X-WIN: Building Chest Radiograph World Model via Predictive Sensing

TL;DR

X-WIN is a novel chest X-ray world model that learns 3D anatomical structures from CT data to improve disease diagnosis and image understanding, using predictive sensing and contrastive alignment.

Contribution

It introduces a new approach to learn 3D anatomical knowledge from CT to enhance CXR analysis and reconstruction, integrating real CXRs with simulated data.

Findings

Outperforms existing models on downstream tasks

Effective in few-shot and linear probing scenarios

Capable of reconstructing 3D volumes from 2D projections

Abstract

Chest X-ray radiography (CXR) is an essential medical imaging technique for disease diagnosis. However, as 2D projectional images, CXRs are limited by structural superposition and hence fail to capture 3D anatomies. This limitation makes representation learning and disease diagnosis challenging. To address this challenge, we propose a novel CXR world model named X-WIN, which distills volumetric knowledge from chest computed tomography (CT) by learning to predict its 2D projections in latent space. The core idea is that a world model with internalized knowledge of 3D anatomical structure can predict CXRs under various transformations in 3D space. During projection prediction, we introduce an affinity-guided contrastive alignment loss that leverages mutual similarities to capture rich, correlated information across projections from the same volume. To improve model adaptability, we incorporate real CXRs into training through masked image modeling and employ a domain classifier to encourage statistically similar representations for real and simulated CXRs. Comprehensive experiments show that X-WIN outperforms existing foundation models on diverse downstream tasks using linear probing and few-shot fine-tuning. X-WIN also demonstrates the ability to render 2D projections for reconstructing a 3D CT volume.