Single Volume Lung Biomechanics from Chest Computed Tomography Using a Mode Preserving Generative Adversarial Network

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 1mm.

[1]  F. Martinez,et al.  Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary. , 2007, American journal of respiratory and critical care medicine.

[2]  Colin Raffel,et al.  Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples , 2020, NeurIPS.

[3]  Gary E. Christensen,et al.  Quantifying ventilation change due to radiation therapy using 4DCT Jacobian calculations , 2018, Medical physics.

[4]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  David W. Kaczka,et al.  Multi-resolution convolutional neural networks for fully automated segmentation of acutely injured lungs in multiple species , 2019, Medical Image Anal..

[6]  Eric A Hoffman,et al.  Computed Tomography Measure of Lung at Risk and Lung Function Decline in Chronic Obstructive Pulmonary Disease , 2017, American journal of respiratory and critical care medicine.

[7]  Jonathan T. Barron,et al.  A General and Adaptive Robust Loss Function , 2017, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Lisa M LaVange,et al.  Design of the Subpopulations and Intermediate Outcomes in COPD Study (SPIROMICS) , 2013, Thorax.

[9]  Gary E. Christensen,et al.  Estimating Local Tissue Expansion in Thoracic Computed Tomography Images Using Convolutional Neural Networks , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[10]  G. Christensen,et al.  Regularized Nonrigid Registration of Lung CT I m ages by Preserving Tissue Volu m e and Vesselness Measure , 2010 .

[11]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[13]  E. Hoffman,et al.  Mass preserving nonrigid registration of CT lung images using cubic B-spline. , 2009, Medical physics.

[14]  Trevor Darrell,et al.  Discriminator Rejection Sampling , 2018, ICLR.

[15]  Andrea Vedaldi,et al.  Instance Normalization: The Missing Ingredient for Fast Stylization , 2016, ArXiv.

[16]  Eric A. Hoffman,et al.  Registration-based estimates of local lung tissue expansion compared to xenon CT measures of specific ventilation , 2008, Medical Image Anal..