Quantitative CT Characteristics of Cluster Phenotypes in the Severe                     Asthma Research Program Cohorts

Trivedi, Abhaya; Hall, Chase; Goss, Charles W.; Lew, Daphne; Sieren, Jered; Li, Huashi; Schechtman, Ken; Schirm, Joshua; McEleney, Stephen; Peterson, S.; Schiebler, Mark L.; Reinhardt, Joseph M.; Newell, John; Hoffman, Eric A.; Israel, Elliot; Levy, Bruce D.; Cernadas, Manuela; Washko, George R.; Haley, Kathleen J.; Cardet, Juan Carlos; Duvall, Melody G.; Forth, Victoria E.; Le, Meghan; Fandozzi, Eva; O’Neill, Allison F.; Gentile, Katarina; Cinelli, Maria; Tulchinsky, Abigail; Lawrance, Guilberto; Czajkowski, Randall; Lemole, Peter; Antunes, William; McGinnis, Ann; Klokeid, Kris; Phipatanakul, Wanda; Sheehan, William J.; Bartnikas, Lisa; Baxi, Sachin N.; Crestani, Elena; Etsy, Brittany; Gaffin, Jonathan M.; Hauptman, Marissa; Kantor, David; Lai, Peggy S.; Louisias, Margee; Nelson, Kyle A.; Permaul, Perdita; Schneider, Lynda C.; Wright, Lakiea S.; Minnicozzi, Samantha; Maciag, Michelle C.; Haktanir-Abul, M.; Gunnlaugsson, Sigfus; Burke-Roberts, Elizabeth; Cunningham, Amparito; Ansel-Kelly, Ethan; Waskosky, Sullivan; Ramsey, Anna; Feloney, Laura; Wenzel, Sally E.; Fajt, Merritt L.; Celedón, Juan C.; Larkin, Allyson; Di, Y. Peter; Chu, Hong Wei; Gauthier, Marc; Wu, Wei; Jain, S.; Camiolo, Matthew; Rauscher, Christine; Luyster, Faith S.; Rebovich, Paul; Demas, Jessa; Wunderley, Renee; Vitari, Catherine; Ilnicki, Melissa; Srollo, Diane; Takosky, Crystal; Lanzo, Rose; Leader, Joseph K.; Lapic, Daniel M.; Etling, Emily; Rhodes, Donna H.; Burger, Jeananne; Glover, Erin; Peters, Albert J.; Smith, Carl H.; Bonfiglio, Nicholas; Trudeau, John B.; Bang, Seojin; Lin, Qiao; Liu, Chia-Hsin; Kupul, Saran; Jarjour, Nizar N.; Denlinger, Loren C.; Lemanske, Robert F.; Fain, Sean B.; Viswanathan, Ravi; Moss, Mark B.; Jackson, Dan; Sorkness, Ronald L.; Ramratnam, Sima; Tattersall, Matthew C.; Crisafi, Gina; Klaus, Danika; Wollet, Lori; Bach, Julia; Johansson, Mats W.; Schiebler, Mark L.; Esnault, Stéphane; Mathur, Sameer K.; Yakey, Jan; Floerke, Heather; Guadarrama, Arturo G.; Maddox, Andrew; Peters, Brooke; Beaman, Katelin; Sumino, Kaharu; Castro, Mario; Bacharier, Leonard B.; Gierada, David S.; Woods, Jason C.; Schechtman, Kenneth B.; Patterson, Brenda; Sheshadri, Ajay; Coverstone, Andrea M.; Shifren, Adrián; Quirk, James D.; Byers, Derek E.; Krings, James G.; McGregor, M.C.; Samant, M.; Tarsi, Jaime; Koch, Tammy; Curtis, Vanessa; Yin‐Declue, Huiqing; Boomer, Jonathan S.; Saylor, Melissa; Frei, Shirley; Rowe, Licia; Sajol, Geneline; Kozlowski, Jim; Hoffman, Eric A.; Allard, Elizabeth; Atha, Jarron; Lin, Ching‐Long; Fahy, John V.; Woodruff, Prescott G.; Ly, Ngoc P.; Bhakta, Nirav R.; Peters, Michael C.; Moreno, Courtney C.; Baum, Ariana; Liu, Donna; Kalra, Anjali; Orain, Xavier; Charbit, Annabelle R; Njoku, Ndidi; Dunican, Eleanor M.; Teague, W. Gerald; Greenwald, Roby; DeBoer, Mark D.; Wavell, Kristin; deRonde, Kimberly; Erzurum, Serpil C.; Carl, John; Khatri, Sumita; Dweik, Raed A.; Comhair, Suzy; Sharp, Jackie; Lempel, Jason K.; Farha, Samar; Taliercio, Rachel M.; Aronica, Mark A.; Zein, Joe; Koo, Michelle S.; Painter, Tracy A.; Hopkins, Kim; Lawrence, Joy; Abi-Saleh, Simon; Labadia, Monica; Qirjaz, Elion; Wehrmann, Ron; Arbruster, Debera; Markle, Teresa; Matuska, Brittany; Baicker-McKee, Sara; Wyszynski, Patrick; Fitzgerald, Kelly; Ross, Kristie; Gaston, Benjamin; Myers, Ross; Craven, Daniel; Roesch, Erica A.; Thomas, Ryan M.; Logan, Laurie; Veri, Laura; Gluvna, Adam; Wallace, Julie; Pryor, Margaret; Smith, Sara N.; Allerton, Patricia; Emrich, Traci; Hilliard, Jay B.; Krenicky, Jeanne E.; Smith, Laura A.; Ferrebee, Matthew; Moore, Wendy C.; Bleecker, Eugene R.; Meyers, Deborah A.; Peters, Stephen P.; Li, Xingnan; Hastie, Annette T.; Ortega, Victor E.; Hawkins, Greg; Krings, Jeff; Ampleford, Elizabeth J.; Pippins, Anna; Field, Paige; Rector, Brian; Sprissler, Ryan; Fransway, Barbara; Fitzpatrick, Anne M.; Stephenson, Susan; Mauger, David T.; Phillips, Brenda R.

doi:10.1148/radiol.210363

Cited by 8 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted a Pearson correlation analysis of the PRM parameters and their correlation with visual evaluation. PRM fSAD is generally considered to have significant SAD above 15–25% [ 15 , 25 – 27 ]. We used R software (Windows version 4.3.0) to binarize GT PRM fSAD (with values ranging from 10 to 30%) and calculated the AUC value between binarized GT PRM fSAD and Pred PRM fSAD (see Additional file 1 : Table S1).…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, both the ground truth and the predicted PRM fSAD correlate with the visual evaluation of emphysema and airway morphology in HRCT, displaying a similar distribution of lung structure abnormalities when risk stratifying SAD. Using GT PRM fSAD to stratify SAD at thresholds of 15%, 20%, and 25% [ 15 , 25 – 27 ], predicted PRM fSAD displayed exceptional classification performance (AUCs of 0.84, 0.78, and 0.84 respectively; p < 0.001), which is sufficient for routine SAD clinical screening.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning parametric response mapping from inspiratory chest CT scans: a new approach for small airway disease screening

Chen,

Liu,

et al. 2023

Respir Res

View full text Add to dashboard Cite

Objectives Parametric response mapping (PRM) enables the evaluation of small airway disease (SAD) at the voxel level, but requires both inspiratory and expiratory chest CT scans. We hypothesize that deep learning PRM from inspiratory chest CT scans can effectively evaluate SAD in individuals with normal spirometry. Methods We included 537 participants with normal spirometry, a history of smoking or secondhand smoke exposure, and divided them into training, tuning, and test sets. A cascaded generative adversarial network generated expiratory CT from inspiratory CT, followed by a UNet-like network predicting PRM using real inspiratory CT and generated expiratory CT. The performance of the prediction is evaluated using SSIM, RMSE and dice coefficients. Pearson correlation evaluated the correlation between predicted and ground truth PRM. ROC curves evaluated predicted PRMfSAD (the volume percentage of functional small airway disease, fSAD) performance in stratifying SAD. Results Our method can generate expiratory CT of good quality (SSIM 0.86, RMSE 80.13 HU). The predicted PRM dice coefficients for normal lung, emphysema, and fSAD regions are 0.85, 0.63, and 0.51, respectively. The volume percentages of emphysema and fSAD showed good correlation between predicted and ground truth PRM (|r| were 0.97 and 0.64, respectively, p < 0.05). Predicted PRMfSAD showed good SAD stratification performance with ground truth PRMfSAD at thresholds of 15%, 20% and 25% (AUCs were 0.84, 0.78, and 0.84, respectively, p < 0.001). Conclusion Our deep learning method generates high-quality PRM using inspiratory chest CT and effectively stratifies SAD in individuals with normal spirometry.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep learning parametric response mapping from inspiratory chest CT scans: a new approach for small airway disease screening

