Cargando…

A systematic approach to deep learning-based nodule detection in chest radiographs

Lung cancer is a serious disease responsible for millions of deaths every year. Early stages of lung cancer can be manifested in pulmonary lung nodules. To assist radiologists in reducing the number of overseen nodules and to increase the detection accuracy in general, automatic detection algorithms...

Descripción completa

Detalles Bibliográficos
Autores principales: Behrendt, Finn, Bengs, Marcel, Bhattacharya, Debayan, Krüger, Julia, Opfer, Roland, Schlaefer, Alexander
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10284921/
https://www.ncbi.nlm.nih.gov/pubmed/37344565
http://dx.doi.org/10.1038/s41598-023-37270-2
_version_ 1785061498510376960
author Behrendt, Finn
Bengs, Marcel
Bhattacharya, Debayan
Krüger, Julia
Opfer, Roland
Schlaefer, Alexander
author_facet Behrendt, Finn
Bengs, Marcel
Bhattacharya, Debayan
Krüger, Julia
Opfer, Roland
Schlaefer, Alexander
author_sort Behrendt, Finn
collection PubMed
description Lung cancer is a serious disease responsible for millions of deaths every year. Early stages of lung cancer can be manifested in pulmonary lung nodules. To assist radiologists in reducing the number of overseen nodules and to increase the detection accuracy in general, automatic detection algorithms have been proposed. Particularly, deep learning methods are promising. However, obtaining clinically relevant results remains challenging. While a variety of approaches have been proposed for general purpose object detection, these are typically evaluated on benchmark data sets. Achieving competitive performance for specific real-world problems like lung nodule detection typically requires careful analysis of the problem at hand and the selection and tuning of suitable deep learning models. We present a systematic comparison of state-of-the-art object detection algorithms for the task of lung nodule detection. In this regard, we address the critical aspect of class imbalance and and demonstrate a data augmentation approach as well as transfer learning to boost performance. We illustrate how this analysis and a combination of multiple architectures results in state-of-the-art performance for lung nodule detection, which is demonstrated by the proposed model winning the detection track of the Node21 competition. The code for our approach is available at https://github.com/FinnBehrendt/node21-submit.
format Online
Article
Text
id pubmed-10284921
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-102849212023-06-23 A systematic approach to deep learning-based nodule detection in chest radiographs Behrendt, Finn Bengs, Marcel Bhattacharya, Debayan Krüger, Julia Opfer, Roland Schlaefer, Alexander Sci Rep Article Lung cancer is a serious disease responsible for millions of deaths every year. Early stages of lung cancer can be manifested in pulmonary lung nodules. To assist radiologists in reducing the number of overseen nodules and to increase the detection accuracy in general, automatic detection algorithms have been proposed. Particularly, deep learning methods are promising. However, obtaining clinically relevant results remains challenging. While a variety of approaches have been proposed for general purpose object detection, these are typically evaluated on benchmark data sets. Achieving competitive performance for specific real-world problems like lung nodule detection typically requires careful analysis of the problem at hand and the selection and tuning of suitable deep learning models. We present a systematic comparison of state-of-the-art object detection algorithms for the task of lung nodule detection. In this regard, we address the critical aspect of class imbalance and and demonstrate a data augmentation approach as well as transfer learning to boost performance. We illustrate how this analysis and a combination of multiple architectures results in state-of-the-art performance for lung nodule detection, which is demonstrated by the proposed model winning the detection track of the Node21 competition. The code for our approach is available at https://github.com/FinnBehrendt/node21-submit. Nature Publishing Group UK 2023-06-21 /pmc/articles/PMC10284921/ /pubmed/37344565 http://dx.doi.org/10.1038/s41598-023-37270-2 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Behrendt, Finn
Bengs, Marcel
Bhattacharya, Debayan
Krüger, Julia
Opfer, Roland
Schlaefer, Alexander
A systematic approach to deep learning-based nodule detection in chest radiographs
title A systematic approach to deep learning-based nodule detection in chest radiographs
title_full A systematic approach to deep learning-based nodule detection in chest radiographs
title_fullStr A systematic approach to deep learning-based nodule detection in chest radiographs
title_full_unstemmed A systematic approach to deep learning-based nodule detection in chest radiographs
title_short A systematic approach to deep learning-based nodule detection in chest radiographs
title_sort systematic approach to deep learning-based nodule detection in chest radiographs
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10284921/
https://www.ncbi.nlm.nih.gov/pubmed/37344565
http://dx.doi.org/10.1038/s41598-023-37270-2
work_keys_str_mv AT behrendtfinn asystematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT bengsmarcel asystematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT bhattacharyadebayan asystematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT krugerjulia asystematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT opferroland asystematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT schlaeferalexander asystematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT behrendtfinn systematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT bengsmarcel systematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT bhattacharyadebayan systematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT krugerjulia systematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT opferroland systematicapproachtodeeplearningbasednoduledetectioninchestradiographs
AT schlaeferalexander systematicapproachtodeeplearningbasednoduledetectioninchestradiographs