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

• 批准号: 10293006
• 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
• 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/10293006
• 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; 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; heart imaging; image guided; image reconstruction; improved; interest; nervous system disorder; neural network; neurotransmission; putamen; radiotracer; reconstruction; reduce symptoms; simulation; single photon emission computed tomography; tomography; tool; uptake; virtual; 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; 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; heart imaging; image guided; image reconstruction; improved; interest; nervous system disorder; neural network; neurotransmission; putamen; radiotracer; reconstruction; reduce symptoms; simulation; single photon emission computed tomography; tomography; tool; uptake; virtual

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.

项目摘要 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 可以执行的功能医学成像技术来评估大脑功能，例如区域 脑灌注和神经传递。 PET重建的空间分辨率通常为3-6 mm， SPECT仅为1-2厘米。受人工智能（AI）/机器学习的最新进展的动机 （ML）及其成功应用于MRI和CT，非常需要开发基于ML的系统 PET/SPECT脑图像重建（我们的特定兴趣之一是帕金森病）以实现更高的 分辨率和较低的噪声比使用常规方法。但是，要开发这样的学习系统， 从真实的角度来指导训练的地面真相数据（准确的图像，用作标签）。 世界。发布的用于PET成像的ML系统已使用常规方法重建的图像作为 指导培训的标签。结果，目标仅针对提高重建速度，而是 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 指导图像，ML系统的性能无法超越常规方法。因此，在这个项目中， 我们提出了一个为期两年的项目，该项目将使用有条件的生成对抗网络（GAN） 产生数字二维人脑幻像，这将与真实的人类大脑高度相似。这 生成的幻影将用作（精确的）基础真实数据，以开发基于ML的PET/SPECT 重建系统（我们的未来研究）。生成的幻影将包含活动图像和一个 衰减图。因此，这项工作的结果可用于模拟脑宠物或SPECT检查 对于各种神经系统疾病，可以用已知的地面真理训练神经网络。此外， 设计ML系统通常依赖大量数据，但是从大量访问数据并不容易 美国的患者进行特定的医学研究（成熟的ML系统用于计算机视觉和图像 分类通常涉及在百万级上进行培训的图像）。现有为MRI，CT开发的ML系统 PET成像通常仅使用几十个患者数据进行培训，甚至更少的数据来验证。 因此，这些系统很可能过多地适合培训中使用的数据。与发电系统 该项目提出的建议，我们可以生产大量的幻影人群以避免过度拟合问题 设计AI图像重建系统时。一旦成功开发了GAN系统，就可以 轻松地将基于AI的CT和基于AI的MRI移植到幻影生成。该方法也可能是 可扩展以产生躯干，腹部和四肢的幻影种群，以模拟心脏成像， 肿瘤成像等