基于人工智能的联合衰减和散射校正策略,用于多标志物全身PET
Hao Sun1,2,3,4, Yanchao Huang5, Debin Hu6
1School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China.
EJNMMI physics
|July 19, 2024
概括
这项研究展示了一种新的AI方法,用于精确的PET图像校正,减少CT扫描辐射暴露. 这种深度学习方法可以改善全身PET成像对多个标记物的成像.
科学领域:
- 医疗成像医学成像
- 人工智能在医学中的应用
- 核医学就是核医学.
背景情况:
- 目前用于PET减弱和散射校正 (ASC) 的低剂量CT带来辐射风险和文物问题.
- 基于CT的ASC (CT-ASC) 在PET和CT数据之间可能存在不匹配.
- 在图像领域的直接ASC提供了一个潜在的替代方案来降低CT剂量.
研究的目的:
- 通过深度学习方法证明直接减弱和散射校正 (ASC) 的可行性,用于多追踪器全身PET.
- 评估不同培训策略,用于图像域ASC的3D条件生成对抗网络 (cGAN).
- 为了减少与全身PET/CT检查中的CT扫描相关的辐射剂量.
主要方法:
- 对[18F]FDG,[18F]FAPI和[68Ga]FAPI的临床uEXPLORER全身PET/CT数据集的回顾性分析.
- 开发一个改进的3D cGAN,直接从未经校正的 (NASC) PET 图像中估计校正的 PET 图像.
- 使用四种培训策略进行验证:集中 (CZ-ASC),特定于追踪器 (DL-ASC),无微调 (NFT-ASC) 和微调 (FT-ASC),以CT-ASC作为参考.
主要成果:
- 在所有标志物中,CZ-ASC,DL-ASC和FT-ASC的视觉质量与CT-ASC相当.
- 所有经过测试的深度学习方法 (CZ-ASC,DL-ASC,FT-ASC) 在定量准确性 (NMAE) 中显著超过了NASC和NFT-ASC.
- 与DL-ASC相比,CZ-ASC和FT-ASC在交叉追踪器全身PET减弱校正方面表现优越.
结论:
- 使用拟议的3D cGAN的直接ASC对于多标记器全身PET是可行的,准确的和强大的.
- 这种基于深度学习的ASC方法有效地减少了冗余CT检查带来的辐射危险.
- 集中式 (CZ-ASC) 和微调式 (FT-ASC) 策略在全身PET减弱校正中有望提高交叉追踪器性能.
相关概念视频
Positron Emission Tomography
4.1K
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...
4.1K
Imaging Studies II: Positron Emission Tomography and Scintigraphy
105
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
105


