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

Diedre S. Carmo, Rosarie A. Tudas, Alejandro P. Comellas, Leticia Rittner, Roberto A. Lotufo +2 more
10/13/2023
eess.IVcs.CV

Official code: MICLab-Unicamp/medseg (12 stars, MIT, PyTorch, last commit 2023-12-04).

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.

View on arXivView PDF

Code Implementations(1)

MICLab-Unicamp/medsegOfficial100%
PyTorchMIT

Official repository for reproducing COVID and Lung segmentation prediction (old version of MEDPSeg)

124Shell, PythonOct 20, 20212 years agoMIT
covid-19lung-segmentationmedical-imagingpytorchsegmentation

Similar Papers

Composite Deep Network with Feature Weighting for Improved Delineation of COVID Infection in Lung CT

91% match2023

Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients

89% match1 repo72020

InfLocNet: Enhanced Lung Infection Localization and Disease Detection from Chest X-Ray Images Using Lightweight Deep Learning

89% match2024

Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem

89% match1 repo7972020

Detection-Guided Deep Learning-Based Model with Spatial Regularization for Lung Nodule Segmentation

88% match2024

CAD-Unet: A Capsule Network-Enhanced Unet Architecture for Accurate Segmentation of COVID-19 Lung Infections from CT Images

88% match2024

Cite this paper

@article{carmo2023automatic,
  title  = {Automatic segmentation of lung findings in CT and application to Long COVID},
  author = {Diedre S. Carmo and Rosarie A. Tudas and Alejandro P. Comellas and Leticia Rittner and Roberto A. Lotufo and Joseph M. Reinhardt and Sarah E. Gerard},
  year   = {2023},
  eprint = {2310.09446},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.09446v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.09446.svg)](https://codeofpaper.com/paper/2310.09446)

Discussion