SynthRCT: Scalable Conditional Deformation Synthesis for Synthetic Repeat CT Generation

Overview of the SynthRCT method

RCTSynth learns a patient-specific distribution of plausible anatomical deformations from longitudinal thoracic CT images. Given a single moving CT volume, the model samples an anatomy-conditioned latent code, decodes it into a stationary velocity field, integrates it into a dense displacement field, and warps the input to produce a synthetic repeat CT.

The model uses a conditional variational registration architecture with a full-volume anatomy-conditioned prior and a memory-aware slab decoder. It supports patient-specific deformation sampling, latent-space traversal, and the export of warped CT volumes, stationary velocity fields, and displacement fields.

This repository contains the official rctsynth.ckpt weights. The checkpoint was trained on paired thoracic 4DCT images from the DIR-Lab 4DCT dataset, with case ID 0 reserved for validation. The training data are not redistributed here and remain subject to the dataset provider's terms.

The complete implementation, preprocessing instructions, inference notebook, and configuration are available in the RCTSynth GitHub repository.

The checkpoint is intended for research and has not been validated for clinical decision-making, diagnosis, treatment planning, or dose calculation.

License

The RCTSynth model weights are released under the MIT License. This license does not grant rights to the DIR-Lab training data or other third-party datasets.

Citation

Coming soon.

References

  1. Castillo, E., Castillo, R., Martinez, J., Shenoy, M., & Guerrero, T. (2010). Four-dimensional deformable image registration using trajectory modeling. Physics in Medicine and Biology, 55(1), 305–327. https://doi.org/10.1088/0031-9155/55/1/018.

  2. Castillo, R., Castillo, E., Guerra, R., Johnson, V. E., McPhail, T., Garg, A. K., & Guerrero, T. (2009). A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets. Physics in Medicine and Biology, 54(7), 1849–1870. https://doi.org/10.1088/0031-9155/54/7/001.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support