文献速递胸部技术与安全CT

基于小样本学习的4DCT可变形图像配准

Few-shot learning for deformable image registration in 4DCT images.
PubMed 文献 · Br J Radiol · 2021-10-18

本研究开发了一种基于深度学习的小样本配准网络FR-Net,用于从各呼吸相位生成到隐式参考图像的形变矢量场,以减少参考图像选择偏倚。在DIR-Lab和POPI胸部4DCT数据集上评估,最大吸气与呼气相间的平均目标配准误差分别为1.48 mm和1.16 mm,优化一个4DCT约需2分钟,在配准精度和计算时间上优于现有方法。

要点

  • FR-Net在DIR-Lab和POPI数据集上平均目标配准误差为1.48 mm和1.16 mm
  • 优化一个4DCT扫描约需2分钟,计算效率高
  • 采用组配准和小样本学习策略,减少参考图像选择偏倚

核心结论

  • FR-Net是一种用于4DCT图像的小样本组配准算法,配准性能好且计算高效,有望用于在线自适应放疗的配准任务。

研究设计与样本

  • 本研究为方法学研究,提出基于深度学习的小样本配准网络FR-Net,使用有限无标签4D数据预训练,并通过最大化特定4DCT扫描的强度相似性进行优化。
  • 在胸部4DCT数据集DIR-Lab和POPI上评估4D组配准和3D成对配准性能。

诊断标准与关键数值

  • 在DIR-Lab和POPI数据集上,最大吸气与呼气相之间的平均目标配准误差分别为1.48 mm和1.16 mm。
  • 优化一个4DCT扫描约需2分钟。

临床应用与阅片要点

  • FR-Net可用于在线自适应放疗中4DCT的快速可变形配准,减少参考图像选择偏倚。
  • 组配准策略或有助于提高呼吸相位间配准的准确性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: To develop a rapid and accurate 4D deformable image registration (DIR) approach for online adaptive radiotherapy.

METHODS: We propose a deep learning (DL)-based few-shot registration network (FR-Net) to generate deformation vector fields from each respiratory phase to an implicit reference image, thereby mitigating the bias introduced by the selection of reference images. The proposed FR-Net is pretrained with limited unlabeled 4D data and further optimized by maximizing the intensity similarity of one specific four-dimensional computed tomography (4DCT) scan. Because of the learning ability of DL models, the few-shot learning strategy facilitates the generalization of the model to other 4D data sets and the acceleration of the optimization process.

RESULTS: The proposed FR-Net is evaluated for 4D groupwise and 3D pairwise registration on thoracic 4DCT data sets DIR-Lab and POPI. FR-Net displays an averaged target registration error of 1.48 mm and 1.16 mm between the maximum inhalation and exhalation phases in the 4DCT of DIR-Lab and POPI, respectively, with approximately 2 min required to optimize one 4DCT. Overall, FR-Net outperforms state-of-the-art methods in terms of registration accuracy and exhibits a low computational time.

CONCLUSION: We develop a few-shot groupwise DIR algorithm for 4DCT images. The promising registration performance and computational efficiency demonstrate the prospective applications of this approach in registration tasks for online adaptive radiotherapy.

ADVANCES IN KNOWLEDGE: This work exploits DL models to solve the optimization problem in registering 4DCT scans while combining groupwise registration and few-shot learning strategy to solve the problem of consuming computational time and inferior registration accuracy.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Chi W, Xiang Z, Guo F, et al. Few-shot learning for deformable image registration in 4DCT images. Br J Radiol. 2021. PMID: 34662242. doi:10.1259/bjr.20210819

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。