A Soft Labeling Approach to Develop Automated Algorithms that Incorporate Uncertainty in Pulmonary Opacification on Chest CT using COVID-19 Pneumonia.

Autor:	Lensink K; Department of Earth, Ocean, and Atmospheric Sciences, University of British Columbia, Vancouver, BC, Canada., Lo FJ; Faculty of Medicine, University of British Columbia, Vancouver, BC, Canada., Eddy RL; UBC Centre for Heart Lung Innovation, St. Paul's Hospital, Vancouver, BC, Canada; Division of Respiratory Medicine, Department of Medicine, University of British Columbia, Vancouver, BC, Canada., Law M; Cloud Innovation Centre, University of British Columbia, Vancouver, BC, Canada., Laradji I; Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada; ServiceNow, Santa Clara, California., Haber E; Department of Earth, Ocean, and Atmospheric Sciences, University of British Columbia, Vancouver, BC, Canada., Nicolaou S; Department of Radiology, University of British Columbia, 2775 Laurel Street, 11th Floor, Vancouver, BC, Canada V5Z 1M9., Murphy D; Department of Radiology, University of British Columbia, 2775 Laurel Street, 11th Floor, Vancouver, BC, Canada V5Z 1M9., Parker WA; Department of Radiology, University of British Columbia, 2775 Laurel Street, 11th Floor, Vancouver, BC, Canada V5Z 1M9. Electronic address: william@alumni.ubc.ca.
Jazyk:	angličtina
Zdroj:	Academic radiology [Acad Radiol] 2022 Jul; Vol. 29 (7), pp. 994-1003. Date of Electronic Publication: 2022 Mar 30.
DOI:	10.1016/j.acra.2022.03.025
Abstrakt:	Rationale and Objectives: Hard data labels for automated algorithm training are binary and cannot incorporate uncertainty between labels. We proposed and evaluated a soft labeling methodology to quantify opacification and percent well-aerated lung (%WAL) on chest CT, that considers uncertainty in segmenting pulmonary opacifications and reduces labeling burden. Materials and Methods: We retrospectively sourced 760 COVID-19 chest CT scans from five international centers between January and June 2020. We created pixel-wise labels for >27,000 axial slices that classify three pulmonary opacification patterns: pure ground-glass, crazy-paving, consolidation. We also quantified %WAL as the total area of lung without opacifications. Inter-user hard label variability was quantified using Shannon entropy (range=0-1.39, low-high entropy/variability). We incorporated a soft labeling and modeling cycle following an initial model with hard labels and compared performance using point-wise accuracy and intersection-over-union of opacity labels with ground-truth, and correlation with ground-truth %WAL. Results: Hard labels annotated by 12 radiologists demonstrated large inter-user variability (3.37% of pixels achieved complete agreement). Our soft labeling approach increased point-wise accuracy from 60.0% to 84.3% (p=0.01) compared to hard labeling at predicting opacification type and area involvement. The soft label model accurately predicted %WAL (R=0.900) compared to the hard label model (R=0.856), but the improvement was not statistically significant (p=0.349). Conclusion: Our soft labeling approach increased accuracy for automated quantification and classification of pulmonary opacification on chest CT. Although we developed the model on COVID-19, our intent is broad application for pulmonary opacification contexts and to provide a foundation for future development using soft labeling methods. (Crown Copyright © 2022. Published by Elsevier Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu