CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network

Sarah E Gerard; Jacob Herrmann; Yi Xin; Kevin T Martin; Emanuele Rezoagli; Davide Ippolito; Giacomo Bellani; Maurizio Cereda; Junfeng Guo; Eric A Hoffman; David W Kaczka; Joseph M Reinhardt

doi:10.1038/s41598-020-80936-4

Back

CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network

Journal article

Open access

Peer reviewed

CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network

Sarah E Gerard, Jacob Herrmann, Yi Xin, Kevin T Martin, Emanuele Rezoagli, Davide Ippolito, Giacomo Bellani, Maurizio Cereda, Junfeng Guo, Eric A Hoffman, …

Scientific reports, Vol.11(1), pp.1455-1455

01/14/2021

DOI: 10.1038/s41598-020-80936-4

PMCID: PMC7809065

PMID: 33446781

Files and links (1)

url

https://doi.org/10.1038/s41598-020-80936-4View

Published (Version of record) Open Access

Abstract

The purpose of this study was to develop a fully-automated segmentation algorithm, robust to various density enhancing lung abnormalities, to facilitate rapid quantitative analysis of computed tomography images. A polymorphic training approach is proposed, in which both specifically labeled left and right lungs of humans with COPD, and nonspecifically labeled lungs of animals with acute lung injury, were incorporated into training a single neural network. The resulting network is intended for predicting left and right lung regions in humans with or without diffuse opacification and consolidation. Performance of the proposed lung segmentation algorithm was extensively evaluated on CT scans of subjects with COPD, confirmed COVID-19, lung cancer, and IPF, despite no labeled training data of the latter three diseases. Lobar segmentations were obtained using the left and right lung segmentation as input to the LobeNet algorithm. Regional lobar analysis was performed using hierarchical clustering to identify radiographic subtypes of COVID-19. The proposed lung segmentation algorithm was quantitatively evaluated using semi-automated and manually-corrected segmentations in 87 COVID-19 CT images, achieving an average symmetric surface distance of [Formula: see text] mm and Dice coefficient of [Formula: see text]. Hierarchical clustering identified four radiographical phenotypes of COVID-19 based on lobar fractions of consolidated and poorly aerated tissue. Lower left and lower right lobes were consistently more afflicted with poor aeration and consolidation. However, the most severe cases demonstrated involvement of all lobes. The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training.

COVID-19 - diagnostic imaging

Female

Humans

Lung - diagnostic imaging

Male

Neural Networks, Computer

Pulmonary Fibrosis - diagnostic imaging

SARS-CoV-2

Tomography, X-Ray Computed

Details

Title: Subtitle: CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network
Creators: Sarah E Gerard - University of Iowa
Jacob Herrmann - Boston University
Yi Xin - University of Pennsylvania
Kevin T Martin - University of Pennsylvania
Emanuele Rezoagli - University of Milano-Bicocca
Davide Ippolito - Department of Diagnostic and Interventional Radiology, San Gerardo Hospital, Monza, Italy.
Giacomo Bellani - University of Milano-Bicocca
Maurizio Cereda - University of Pennsylvania
Junfeng Guo - University of Iowa
Eric A Hoffman - University of Iowa
David W Kaczka - University of Iowa
Joseph M Reinhardt - University of Iowa
Resource Type: Journal article
Publication Details: Scientific reports, Vol.11(1), pp.1455-1455
DOI: 10.1038/s41598-020-80936-4
PMID: 33446781
PMCID: PMC7809065
NLM abbreviation: Sci Rep
ISSN: 2045-2322
eISSN: 2045-2322
Grant note: R01 HL142625 / NHLBI NIH HHS 19-5154 / Roy J. Carver Charitable Trust R01-HL142625 / NIH HHS W81XWH-16-1-0434 / Office of the Assistant Secretary of Defense for Health Affairs T32 HL144461 / NHLBI NIH HHS
Language: English
Date published: 01/14/2021
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Anesthesia; Internal Medicine
Record Identifier: 9984196992302771

Metrics

12 Record Views

45 Times Cited - Web of Science