Researchers have developed SynthRCT, a novel framework for generating synthetic 4D computed tomography (4DCT) images, which are crucial for evaluating the robustness of proton therapy treatment plans. This conditional generative model, based on a conditional variational autoencoder, learns to synthesize realistic anatomical deformations. SynthRCT can generate these transformations at scale, enabling more comprehensive patient-specific variability analysis beyond simplified scenarios. AI
IMPACT Enables more robust AI-driven treatment planning in medical imaging by providing realistic synthetic data.
RANK_REASON The cluster contains a research paper detailing a new method for synthetic data generation. [lever_c_demoted from research: ic=1 ai=1.0]
- 4DCT
- arXiv
- computed tomography
- conditional variational autoencoder
- Hugging Face
- proton therapy
- SynthRCT
- Tomás Guija Valiente
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →