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

2025-10-21

AI Summary

Generating high-fidelity, anatomically accurate, and computationally efficient 3D chest CT volumes remains challenging. Method: We propose a conditional latent diffusion model that jointly incorporates a global lung-structure mask and a local nodule mask as dual anatomical priors, enabling fine-grained control over both lung parenchyma and nodules. Contribution/Results: This dual-mask guidance significantly improves anatomical plausibility—mitigating structural distortions observed when using nodule masks alone—while maintaining high generation diversity and fidelity. The model efficiently synthesizes high-resolution 256×256×256-voxel CT volumes on a single mid-tier GPU, substantially reducing hardware requirements. Quantitative and qualitative evaluations confirm stable generation of anatomically correct, diverse, and realistic CT volumes. The method demonstrates practical utility for AI model training and clinical education, offering a scalable solution for synthetic medical imaging data generation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

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.

Problem

• Generates 3D chest CT scans from anatomical masks
• Reduces computational cost for volumetric image synthesis
• Enables controlled generation of lung nodules and structures

Innovation

• Latent diffusion model generates 3D chest CT scans
• Conditioning on anatomical masks controls output features
• Synthesizes high-resolution volumes using single GPU