Chen,

Liu,

et al. 2023

Respir Res

View full text Add to dashboard Cite

show abstract

“…Molecular patterns are also impacted by background therapy and duration of disease. Incorporating clinical/physiologic (including environmental and social determinants 24 , 25 ) and radiologic characteristics 26 (used collectively with molecular, genetic, and other omic features) into the input variables (rather than as outcomes) is also important. Additionally, comorbidities can also influence asthma and the overall molecular profile.…”

Section: Moving Toward Endotypesmentioning

confidence: 99%

Determining asthma endotypes and outcomes: Complementing existing clinical practice with modern machine learning

Ray¹,

Das²,

Wenzel³

2022

Cell Reports Medicine

Self Cite

View full text Add to dashboard Cite

“…where L(•, •) denoted L LP IP S (•, •) in (7) and each term corresponded to a different view of the volume. This simple extension enabled style transfer at a volumetric level.…”

Section: B Meal: Multiview Perceptual Similaritymentioning

confidence: 99%

“…For instance, parametric response mapping (PRM) and disease probability maps (DPM) have been used to identify local patterns of emphysema and functional small airways disease (fSAD) from co-registered, inspiratory-expiratory chest CT volumes [3], [4]. PRM and DPM have since gathered widespread clinical attention as they have been used to detect and characterize COPD and asthma [7]. Bodduluri et al showed that registrationderived local tissue expansion of the lung was associated with respiratory function, emphysema, and patient quality of life [6].…”

mentioning

confidence: 99%

Lung2Lung: Volumetric Style Transfer with Self-Ensembling for High-Resolution Cross-Volume Computed Tomography

Chaudhary¹,

Gerard²,

Christensen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Chest computed tomography (CT) at inspiration is often complemented by an expiratory CT for identifying peripheral airways disease in the form of air trapping. Additionally, co-registered inspiratory-expiratory volumes are used to derive several clinically relevant measures of local lung function. Acquiring CT at different volumes, however, increases radiation dosage, acquisition time, and may not be achievable due to various complications, limiting the utility of registration-based measures. To address this, we propose Lung2Lung -a style-based generative adversarial approach for translating CT images from end-inspiratory to end-expiratory volume. Lung2Lung addresses several limitations of the traditional generative models including slicewise discontinuities, limited size of generated volumes, and their inability to model neural style at a volumetric level. We introduce multiview perceptual similarity (MEAL) to capture neural styles in 3D. To incorporate global information into the training process and refine the output of our model, we also propose self-ensembling (SE). Lung2Lung, with MEAL and SE, is able to generate large 3D volumes of size 320 × 320 × 320 that are validated using a diverse cohort of 1500 subjects with varying disease severity. The model shows superior performance against several state-of-the-art 2D and 3D generative models with a peak-signal-to-noise ratio of 24.53 dB and structural similarity of 0.904. Clinical validation shows that the synthetic volumes can be used to reliably extract several clinical endpoints of chronic obstructive pulmonary disease.

show abstract

Quantitative CT Characteristics of Cluster Phenotypes in the Severe Asthma Research Program Cohorts

Cited by 8 publications

References 31 publications

Deep learning parametric response mapping from inspiratory chest CT scans: a new approach for small airway disease screening

Deep learning parametric response mapping from inspiratory chest CT scans: a new approach for small airway disease screening

Determining asthma endotypes and outcomes: Complementing existing clinical practice with modern machine learning

Lung2Lung: Volumetric Style Transfer with Self-Ensembling for High-Resolution Cross-Volume Computed Tomography

Contact Info

Product

Resources

About