Towards building advanced machine learning image translation models to estimate Amyloid-Beta and Tau PET images from structural MRI

致力于构建先进的机器学习图像翻译模型，以估计来自结构 MRI 的淀粉样蛋白-Beta 和 Tau PET 图像

• 批准号: 580342-2022
• 负责人: MacDonald, MatthewEthanME
• 金额: $ 3.64万
• 依托单位: University of Calgary
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=746121
• 关键词: Towards; building; advanced; machine; learning

Image-translation is an advanced form of machine learning. It can be used to generate high-cost images from lower-cost inputs. Alzheimer's Disease is the most common type of dementia, impacting tens of millions of people worldwide. A popular hypothesis proposes Amyloid-Beta and Tau are the main causes of Alzheimer's Disease, aggregating in the brain forming the well-known 'plaques.' These plaques have been visible on microscopes from the brains of post-mortem demented patients for over a hundred years, and more recently can be visualized with PET imaging in-vivo. PET imaging is, however, a very expensive test to run ($3000-to-$8000), relative to a conventional structural MRI ($500). It is also more invasive requiring injection of a radiation inducing tracer and blood sampling during the procedure. Furthermore, the tracers and technologies are not available in all jurisdictions (Very limited use in Alberta!). MRI has the advantage of being more affordable and accessible, it is less invasive, however it does not provide the same detailed molecular information as PET data. Previous studies indicate there is mutual information relating Amyloid-Beta and Tau PET and structural MRI. This project will utilize machine learning to translate structural MRI images to Amyloid-Beta and Tau PET images. Key preliminary work has already been completed, including gathering of the required data, obtaining institutional ethics approval, and building a 2D proof-of-concept model. Aim 1: Develop a Simple 3D U-Net Model that is Capable of PET Estimation; Aim 2: Improve Model Performance with Cost Functions and 3D GAN; Aim 3: Implement Vision Transformer GAN and compare with CNN-GAN. The impact of obtaining Amyloid-Beta and Tau PET images from basic MRI is important for the early detection of Alzheimer's disease. This would facilitate a method for screening, as repeat MRI is very practical and safe, while repeat PET is associated with radiation exposure and the injection of radiation inducing tracer. A notable valuable proposition once refined and validated. Advances in quantitative image translation could be applied to many other high value applications.

图像翻译是机器学习的一种高级形式。 它可用于从低成本输入生成高成本图像。 阿尔茨海默病是最常见的痴呆症，影响着全世界数千万人。 一种流行的假设认为，β 淀粉样蛋白和 Tau 蛋白是阿尔茨海默病的主要原因，它们在大脑中聚集形成众所周知的“斑块”。 一百多年来，这些斑块在死后的痴呆患者大脑中都可以在显微镜下看到，最近可以通过体内 PET 成像来观察。 然而，相对于传统的结构 MRI（500 美元），PET 成像是一项非常昂贵的测试（3000 至 8000 美元）。 它也更具侵入性，需要在手术过程中注射辐射诱导示踪剂和血液采样。 此外，追踪器和技术并非在所有司法管辖区都可用（在艾伯塔省使用非常有限！）。 MRI 的优点是更便宜、更容易获得，侵入性较小，但它不能提供与 PET 数据相同的详细分子信息。 先前的研究表明，β 淀粉样蛋白和 Tau PET 以及结构 MRI 之间存在相互信息。 该项目将利用机器学习将结构 MRI 图像转换为 Amyloid-Beta 和 Tau PET 图像。关键的前期工作已经完成，包括收集所需数据、获得机构伦理批准以及构建二维概念验证模型。 目标 1：开发一个能够进行 PET 估计的简单 3D U-Net 模型；目标 2：利用成本函数和 3D GAN 提高模型性能；目标 3：实现 Vision Transformer GAN 并与 CNN-GAN 进行比较。 从基础 MRI 中获取淀粉样蛋白-β 和 Tau PET 图像对于阿尔茨海默病的早期检测非常重要。 这将有利于筛查方法，因为重复 MRI 非常实用且安全，而重复 PET 与辐射暴露和注射辐射诱导示踪剂有关。 一旦完善和验证，这是一个值得注意的有价值的主张。 定量图像翻译的进步可以应用于许多其他高价值应用。