Registration-Invariant Biomechanical Features for Disease Staging of COPD in SPIROMICS

Chaudhary, Muhammad F. A.; Pan, Yue; Wang, Di; Bodduluri, Sandeep; Bhatt, Surya P.; Comellas, Alejandro P.; Hoffman, Eric A.; Christensen, Gary E.; Reinhardt, Joseph M.

doi:10.1007/978-3-030-62469-9_13

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Jacobian determinant ( J ) of the registration displacement field quantifies local volume change, and has been validated against a well‐known, noninvasive method for estimating regional lung ventilation: xenon‐enhanced CT (Xe‐CT) 17,18 . Registration‐derived biomechanical measures have since gained widespread attention for understanding COPD 21–24 . Bodduluri et al.…”

Section: Introductionmentioning

confidence: 99%

“…17,18 Registration-derived biomechanical measures have since gained widespread attention for understanding COPD. [21][22][23][24] Bodduluri et al demonstrated that biomechanical features (extracted from Jacobians) were better predictors of COPD severity than conventional texture-and intensity-based features. 21 Local change in lung volume averaged over the lung field was shown to be in better agreement with spirometry and was able to capture lung function decline and parenchymal tissue destruction.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Direct estimation of regional lung volume change from paired and single CT images using residual regression neural network

et al. 2023

Self Cite

View full text Add to dashboard Cite

BackgroundChest computed tomography (CT) enables characterization of pulmonary diseases by producing high‐resolution and high‐contrast images of the intricate lung structures. Deformable image registration is used to align chest CT scans at different lung volumes, yielding estimates of local tissue expansion and contraction.PurposeWe investigated the utility of deep generative models for directly predicting local tissue volume change from lung CT images, bypassing computationally expensive iterative image registration and providing a method that can be utilized in scenarios where either one or two CT scans are available.MethodsA residual regression convolutional neural network, called Reg3DNet+, is proposed for directly regressing high‐resolution images of local tissue volume change (i.e., Jacobian) from CT images. Image registration was performed between lung volumes at total lung capacity (TLC) and functional residual capacity (FRC) using a tissue mass‐ and structure‐preserving registration algorithm. The Jacobian image was calculated from the registration‐derived displacement field and used as the ground truth for local tissue volume change. Four separate Reg3DNet+ models were trained to predict Jacobian images using a multifactorial study design to compare the effects of network input (i.e., single image vs. paired images) and output space (i.e., FRC vs. TLC). The models were trained and evaluated on image datasets from the COPDGene study. Models were evaluated against the registration‐derived Jacobian images using local, regional, and global evaluation metrics.ResultsStatistical analysis revealed that both factors – network input and output space – were significant determinants for change in evaluation metrics. Paired‐input models performed better than single‐input models, and model performance was better in the output space of FRC rather than TLC. Mean structural similarity index for paired‐input models was 0.959 and 0.956 for FRC and TLC output spaces, respectively, and for single‐input models was 0.951 and 0.937. Global evaluation metrics demonstrated correlation between registration‐derived Jacobian mean and predicted Jacobian mean: coefficient of determination (r2) for paired‐input models was 0.974 and 0.938 for FRC and TLC output spaces, respectively, and for single‐input models was 0.598 and 0.346. After correcting for effort, registration‐derived lobar volume change was strongly correlated with the predicted lobar volume change: for paired‐input models r2 was 0.899 for both FRC and TLC output spaces, and for single‐input models r2 was 0.803 and 0.862, respectively.ConclusionsConvolutional neural networks can be used to directly predict local tissue mechanics, eliminating the need for computationally expensive image registration. Networks that use paired CT images acquired at TLC and FRC allow for more accurate prediction of local tissue expansion compared to networks that use a single image. Networks that only require a single input image still show promising results, particularly after correcting for effort, and allow for local tissue expansion estimation in cases where multiple CT scans are not available. For single‐input networks, the FRC image is more predictive of local tissue volume change compared to the TLC image.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Direct estimation of regional lung volume change from paired and single CT images using residual regression neural network

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

Diseased and healthy murine local lung strains evaluated using digital image correlation

Nelson

Quiros

Dominguez

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Tissue remodeling in pulmonary disease irreversibly alters lung functionality and impacts quality of life. Mechanical ventilation is amongst the few pulmonary interventions to aid respiration, but can be harmful or fatal, inducing excessive regional (i.e., local) lung strains. Previous studies have advanced understanding of diseased global-level lung response under ventilation, but do not adequately capture the critical local-level response. Here, we pair a custom-designed pressure–volume ventilator with new applications of digital image correlation, to directly assess regional strains in the fibrosis-induced ex-vivo mouse lung, analyzed via regions of interest. We discuss differences between diseased and healthy lung mechanics, such as distensibility, heterogeneity, anisotropy, alveolar recruitment, and rate dependencies. Notably, we compare local and global compliance between diseased and healthy states by assessing the evolution of pressure-strain and pressure–volume curves resulting from various ventilation volumes and rates. We find fibrotic lungs are less-distensible, with altered recruitment behaviors and regional strains, and exhibit disparate behaviors between local and global compliance. Moreover, these diseased characteristics show volume-dependence and rate trends. Ultimately, we demonstrate how fibrotic lungs may be particularly susceptible to damage when contrasted to the strain patterns of healthy counterparts, helping to advance understanding of how ventilator induced lung injury develops.

show abstract

Robust Measures of Image-Registration-Derived Lung Biomechanics in SPIROMICS

et al. 2022

View full text Add to dashboard Cite

Chronic obstructive pulmonary disease (COPD) is an umbrella term used to define a collection of inflammatory lung diseases that cause airflow obstruction and severe damage to the lung parenchyma. This study investigated the robustness of image-registration-based local biomechanical properties of the lung in individuals with COPD as a function of Global Initiative for Chronic Obstructive Lung Disease (GOLD) stage. Image registration was used to estimate the pointwise correspondences between the inspiration (total lung capacity) and expiration (residual volume) computed tomography (CT) images of the lung for each subject. In total, three biomechanical measures were computed from the correspondence map: the Jacobian determinant; the anisotropic deformation index (ADI); and the slab-rod index (SRI). CT scans from 245 subjects with varying GOLD stages were analyzed from the SubPopulations and InteRmediate Outcome Measures In COPD Study (SPIROMICS). Results show monotonic increasing or decreasing trends in the three biomechanical measures as a function of GOLD stage for the entire lung and on a lobe-by-lobe basis. Furthermore, these trends held across all five image registration algorithms. The consistency of the five image registration algorithms on a per individual basis is shown using Bland–Altman plots.

show abstract

Registration-Invariant Biomechanical Features for Disease Staging of COPD in SPIROMICS

Cited by 3 publications

References 23 publications

Direct estimation of regional lung volume change from paired and single CT images using residual regression neural network

Direct estimation of regional lung volume change from paired and single CT images using residual regression neural network

Diseased and healthy murine local lung strains evaluated using digital image correlation

Robust Measures of Image-Registration-Derived Lung Biomechanics in SPIROMICS

Contact Info

Product

Resources

About