusion Persons Physics Population Positron-Emission Tomography Procedures Publishing Research Resolution Scheme Speed System Time Training Training Support Transplantation United States Vascular Diseases Water Width Work attenuation base bone cancer imaging data access design digital digital imaging dopaminergic neuron generative adversarial network heart imaging image guided image reconstruction improved interest nervous system disorder neural network neurotransmission nigrostriatal degeneration putamen radiotracer reconstruction reduce symptoms simulation single photon emission computed tomography tomography tool uptake virtual

项目摘要

Project Summary Positron emission tomography (PET) and single photon emission computed tomography (SPECT) are useful functional medical imaging techniques that can be performed to evaluate brain functions such as regional cerebral perfusion and neurotransmission. The spatial resolution of reconstruction for PET is usually 3-6 mm, and for SPECT is only 1-2 cm. Motivated by the latest advances in artificial intelligence (AI)/machine learning (ML) and its successful application to MRI and CT, it is highly desirable to develop an ML-based system for PET/SPECT cerebral image reconstruction (one of our specific interests is Parkinson disease) to achieve higher resolution and lower noise than using conventional approaches. However, to develop such a learning system, ground-truth data (accurate images, used as the labels) that guide the training are unavailable from the the real world. Published ML systems for PET imaging have used reconstructed images from conventional methods as the label to guide the training. As a result, the goal was only targeted to improve reconstruction speed, rather than improving the image quality. Since the quality of reconstructed image by ML system cannot exceed the guiding images, the performance of ML system cannot surpass conventional methods. Therefore, in this project, we propose a two-year project that will use conditional generative adversarial networks (GAN) to generate digital 2-D human brain phantoms, which will be highly similar to real human brains. The generated phantoms will serve as the (precise) ground-truth data to develop ML-based PET/SPECT reconstruction systems (our future research). The generated phantoms will contain an activity image and an attenuation map. Hence, results from this work can be used for simulating brain PET or SPECT examinations for various neurological disorders, and neural network can be trained with known ground truth. In addition, designing ML systems often relies on large amounts of data, but it is not easy to access data from a large number of patients in the US for specific medical research (mature ML systems developed for computer vision and image classification often involve images on the million level for training). Existing ML systems developed for MRI, CT, and PET imaging often merely uses a few tens of patient data for training and even less data to validate. Therefore, those systems are high-likely overfitted to the data used in training. With the generation system proposed from this project, we can produce a large phantom population to avoid the overfitting problem when design the AI image-reconstruction system. Once the GAN system is successfully developed, it can be easily transplanted to phantom generation for the AI-based CT and AI-based MRI. The method is also potentially extendable to generate phantom populations of torso, abdomen, and extremities for simulating cardiac imaging, tumor imaging, etc.

项目概要正电子发射断层扫描 (PET) 和单光子发射计算机断层扫描 (SPECT) 很有用功能医学成像技术可用于评估大脑功能，例如区域性功能脑灌注和神经传递。 PET重建的空间分辨率通常为3-6毫米， SPECT 仅为 1-2 厘米。受到人工智能 (AI)/机器学习最新进展的推动（ML）及其在 MRI 和 CT 中的成功应用，非常需要开发一种基于 ML 的系统 PET/SPECT 脑图像重建（我们的具体兴趣之一是帕金森病）以实现更高的与传统方法相比，分辨率和噪声更低。然而，要开发这样一个学习系统，指导训练的地面实况数据（准确的图像，用作标签）无法从真实数据中获得世界。已发布的用于 PET 成像的 ML 系统使用了传统方法的重建图像：指导训练的标签。因此，目标只是提高重建速度，而不是而不是提高图像质量。由于ML系统重建图像的质量不能超过引导图像，ML系统的性能无法超越传统方法。因此，在这个项目中，我们提出了一个为期两年的项目，该项目将使用条件生成对抗网络（GAN）生成数字二维人脑模型，与真实的人脑高度相似。这生成的模型将作为（精确的）真实数据来开发基于 ML 的 PET/SPECT 重建系统（我们未来的研究）。生成的模型将包含一个活动图像和一个衰减图。因此，这项工作的结果可用于模拟大脑 PET 或 SPECT 检查对于各种神经系统疾病，神经网络可以用已知的事实进行训练。此外，设计 ML 系统通常依赖于大量数据，但访问大量数据并不容易美国进行特定医学研究的患者数量（为计算机视觉和图像开发的成熟机器学习系统）分类通常涉及百万级图像进行训练）。现有的 ML 系统是为 MRI、CT、 PET 成像通常仅使用几十个患者数据进行训练，甚至更少的数据进行验证。因此，这些系统很可能过度拟合训练中使用的数据。随着生成系统从这个项目中提出，我们可以产生大量的幻像群体来避免过度拟合问题在设计AI图像重建系统时。一旦GAN系统开发成功，就可以轻松移植到基于 AI 的 CT 和基于 AI 的 MRI 的体模生成。该方法也有潜力可扩展以生成躯干、腹部和四肢的模型群来模拟心脏成像，肿瘤影像学等

项目成果

期刊论文数量（4）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Dielectric Breast Phantoms by Generative Adversarial Network.

DOI：
10.1109/tap.2021.3121149
发表时间：
2022-08
期刊：
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
影响因子：
5.7
作者：
Shao, Wenyi;Zhou, Beibei
通讯作者：
Zhou, Beibei

Generation of Digital Brain Phantom for Machine Learning Application of Dopamine Transporter Radionuclide Imaging.

DOI：
10.3390/diagnostics12081945
发表时间：
2022-08-12
期刊：
DIAGNOSTICS
影响因子：
3.6
作者：
Shao, Wenyi;Leung, Kevin H.;Xu, Jingyan;Coughlin, Jennifer M.;Pomper, Martin G.;Du, Yong
通讯作者：
Du, Yong

Near-Field Microwave Scattering Formulation by A Deep Learning Method.