在临床动态F-FDG全身PET中使用模拟数据驱动的机器学习算法进行Ki参数成像的可行性
Wenjian Gu1,2, Weiping Liu3,1, Wentong Yang1,4
1United Imaging Healthcare Group Co., Ltd, Shanghai, China.
Medical physics
|October 12, 2025
概括
这项研究引入了一种新的模拟数据方法,用于从缩短时间的正子发射断层扫描 (PET) 扫描中生成准确的动力参数 (Ki) 图像. 这种方法显著提高了Ki图像的可靠性,并减少了对广泛的现实世界数据收集的需求.
科学领域:
- 核医学就是核医学.
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 动力参数 (Ki) 成像提供了高的诊断准确性,但受到长时间扫描时间的限制.
- 目前用于Ki成像的机器学习方法需要大量的现实世界数据进行训练.
研究的目的:
- 研究一种基于模拟数据的策略,用于高效的临床Ki参数成像,缩短扫描时间.
- 克服现有的机器学习模型对K图像生成的数据依赖.
主要方法:
- 通过使用帕特拉克方程和K-Means集群生成模拟PET数据,其噪声水平可变.
- 在模拟数据集上训练 XGBoost 模型,从短时间 (50-60 分钟) 的 PET 扫描中预测 Ki 值.
- 使用模拟和现实世界的动态全身PET数据验证了该方法,与传统的帕特拉克方法进行了比较.
主要成果:
- 使用包括噪声在内的模拟数据进行训练显著提高了Ki值的准确性.
- 拟议的方法在现实数据上比传统的帕特拉克方法取得了更高的性能 (皮尔森的r=0.94对0.42,NMSE=0.11对5.33).
- 与帕特拉克方法相比,实现了更高的峰值信号噪声比率 (64.32比47.87).
结论:
- 一种基于模拟数据的方法可用于从临床F-FDG动态全身PET扫描中生成可靠的Ki图像.
- 这种方法有效地减少了对昂贵的真实世界数据采集的依赖.
- 可实现高效的Ki成像,缩短扫描时间.
相关概念视频
Positron Emission Tomography
6.8K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
6.8K
Imaging Studies II: Positron Emission Tomography and Scintigraphy
456
Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET
Fundamental Principles of PET
456


