Emphysema Score in CT for COPD Quantifications Using Artificial Intelligence Informed by Virtual Imaging Datasets

Sotoudeh-Paima, Saman; Nejad, M.G.; Segars, W. Paul; O'Sullivan-Murphy, B.; MacIntyre, Neil R.; Lynch, David A.; McAdams, H. Page; Samei, Ehsan; Abadi, Ehsan

doi:10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a4021

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Upon patient selection, the modeling process was conducted in six steps: 1) major organs and anatomical structures were segmented using a commercial segmentation prototype (DirectORGANS 2.0, Siemens) [11]- [13]; 2) pulmonary vessels and airway structures were segmented using two separate algorithms [14], [15]; 3) emphysema regions were segmented using an in-house algorithm [16]; 4) airways were grown from the segmented airway branches to include a more detailed lung non-parenchymal architecture; 5) intra-organ heterogeneities were added to the lung parenchyma and bone regions using mathematical and anatomically-informed models [17]- [19]; 6) emphysema heterogeneity was included and lung parenchymal density was adjusted.…”

Section: Longitudinal Emphysema Modelsmentioning

confidence: 99%

“…The utility of the longitudinal emphysema models was demonstrated by evaluating the accuracy and precision of two previously developed algorithms for quantifying emphysema progression: CT-HARMONICA [21], and EmphysemaSeg [16]. CT-HARMONICA is a lung density harmonizer with a modularized design that transforms CT images to a reference voxel size, spatial resolution, and noise magnitude.…”

Section: Algorithm Testing and Developmentmentioning

confidence: 99%

See 1 more Smart Citation

Development and application of a virtual imaging trial framework for longitudinal quantification of emphysema in CT

Sotoudeh-Paima,

Ho,

Ghojogh Nejad

et al. 2024

Medical Imaging 2024: Physics of Medical Imaging

View full text Add to dashboard Cite

Pulmonary emphysema is a progressive lung disease that requires accurate evaluation for optimal management. This task, possible using quantitative CT, is particularly challenging as scanner and patient attributes change over time, negatively impacting the CT-derived quantitative measures. Efforts to minimize such variations have been limited by the absence of ground truth in clinical data, thus necessitating reliance on clinical surrogates, which may not have one-toone correspondence to CT-based findings. This study aimed to develop the first suite of human models with emphysema at multiple time points, enabling longitudinal assessment of disease progression with access to ground truth. A total of 14 virtual subjects were modeled across three time points. Each human model was virtually imaged using a validated imaging simulator (DukeSim), modeling an energy-integrating CT scanner. The models were scanned at two dose levels and reconstructed with two reconstruction kernels, slice thicknesses, and pixel sizes. The developed longitudinal models were further utilized to demonstrate utility in algorithm testing and development. Two previously developed image processing algorithms (CT-HARMONICA, EmphysemaSeg) were evaluated. The results demonstrated the efficacy of both algorithms in improving the accuracy and precision of longitudinal quantifications, from 6.1±6.3% to 1.1±1.1% and 1.6±2.2% across years 0-5. Further investigation in EmphysemaSeg identified that baseline emphysema severity, defined as >5% emphysema at year 0, contributed to its reduced performance. This finding highlights the value of virtual imaging trials in enhancing the explainability of algorithms. Overall, the developed longitudinal human models enabled ground-truth based assessment of image processing algorithms for lung quantifications.

show abstract