Scholarlink

Purpose: <p>Internal anatomical motion challenges precise radiation delivery during external beam radiotherapy. Estimating and compensating for anatomical motion are essential for improving planned dose delivery to target volumes while sparing organs-at-risk. This research achieves accurate motion prediction using only planar X-ray imaging from conventional linear accelerators, without surrogate signals or invasive fiducial markers.</p> Methods: <p>We propose Deep-Motion-Net: a patient-specific end-to-end graph neural network (GNN) enabling 3D volumetric organ reconstruction from single in-treatment kV planar X-ray images at arbitrary projection angles. A 2D convolutional neural network (CNN) encoder extracts image features, which four feature pooling networks fuse to a 3D template organ mesh. A ResNet-based graph attention network then deforms the feature-encoded mesh. Training uses synthetically generated organ motion instances and corresponding kV images, created by deforming a reference CT volume aligned with the template mesh, generating digitally reconstructed radiographs (DRRs) at required angles, and applying DRR-to-kV style transfer via conditional CycleGAN.</p> Results: <p>Quantitative testing on synthetic respiratory motion scenarios and qualitative assessment on in-treatment images from four liver cancer patients demonstrated overall mean prediction errors of 0.16&#xa0;±&#xa0;0.13 mm, 0.18&#xa0;±&#xa0;0.19 mm, 0.22&#xa0;±&#xa0;0.34 mm, and 0.12&#xa0;±&#xa0;0.11 mm across datasets. Mean peak prediction errors were 1.39 mm, 1.99 mm, 3.29 mm, and 1.16 mm.</p> Conclusion: <p>This approach leverages accessible in-treatment imaging, avoiding expensive MRI systems or invasive markers. To the best of our knowledge, this is the first deep learning framework reconstructing volumetric 3D organ models from single-view images at arbitrary angles throughout an entire in-treatment scan series. Our approach achieves sub-millimetre accuracy when validated on synthetic motion instances and demonstrates clinical feasibility on real-treatment kV images, for which volumetric ground truth is inherently unavailable. The code is available at <a href="https://github.com/isurusuranga/DeepMotionNet">https://github.com/isurusuranga/DeepMotionNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep-Motion-Net: GNN-based volumetric liver shape reconstruction from single-view 2D projections

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月13日

查看全文
  • Isuru Wijesinghe,
  • Michael Nix,
  • Arezoo Zakeri,
  • Alireza Hokmabadi,
  • Bashar Al-Qaisieh,
  • Ali Gooya,
  • Zeike Taylor

摘要

Purpose:

Internal anatomical motion challenges precise radiation delivery during external beam radiotherapy. Estimating and compensating for anatomical motion are essential for improving planned dose delivery to target volumes while sparing organs-at-risk. This research achieves accurate motion prediction using only planar X-ray imaging from conventional linear accelerators, without surrogate signals or invasive fiducial markers.

Methods:

We propose Deep-Motion-Net: a patient-specific end-to-end graph neural network (GNN) enabling 3D volumetric organ reconstruction from single in-treatment kV planar X-ray images at arbitrary projection angles. A 2D convolutional neural network (CNN) encoder extracts image features, which four feature pooling networks fuse to a 3D template organ mesh. A ResNet-based graph attention network then deforms the feature-encoded mesh. Training uses synthetically generated organ motion instances and corresponding kV images, created by deforming a reference CT volume aligned with the template mesh, generating digitally reconstructed radiographs (DRRs) at required angles, and applying DRR-to-kV style transfer via conditional CycleGAN.

Results:

Quantitative testing on synthetic respiratory motion scenarios and qualitative assessment on in-treatment images from four liver cancer patients demonstrated overall mean prediction errors of 0.16 ± 0.13 mm, 0.18 ± 0.19 mm, 0.22 ± 0.34 mm, and 0.12 ± 0.11 mm across datasets. Mean peak prediction errors were 1.39 mm, 1.99 mm, 3.29 mm, and 1.16 mm.

Conclusion:

This approach leverages accessible in-treatment imaging, avoiding expensive MRI systems or invasive markers. To the best of our knowledge, this is the first deep learning framework reconstructing volumetric 3D organ models from single-view images at arbitrary angles throughout an entire in-treatment scan series. Our approach achieves sub-millimetre accuracy when validated on synthetic motion instances and demonstrates clinical feasibility on real-treatment kV images, for which volumetric ground truth is inherently unavailable. The code is available at https://github.com/isurusuranga/DeepMotionNet.