MedSyn2 generates controllable high-resolution 3D CT volumes using optional text prompts and partial semantic segmentation masks via a modified diffusion transformer with gated attention.
Maisi-v2: Accelerated 3d high-resolution medical image synthesis with rectified flow and region-specific contrastive loss.arXiv preprint arXiv:2508.05772
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
CRAFT adapts diffusion models to medical images via clinical reward alignment from LLMs and VLMs, improving alignment scores and cutting low-quality generations by 20.4% on average across modalities.
DiffKT3D transfers priors from video diffusion models to 3D radiotherapy dose prediction via modality-specific embeddings and clinically guided RL, reducing voxel MAE from 2.07 to 1.93 and claiming SOTA over the GDP-HMM challenge winner.
Training-free guidance of a pretrained 3D rectified flow model enables weakly-supervised lung nodule segmentation using only image-level labels and produces improved results on the LUNA16 dataset.
WFDM uses wavelet-fusion VAE and conditional latent diffusion to generate synthetic multimodal brain MRI, claiming strongest distributional alignment among evaluated generators.
citing papers explorer
-
MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts
MedSyn2 generates controllable high-resolution 3D CT volumes using optional text prompts and partial semantic segmentation masks via a modified diffusion transformer with gated attention.
-
CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis
CRAFT adapts diffusion models to medical images via clinical reward alignment from LLMs and VLMs, improving alignment scores and cutting low-quality generations by 20.4% on average across modalities.
-
Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study
DiffKT3D transfers priors from video diffusion models to 3D radiotherapy dose prediction via modality-specific embeddings and clinically guided RL, reducing voxel MAE from 2.07 to 1.93 and claiming SOTA over the GDP-HMM challenge winner.
-
Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
Training-free guidance of a pretrained 3D rectified flow model enables weakly-supervised lung nodule segmentation using only image-level labels and produces improved results on the LUNA16 dataset.
-
Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning
WFDM uses wavelet-fusion VAE and conditional latent diffusion to generate synthetic multimodal brain MRI, claiming strongest distributional alignment among evaluated generators.