analiza aiqbench
SynthRCT introduces a scalable conditional generative framework using a variational autoencoder to synthesize patient-specific anatomical deformations for proton therapy robustness evaluation. By learning a latent deformation space, the method generates complex, plausible 3D transformations that surpass simplified perturbation scenarios in medical imaging workflows. This approach directly advances machine learning applications in specialized healthcare domains by enabling more rigorous testing of treatment plans against realistic anatomical variability.
SynthRCT: Scalable Conditional Deformation Synthesis for Synthetic Repeat CT Generation
arXiv:2609.08627v1 Announce Type: cross Abstract: In proton therapy, plans are typically optimized on a single planning CT, making robustness evaluation essential under anatomical changes. However, current scenarios often rely on simplified perturbations that poorly capture complex, patient-specific variability. We propose SynthRCT, a scalable conditional generative framework for 3D anatomical deformation synthesis. Based on a conditional variational autoencoder, SynthRCT learns a latent deformation space and decodes sampled latent codes into local stationary velocity fields conditioned on an input anatomy. Local fields are assembled into coherent full-volume transformations, enabling memory-scalable generation for large field-of-view CT data. We validate the approach on respiratory 4DCT data with multiple breathing-phase anatomies per subject. SynthRCT enables patient-specific sampling of plausible anatomical transformations beyond predefined robustness scenarios. Code available at: https://github.com/TomasGuija/SynthRCT.
Abstract:In proton therapy, plans are typically optimized on a single planning CT, making robustness evaluation essential under anatomical changes. However, current scenarios often rely on simplified perturbations that poorly capture complex, patient-specific variability. We propose SynthRCT, a scalable conditional generative framework for 3D anatomical deformation synthesis. Based on a conditional variational autoencoder, SynthRCT learns a latent deformation space and decodes sampled latent codes into local stationary velocity fields conditioned on an input anatomy. Local fields are assembled into coherent full-volume transformations, enabling memory-scalable generation for large field-of-view CT data. We validate the approach on respiratory 4DCT data with multiple breathing-phase anatomies per subject. SynthRCT enables patient-specific sampling of plausible anatomical transformations beyond predefined robustness scenarios. Code available at: this https URL.
11 pages, 4 figures. Accepted at the MIART Workshop, MICCAI 2026. This preprint corresponds to the initial submission prior to peer review
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2609.08627 [cs.CV]
(or arXiv:2609.08627v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.08627 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 246 cuvinte
Subiecte conexe
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · 28 iul. 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026
News
Quantum Computing Report · 7 iun. 2026
Synthetic Data Generation for Financial AI Research with NVIDIA NeMo
NVIDIA · 9 iul. 2026