Logo image
Back
Lung-DDPM+: Efficient thoracic CT image synthesis using diffusion probabilistic model
Journal article   Peer reviewed

Lung-DDPM+: Efficient thoracic CT image synthesis using diffusion probabilistic model

Yifan Jiang, Ahmad Shariftabrizi and Venkata S.K. Manem
Computers in biology and medicine, Vol.199, 111290
12/2025
DOI: 10.1016/j.compbiomed.2025.111290
PMID: 41270520
url
https://arxiv.org/pdf/2508.09327View
Open Access

Abstract

Generative artificial intelligence (AI) has been playing an important role in various domains. Leveraging its high capability to generate high-fidelity and diverse synthetic data, generative AI is widely applied in diagnostic tasks, such as lung cancer diagnosis using computed tomography (CT). However, existing generative models for lung cancer diagnosis suffer from low efficiency and anatomical imprecision, which limit their clinical applicability. To address these drawbacks, we propose Lung-DDPM+, an improved version of our previous model, Lung-DDPM. This novel approach is a denoising diffusion probabilistic model (DDPM) guided by nodule semantic layouts and accelerated by a pulmonary DPM-solver, enabling the method to focus on lesion areas while achieving a better trade-off between sampling efficiency and quality. Evaluation results on the public LIDC-IDRI dataset suggest that the proposed method achieves 8× fewer FLOPs (floating point operations per second), 6.8× lower GPU memory consumption, and 14× faster sampling compared to Lung-DDPM. Moreover, it maintains comparable sample quality to both Lung-DDPM and other state-of-the-art (SOTA) generative models in two downstream segmentation tasks. We also conducted a Visual Turing Test by an experienced radiologist, showing the advanced quality and fidelity of synthetic samples generated by the proposed method. These experimental results demonstrate that Lung-DDPM+ can effectively generate high-quality thoracic CT images with lung nodules, highlighting its potential for broader applications, such as general tumor synthesis and lesion generation in medical imaging. The code and pretrained models are available at https://github.com/Manem-Lab/Lung-DDPM-PLUS. •Novel diffusion model for lung nodule synthesis in 3D thoracic CT scans.•Pulmonary DPM-solver is proposed to improve sampling efficiency.•Solving the common anatomical imprecision issues of SOTA generative models.•Up to 8× lower FLOPs, 6.8× lower GPU memory usage, 14× faster sampling compared to competitors.•Advanced performance in a radiologist-verified Visual Turing Test and segmentation tasks.
 Computed Tomography Lung Cancer Denoising diffusion probabilistic models Image synthesis Lung nodule segmentation

Details

Metrics

8 Record Views
Logo image