来自T1脑MRI的基于GAN的合成FDG PET图像可以用于提高深度无监督异常检测模型的性能
Daria Zotova1, Nicolas Pinon1, Robin Trombetta1
1INSA Lyon, Université Claude Bernard Lyon 1, CNRS, Inserm, CREATIS UMR 5220, U1294, Lyon, F-69621, France.
Computer methods and programs in biomedicine
|April 5, 2025
概括
生成对抗网络 (GAN) 从MRI扫描中创建现实的合成大脑[18F]氧糖 (FDG) PET图像. 这些合成图像有效地训练无监督异常检测模型用于病变检测.
科学领域:
- 医疗图像分析 医学图像分析
- 医疗保健中的人工智能
- 神经成像是一种神经成像.
背景情况:
- 生成对抗网络 (GAN) 显示出跨模态医疗图像翻译的前景,解决有限的多模态数据集.
- 很少有研究评估合成数据的基于任务的性能,用于训练深度学习模型.
研究的目的:
- 使用GANs从T1加权MRI生成合成大脑[18F]氧葡萄糖 (FDG) PET图像.
- 评估这些合成PET图像对于培训无监督异常检测 (UAD) 模型用于病变检测的实用性.
主要方法:
- 将T1MRI的各种GAN框架与FDG PET图像合成进行比较.
- 使用标准指标和新型诊断任务导向指标评估合成图像质量.
- 在真实和合成规范PET数据上训练了一种UAD模型 (罗式自编码器+OC-SVM).
- 在患者数据上比较UAD模型的性能.
主要成果:
- 最好的GAN模型生成了具有高SSIM (0.9) 和PSNR (23.8) 的真实合成PET图像.
- 在合成PET数据上训练的UAD模型在检测病变时获得了74%的灵敏度.
- 对于MR T1到FDG PET的转换,GANs的性能优于变压器和扩散模型.
结论:
- 基于GAN的模型是MR T1到FDG PET转换的最佳选择.
- 合成医学成像数据对于训练UAD模型具有诊断价值.
- 该研究提供了开源代码和规范图像数据集.
更多相关视频
10:04Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
Published on: September 5, 2017
18.7K
09:03Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
Published on: October 22, 2019
9.9K
相关概念视频
01:29Positron Emission Tomography
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 being...
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 being...
01:14Brain Imaging
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).