RECORD
CT Image Segmentation for Inflamed and Fibrotic Lungs Using a Multi-Resolution Convolutional Neural Network
Image and Video Processing · Submitted 16 Oct 2020
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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 $0.495 \pm 0.309$ mm and Dice coefficient of $0.985 \pm 0.011$. 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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | 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. | contribution 0.76 | 0.51 | 0.05 | asserted 0.83 |
| s1 | 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. | method 0.93 | 0.91 | 0.04 | asserted 0.98 |
| s2 | The resulting network is intended for predicting left and right lung regions in humans with or without diffuse opacification and consolidation. | contribution 0.56 | 0.37 | 0.06 | asserted 0.81 |
| s3 | 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. | method 0.55 | 0.95 | 0.12 | asserted 0.99 |
| s4 | Lobar segmentations were obtained using the left and right lung segmentation as input to the LobeNet algorithm. | method 1.00 | 0.85 | 0.03 | asserted 0.99 |
| s5 | Regional lobar analysis was performed using hierarchical clustering to identify radiographic subtypes of COVID-19. | method 0.97 | 0.93 | 0.05 | asserted 0.97 |
| s6 | 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 $0.495 \pm 0.309$ mm and Dice coefficient of $0.985 \pm 0.011$. | result 0.99 | 0.97 | 0.16 | asserted 1.00 |
| s7 | Hierarchical clustering identified four radiographical phenotypes of COVID-19 based on lobar fractions of consolidated and poorly aerated tissue. | result 1.00 | 0.95 | 0.14 | asserted 1.00 |
| s8 | Lower left and lower right lobes were consistently more afflicted with poor aeration and consolidation. | result 0.99 | 0.94 | 0.08 | asserted 1.00 |
| s9 | However, the most severe cases demonstrated involvement of all lobes. | result 0.93 | 0.89 | 0.06 | asserted 1.00 |
| s10 | The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training. | result 0.79 | 0.93 | 0.50 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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 $0.495 \pm 0.309$ mm and Dice coefficient of $0.985 \pm 0.011$. 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.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.