针对未配对跨模式医疗图像翻译的目标导向扩散模型
IEEE journal of biomedical and health informatics
|April 25, 2024
概括
这项研究引入了一种用于医学图像翻译的新型扩散模型,将CT或超声等缺失的模式从MRI等可用的模式中合成. 该方法提高了图像现实性和临床适用性,而无需配对数据.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 计算机视觉 计算机视觉
背景情况:
- 医学成像模式的获取可能受到成本和辐射暴露的限制.
- 未配对的交叉模式翻译对于合成无法使用的医疗图像类型至关重要.
- 已经使用了生成对抗网络 (GAN),但扩散模型提供了有前途的替代方案.
研究的目的:
- 提出一个目标导向扩散模型 (TGDM) 进行无配对交叉模式的医学图像翻译.
- 在培训期间使用感知优先重量 (P2W) 方案来增强视觉概念的学习.
- 通过在采样过程中减少源特定的工件来提高合成图像质量.
主要方法:
- 开发了一种新的目标引导扩散模型 (TGDM),用于未配对的交叉模式图像合成.
- 在培训目标中实施了感知优先权重 (P2W) 计划,以改善概念学习.
- 将预先训练的分类器集成到反向采样过程中,以减少模式特定的残留物.
主要成果:
- TGDM成功地在不同方式 (例如,MRI-to-CT,MRI-to-Ultrasound) 中合成了现实的医疗图像.
- 合成图像准确地描绘了解剖结构,模仿了目标模式.
- 主观评估证实了产生的图像的临床价值和视觉现实性.
结论:
- 拟议的TGDM有效地执行未配对的跨模式医疗图像翻译.
- P2W方案和分类器引导的采样提高了合成图像的质量和临床相关性.
- TGDM为特定的医学成像模式无法使用的情况提供了可行的解决方案.
相关概念视频
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...