X-ray2CTPA: Leveraging Diffusion Models to Enhance Pulmonary Embolism Classification

TL;DR

This paper introduces a diffusion-based AI model that translates 2D chest X-rays into 3D CTPA scans, improving pulmonary embolism classification and potentially making advanced diagnostics more accessible and cost-effective.

Contribution

The paper presents a novel diffusion model for cross-modal translation from X-ray to CTPA, enhancing diagnostic accuracy and generalizability in medical imaging.

Findings

Improved AUC in PE classification using synthesized 3D images

Qualitative feedback from radiologists supports diagnostic relevance

Model demonstrates potential for other cross-modality translations

Abstract

Chest X-rays or chest radiography (CXR), commonly used for medical diagnostics, typically enables limited imaging compared to computed tomography (CT) scans, which offer more detailed and accurate three-dimensional data, particularly contrast-enhanced scans like CT Pulmonary Angiography (CTPA). However, CT scans entail higher costs, greater radiation exposure, and are less accessible than CXRs. In this work we explore cross-modal translation from a 2D low contrast-resolution X-ray input to a 3D high contrast and spatial-resolution CTPA scan. Driven by recent advances in generative AI, we introduce a novel diffusion-based approach to this task. We evaluate the models performance using both quantitative metrics and qualitative feedback from radiologists, ensuring diagnostic relevance of the generated images. Furthermore, we employ the synthesized 3D images in a classification framework and show improved AUC in a PE categorization task, using the initial CXR input. The proposed method is generalizable and capable of performing additional cross-modality translations in medical imaging. It may pave the way for more accessible and cost-effective advanced diagnostic tools. The code for this project is available: https://github.com/NoaCahan/X-ray2CTPA .