High-Fidelity 3D Lung CT Synthesis in ARDS Swine Models Using Score-Based 3D Residual Diffusion Models

TL;DR

This paper presents a novel score-based 3D residual diffusion model that synthesizes high-fidelity 3D lung CT images from 2D X-ray images, potentially improving ARDS diagnosis and management without the need for direct CT scans.

Contribution

The study introduces a new deep learning method for generating 3D lung CT images from 2D X-ray images using score-based residual diffusion models, addressing practical limitations in ARDS imaging.

Findings

High-quality 3D CT images synthesized from 2D X-rays

Validation against ground truth confirms accuracy

Potential to improve ARDS diagnosis and treatment

Abstract

Acute respiratory distress syndrome (ARDS) is a severe condition characterized by lung inflammation and respiratory failure, with a high mortality rate of approximately 40%. Traditional imaging methods, such as chest X-rays, provide only two-dimensional views, limiting their effectiveness in fully assessing lung pathology. Three-dimensional (3D) computed tomography (CT) offers a more comprehensive visualization, enabling detailed analysis of lung aeration, atelectasis, and the effects of therapeutic interventions. However, the routine use of CT in ARDS management is constrained by practical challenges and risks associated with transporting critically ill patients to remote scanners. In this study, we synthesize high-fidelity 3D lung CT from 2D generated X-ray images with associated physiological parameters using a score-based 3D residual diffusion model. Our preliminary results demonstrate that this approach can produce high-quality 3D CT images that are validated with ground truth, offering a promising solution for enhancing ARDS management.