Single volume lung biomechanics from chest computed tomography using a mode preserving generative adversarial network

TL;DR

This paper introduces a generative adversarial network that estimates lung tissue expansion from a single CT scan, reducing the need for multiple scans and associated risks.

Contribution

It presents a novel GAN-based framework for direct tissue expansion estimation from single CT scans, bypassing traditional registration methods.

Findings

Achieved PSNR of 18.95 dB and SSIM of 0.840.

Correlated well with disease severity across 2500 subjects.

Outperformed UNet and Pix2Pix in accuracy.

Abstract

Local tissue expansion of the lungs is typically derived by registering computed tomography (CT) scans acquired at multiple lung volumes. However, acquiring multiple scans incurs increased radiation dose, time, and cost, and may not be possible in many cases, thus restricting the applicability of registration-based biomechanics. We propose a generative adversarial learning approach for estimating local tissue expansion directly from a single CT scan. The proposed framework was trained and evaluated on 2500 subjects from the SPIROMICS cohort. Once trained, the framework can be used as a registration-free method for predicting local tissue expansion. We evaluated model performance across varying degrees of disease severity and compared its performance with two image-to-image translation frameworks - UNet and Pix2Pix. Our model achieved an overall PSNR of 18.95 decibels, SSIM of 0.840, and Spearman's correlation of 0.61 at a high spatial resolution of 1 mm3.