相关实验视频

Updated: Jun 8, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

通过混合相似度度和基于CycleGAN的自动细分来提高可变形图像注册的准确性

Keyur D Shah^1,2,3, James A Shackleford², Nagarajan Kandasamy²

¹Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA 30322.

|December 9, 2024

概括

结合CycleGAN自分割和点对距离得分的混合相似度指标显著改善了适应性辐射疗法 (ART) 的可变形图像记录 (DIR) 准确性. 这种人工智能驱动的方法增强软组织对比度和器官对齐,这对于精确的治疗提供至关重要.

科学领域:

医疗成像医学成像
放射治疗物理物理
人工智能在医学中的应用

背景情况:

可变形图像注册 (DIR) 对于适应性辐射疗法 (ART) 是必不可少的,以考虑到治疗期间的解剖学变化.
传统的基于强度的DIR方法与强度不平等的图像作斗争,限制了准确性.
混合相似度指标,结合强度和结构信息,可以提高DIR性能.

研究的目的:

使用混合图像相似度指标,评估可变形图像注册 (DIR) 的准确性.
为了利用CycleGAN进行强度校正和解剖结构的自动分割.
为了比较三个DIR工作流程的性能:传统的基于强度,CycleGAN自动细分和专家手动细分.

主要方法:

开发了一个混合相似度指标,整合了点对距离 (PD) 和强度相似度得分.
合成CT (sCT) 图像使用2D CycleGAN模型生成,以改善CBCT软组织对比度.
在三个工作流程中使用子相似系数 (DSC),95%的豪斯多夫距离 (HD) 和信托分离来评估DIR准确性.

主要成果:

混合相似度指标显著提高了前列腺,膀和直肠的DIR精度.
前列腺DSC从0.61 (没有PD) 增加到0.82 (CycleGAN PD) 和0.89 (专家PD).
前列腺的95%的HD从11.75毫米减少到4.86毫米 (CycleGAN PD) 和3.27毫米 (专家PD).

结论:

结合基于CycleGAN的自动细分的混合相似度指标为ART中的DIR准确性提供了有前途的进步.
将人工智能驱动的图像校正和自动细分与经典的DIR技术相结合,可以大大提高处理精度.
拟议的方法证明了其稳定性和在适应性辐射治疗中改善患者治疗结果的潜力.

关键词:

适应性辐射疗法适应性辐射疗法自动细分可以实现.循环GANAN是一个循环.可变形图像注册变形图像注册

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

相关概念视频

Improving Translational Accuracy

Improving 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...

Improving Translational Accuracy

Improving 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...