Multi-View Transformers for Airway-To-Lung Ratio Inference on Cardiac CT Scans: The C4R Study

2025-01-15

AI Summary

Cardiac CT scans cover only ~2/3 of the lung volume and employ slice thicknesses 5–6× larger than standard pulmonary CT, severely impeding accurate quantification of the airway-to-lung ratio (ALR) across the entire lung. Method: We propose the first multi-view Swin Transformer model specifically designed for cardiac CT, trained via paired supervision using cardiac and full-lung CT, and guided by joint segmentation of lung parenchyma and airway trees to map low-resolution cardiac CT to high-fidelity, whole-lung ALR maps. Results: Validated on the MESA cohort, our method achieves ALR estimation accuracy comparable to that obtained from dedicated full-lung CT rescan—significantly outperforming direct regression baselines—while maintaining clinical interpretability and cross-scanner robustness. This work establishes a novel paradigm for large-scale epidemiological studies of COPD, severe COVID-19, and post-acute sequelae of SARS-CoV-2 infection (PASC) using widely available cardiac CT data.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The ratio of airway tree lumen to lung size (ALR), assessed at full inspiration on high resolution full-lung computed tomography (CT), is a major risk factor for chronic obstructive pulmonary disease (COPD). There is growing interest to infer ALR from cardiac CT images, which are widely available in epidemiological cohorts, to investigate the relationship of ALR to severe COVID-19 and post-acute sequelae of SARS-CoV-2 infection (PASC). Previously, cardiac scans included approximately 2/3 of the total lung volume with 5-6x greater slice thickness than high-resolution (HR) full-lung (FL) CT. In this study, we present a novel attention-based Multi-view Swin Transformer to infer FL ALR values from segmented cardiac CT scans. For the supervised training we exploit paired full-lung and cardiac CTs acquired in the Multi-Ethnic Study of Atherosclerosis (MESA). Our network significantly outperforms a proxy direct ALR inference on segmented cardiac CT scans and achieves accuracy and reproducibility comparable with a scan-rescan reproducibility of the FL ALR ground-truth.

Problem

• ALR Measurement
• Severe Pneumonia
• COVID-19 Complications

Innovation

• Swin Transformer
• ALR Estimation
• COVID-19 Pneumonia