Cargando…

A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities

We evaluated the efficacy of a curriculum learning strategy using two steps to detect pulmonary abnormalities including nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax with chest-PA X-ray (CXR) images from two centres. CXR images of 6069 healthy subjects and 3417 p...

Descripción completa

Detalles Bibliográficos
Autores principales: Park, Beomhee, Cho, Yongwon, Lee, Gaeun, Lee, Sang Min, Cho, Young-Hoon, Lee, Eun Sol, Lee, Kyung Hee, Seo, Joon Beom, Kim, Namkug
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6814828/
https://www.ncbi.nlm.nih.gov/pubmed/31653943
http://dx.doi.org/10.1038/s41598-019-51832-3
_version_ 1783463066716864512
author Park, Beomhee
Cho, Yongwon
Lee, Gaeun
Lee, Sang Min
Cho, Young-Hoon
Lee, Eun Sol
Lee, Kyung Hee
Seo, Joon Beom
Kim, Namkug
author_facet Park, Beomhee
Cho, Yongwon
Lee, Gaeun
Lee, Sang Min
Cho, Young-Hoon
Lee, Eun Sol
Lee, Kyung Hee
Seo, Joon Beom
Kim, Namkug
author_sort Park, Beomhee
collection PubMed
description We evaluated the efficacy of a curriculum learning strategy using two steps to detect pulmonary abnormalities including nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax with chest-PA X-ray (CXR) images from two centres. CXR images of 6069 healthy subjects and 3417 patients at AMC and 1035 healthy subjects and 4404 patients at SNUBH were obtained. Our approach involved two steps. First, the regional patterns of thoracic abnormalities were identified by initial learning of patch images around abnormal lesions. Second, Resnet-50 was fine-tuned using the entire images. The network was weakly trained and modified to detect various disease patterns. Finally, class activation maps (CAM) were extracted to localise and visualise the abnormal patterns. For average disease, the sensitivity, specificity, and area under the curve (AUC) were 85.4%, 99.8%, and 0.947, respectively, in the AMC dataset and 97.9%, 100.0%, and 0.983, respectively, in the SNUBH dataset. This curriculum learning and weak labelling with high-scale CXR images requires less preparation to train the system and could be easily extended to include various diseases in actual clinical environments. This algorithm performed well for the detection and classification of five disease patterns in CXR images and could be helpful in image interpretation.
format Online
Article
Text
id pubmed-6814828
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-68148282019-10-30 A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities Park, Beomhee Cho, Yongwon Lee, Gaeun Lee, Sang Min Cho, Young-Hoon Lee, Eun Sol Lee, Kyung Hee Seo, Joon Beom Kim, Namkug Sci Rep Article We evaluated the efficacy of a curriculum learning strategy using two steps to detect pulmonary abnormalities including nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax with chest-PA X-ray (CXR) images from two centres. CXR images of 6069 healthy subjects and 3417 patients at AMC and 1035 healthy subjects and 4404 patients at SNUBH were obtained. Our approach involved two steps. First, the regional patterns of thoracic abnormalities were identified by initial learning of patch images around abnormal lesions. Second, Resnet-50 was fine-tuned using the entire images. The network was weakly trained and modified to detect various disease patterns. Finally, class activation maps (CAM) were extracted to localise and visualise the abnormal patterns. For average disease, the sensitivity, specificity, and area under the curve (AUC) were 85.4%, 99.8%, and 0.947, respectively, in the AMC dataset and 97.9%, 100.0%, and 0.983, respectively, in the SNUBH dataset. This curriculum learning and weak labelling with high-scale CXR images requires less preparation to train the system and could be easily extended to include various diseases in actual clinical environments. This algorithm performed well for the detection and classification of five disease patterns in CXR images and could be helpful in image interpretation. Nature Publishing Group UK 2019-10-25 /pmc/articles/PMC6814828/ /pubmed/31653943 http://dx.doi.org/10.1038/s41598-019-51832-3 Text en © The Author(s) 2019 Open Access This 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 license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license 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 license, visit http://creativecommons.org/licenses/by/4.0/.
spellingShingle Article
Park, Beomhee
Cho, Yongwon
Lee, Gaeun
Lee, Sang Min
Cho, Young-Hoon
Lee, Eun Sol
Lee, Kyung Hee
Seo, Joon Beom
Kim, Namkug
A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities
title A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities
title_full A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities
title_fullStr A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities
title_full_unstemmed A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities
title_short A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities
title_sort curriculum learning strategy to enhance the accuracy of classification of various lesions in chest-pa x-ray screening for pulmonary abnormalities
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6814828/
https://www.ncbi.nlm.nih.gov/pubmed/31653943
http://dx.doi.org/10.1038/s41598-019-51832-3
work_keys_str_mv AT parkbeomhee acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT choyongwon acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leegaeun acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leesangmin acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT choyounghoon acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leeeunsol acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leekyunghee acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT seojoonbeom acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT kimnamkug acurriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT parkbeomhee curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT choyongwon curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leegaeun curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leesangmin curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT choyounghoon curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leeeunsol curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT leekyunghee curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT seojoonbeom curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities
AT kimnamkug curriculumlearningstrategytoenhancetheaccuracyofclassificationofvariouslesionsinchestpaxrayscreeningforpulmonaryabnormalities