使用混合CNN转换器合成器和注册网络的多站点CBCT到CT翻译的联合学习框架
Ying Hu1,2, Mengjie Cheng3, Hui Wei4
1School of Mathematics and Statistics, Hubei University of Education, Wuhan, Hubei, China.
Frontiers in oncology
|August 23, 2024
概括
一种新的深度学习模型SynREG通过生成合成CT (sCT) 图像和纠正解剖错位,提高了适应性辐射疗法 (ART) 的形束计算断层扫描 (CBCT) 图像质量.
科学领域:
- 医疗成像医学成像
- 医疗保健中的人工智能
- 辐射瘤学 辐射瘤学
背景情况:
- 圆束计算断层扫描 (CBCT) 在适应性辐射疗法 (ART) 中提供了方便,但其图像质量不佳.
- 提高CBCT图像质量对于改善不同解剖部位的ART疗效至关重要.
研究的目的:
- 开发一个统一的深度学习模型,以持续提高CBCT图像质量.
- 从各种解剖位置的CBCT数据生成高保真度合成CT (sCT) 图像.
主要方法:
- 一个监督学习框架,SynREG,是使用对联CBCT和计划CT图像的数据集开发的,来自135名癌症患者.
- SynREG集成了用于sCT生成的混合CNN变压器和用于纠正局部结构错位的注册网络.
- 模型的性能与基准模型进行了评估,并评估其对自细分精度的影响.
主要成果:
- SynREG显著提高了CBCT图像质量,将平均绝对误差 (MAE) 降至16.81 ± 8.42 HU,并将结构相似度指数 (SSIM) 提高到94.34 ± 2.85%.
- 该模型有效地抑制了噪音和文物,特别有利于低对比度器官.
- 自分化的准确性大大提高,大脑干的Dice相似系数 (DSC) 从0.61增加到0.89.
结论:
- SynREG有效地解决对联数据集中的残余解剖差异,提高CBCT图像质量.
- 该模型显示了通过优越的图像质量和细分精度来改善图像导向放射治疗的巨大潜力.
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...