LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Oliveras, Anna, Marí, Roger, Redondo, Rafael, Guardià, Oriol, Tost, Ana, Nagarajan, Bhalaji, Migliorelli, Carolina, Ribas, Vicent, Radeva, Petia
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911223758454784
author Oliveras, Anna
Marí, Roger
Redondo, Rafael
Guardià, Oriol
Tost, Ana
Nagarajan, Bhalaji
Migliorelli, Carolina
Ribas, Vicent
Radeva, Petia
author_facet Oliveras, Anna
Marí, Roger
Redondo, Rafael
Guardià, Oriol
Tost, Ana
Nagarajan, Bhalaji
Migliorelli, Carolina
Ribas, Vicent
Radeva, Petia
contents This work introduces a new latent diffusion model to generate high-quality 3D chest CT scans conditioned on 3D anatomical masks. The method synthesizes volumetric images of size 256x256x256 at 1 mm isotropic resolution using a single mid-range GPU, significantly lowering the computational cost compared to existing approaches. The conditioning masks delineate lung and nodule regions, enabling precise control over the output anatomical features. Experimental results demonstrate that conditioning solely on nodule masks leads to anatomically incorrect outputs, highlighting the importance of incorporating global lung structure for accurate conditional synthesis. The proposed approach supports the generation of diverse CT volumes with and without lung nodules of varying attributes, providing a valuable tool for training AI models or healthcare professionals.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18446
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance
Oliveras, Anna
Marí, Roger
Redondo, Rafael
Guardià, Oriol
Tost, Ana
Nagarajan, Bhalaji
Migliorelli, Carolina
Ribas, Vicent
Radeva, Petia
Computer Vision and Pattern Recognition
This work introduces a new latent diffusion model to generate high-quality 3D chest CT scans conditioned on 3D anatomical masks. The method synthesizes volumetric images of size 256x256x256 at 1 mm isotropic resolution using a single mid-range GPU, significantly lowering the computational cost compared to existing approaches. The conditioning masks delineate lung and nodule regions, enabling precise control over the output anatomical features. Experimental results demonstrate that conditioning solely on nodule masks leads to anatomically incorrect outputs, highlighting the importance of incorporating global lung structure for accurate conditional synthesis. The proposed approach supports the generation of diverse CT volumes with and without lung nodules of varying attributes, providing a valuable tool for training AI models or healthcare professionals.
title LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.18446