Automatic segmentation of lung findings in CT and application to Long COVID

Diedre Carmo; Rosarie Tudas; Alejandro Comellas; Leticia Rittner; Roberto Lotufo; Joseph Reinhardt; Sarah Gerard

doi:10.48550/arxiv.2310.09446

Back

Automatic segmentation of lung findings in CT and application to Long COVID

Preprint

Open access

Automatic segmentation of lung findings in CT and application to Long COVID

Diedre Carmo, Rosarie Tudas, Alejandro Comellas, Leticia Rittner, Roberto Lotufo, Joseph Reinhardt and Sarah Gerard

arXiv.org

Cornell University Library, arXiv.org

10/13/2023

DOI: 10.48550/arxiv.2310.09446

Files and links (1)

url

https://doi.org/10.48550/arxiv.2310.09446View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Automated segmentation of lung abnormalities in computed tomography is an important step for diagnosing and characterizing lung disease. In this work, we improve upon a previous method and propose S-MEDSeg, a deep learning based approach for accurate segmentation of lung lesions in chest CT images. S-MEDSeg combines a pre-trained EfficientNet backbone, bidirectional feature pyramid network, and modern network advancements to achieve improved segmentation performance. A comprehensive ablation study was performed to evaluate the contribution of the proposed network modifications. The results demonstrate modifications introduced in S-MEDSeg significantly improves segmentation performance compared to the baseline approach. The proposed method is applied to an independent dataset of long COVID inpatients to study the effect of post-acute infection vaccination on extent of lung findings. Open-source code, graphical user interface and pip package are available at https://github.com/MICLab-Unicamp/medseg.

Computed Tomography

Ablation

Abnormalities

Graphical user interface

Image segmentation

Source code

Details

Title: Subtitle: Automatic segmentation of lung findings in CT and application to Long COVID
Creators: Diedre Carmo
Rosarie Tudas - University of Iowa, Internal Medicine
Alejandro Comellas - University of Iowa, Internal Medicine
Leticia Rittner
Roberto Lotufo
Joseph Reinhardt
Sarah Gerard
Resource Type: Preprint
Publication Details: arXiv.org
DOI: 10.48550/arxiv.2310.09446
eISSN: 2331-8422
Publisher: Cornell University Library, arXiv.org; Ithaca
Language: English
Date posted: 10/13/2023
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Pulmonary, Critical Care, and Occupational Medicine; ICTS; Internal Medicine
Record Identifier: 9984482558102771

Metrics

78 Record Views