Attention-based multi-residual network for lung segmentation in diseased lungs with custom data augmentation

Lung disease analysis in chest X-rays (CXR) using deep learning presents significant challenges due to the wide variation in lung appearance caused by disease progression and differing X-ray settings. While deep learning models have shown remarkable success in segmenting lungs from CXR images with n...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2024-11, Vol.14 (1), p.28983-11, Article 28983
Main Authors: Alam, Md. Shariful, Wang, Dadong, Arzhaeva, Yulia, Ende, Jesse Alexander, Kao, Joanna, Silverstone, Liz, Yates, Deborah, Salvado, Olivier, Sowmya, Arcot
Format: Article
Language:English
Subjects:
631/114
692/698
COVID-19
COVID-19 - diagnostic imaging
COVID-19 - virology
Deep Learning
Humanities and Social Sciences
Humans
Image processing
Information processing
Lung - diagnostic imaging
Lung diseases
Lung Diseases - diagnostic imaging
Lung Diseases - pathology
Lungs
multidisciplinary
Pneumoconiosis
Pneumoconiosis - diagnostic imaging
Radiographic Image Interpretation, Computer-Assisted - methods
Radiography, Thoracic - methods
SARS-CoV-2
Science
Science (multidisciplinary)
Segmentation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Lung disease analysis in chest X-rays (CXR) using deep learning presents significant challenges due to the wide variation in lung appearance caused by disease progression and differing X-ray settings. While deep learning models have shown remarkable success in segmenting lungs from CXR images with normal or mildly abnormal findings, their performance declines when faced with complex structures, such as pulmonary opacifications. In this study, we propose AMRU++, an attention-based multi-residual UNet++ network designed for robust and accurate lung segmentation in CXR images with both normal and severe abnormalities. The model incorporates attention modules to capture relevant spatial information and multi-residual blocks to extract rich contextual and discriminative features of lung regions. To further enhance segmentation performance, we introduce a data augmentation technique that simulates the features and characteristics of CXR pathologies, addressing the issue of limited annotated data. Extensive experiments on public and private datasets comprising 350 cases of pneumoconiosis, COVID-19, and tuberculosis validate the effectiveness of our proposed framework and data augmentation technique.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-79494-w