循环H-CUT:基于循环一致性和混合对比学习的无监督医疗图像翻译方法
Weiwei Jiang1, Yingyu Qin1, Xiaoyan Wang1
1College of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, People's Republic of China.
Physics in medicine and biology
|February 5, 2025
概括
这项研究介绍了CycleH-CUT,这是一种无监督的医学图像翻译方法,可以减少文物. 它使用混合对比学习和循环一致性有效地翻译未配对的医疗图像.
科学领域:
- 医学成像医学成像
- 人工智能的人工智能是人工智能.
- 计算机视觉 计算机视觉 计算机视觉
背景情况:
- 由于缺乏配对数据,无监督的医学图像翻译具有挑战性.
- 现有的基于CycleGAN的方法可以在翻译图像中生成文物.
研究的目的:
- 提出一个无监督网络,CycleH-CUT,用于医疗图像翻译中的工件减少.
- 提高医疗图像翻译的质量和可靠性.
主要方法:
- 开发了CycleH-CUT,将混合对比无偶翻译 (H-CUT) 与循环一致性集成在一起.
- H-CUT利用了查询选择的注意力机制,并增强了对比性学习损失.
- 光谱正常化增强了训练稳定性和特征提取.
主要成果:
- 循环H-CUT在多个数据集 (BraTS,OASIS3,IXI,脊柱) 中显示出有效性.
- 实现了高的结构相似性指数 (SSIM) 评分:0.926 (BraTS),0.796 (OASIS3),0.932 (IXI) 和0.890 (脊柱). 在这个过程中,我们可以获得高的分数.
结论:
- 循环H-CUT成功地解决了在无监督医疗图像翻译中的文物生成问题.
- 拟议的方法为高质量的未配对医疗图像翻译提供了强大的解决方案.
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...