← Back to all news
arXiv Computer Vision By Can Zhao, Pengfei Guo, Dong Yang, Yufan He, Yucheng Tang, Ahmed Harouni, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu

NV-Generate-Body: 3D Latent Diffusion Model forControllable Anatomy, Tumor, and Demographic Body Mask Synthesis

Read the original on arXiv Computer Vision →

NV-Generate-BodyMask is a 3D latent diffusion model that generates whole-body CT segmentation masks with precise control over organ anatomy, tumor burden, and patient demographics. It operates in the compressed latent space of a frozen mask autoencoder, producing 256³ volumetric label maps conditioned on a 19‑dimensional vector via Adaptive Group Normalization and cross‑attention. Trained on 8,571 masks from 26 cohorts, the model achieves high Spearman correlations for organ size, excellent tumor recall for several lesion types, and strong demographic alignment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jul 8

CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training

arXiv:2607. 02998v2 Announce Type: replace-cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning.

By Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
llmsdiffusionreinforcement-learning
More like this →
arXiv AI
Jul 7

CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training

arXiv:2607. 02998v1 Announce Type: cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning.

By Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
llmsdiffusionreinforcement-learning
More like this →
arXiv AI
Sep 10

Diffusion Model in Latent Space for Medical Image Segmentation Task

The paper introduces MedSegLatDiff, a diffusion-based framework that combines a variational autoencoder (VAE) with a latent diffusion model for medical image segmentation. By compressing images into a low-dimensional latent space, the method reduces noise and speeds up training, while a weighted cross‑entropy loss preserves tiny structures such as small nodules. Evaluated on ISIC‑2018, CVC‑Clinic, and LIDC‑IDRI datasets, MedSegLatDiff achieves state‑of‑the‑art Dice and IoU scores, generates diverse segmentation hypotheses, and produces confidence maps that enhance interpretability and reliability for clinical deployment.

By Ngoc Huynh Trinh, Hai Toan Nguyen, Son Ba Luong, Quoc Long Tran
diffusioncomputer-visionsafety
More like this →