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

Wijesinghe, I.; Nix, M.; Zakeri, A.; Hokmabadi, A.; Al-Qaisieh, B.; Gooya, A.; Taylor, Z.

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

All Authors

Wijesinghe, I.

Nix, M.

Zakeri, A.

Hokmabadi, A.

Al-Qaisieh, B.

Gooya, A.

Taylor, Z.

LTHT Author

Nix, Michael
Al-Qaisieh, Bashar

LTHT Department

Oncology
Medical Physics & Engineering
Radiotherapy Physics

Contributor Profession (Non Medical)

Healthcare Scientist

Publication Date

2026

Item Type

Journal Article

Abstract

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 .