Cargando…

Automatic classification of canine thoracic radiographs using deep learning

The interpretation of thoracic radiographs is a challenging and error-prone task for veterinarians. Despite recent advancements in machine learning and computer vision, the development of computer-aided diagnostic systems for radiographs remains a challenging and unsolved problem, particularly in th...

Descripción completa

Detalles Bibliográficos
Autores principales: Banzato, Tommaso, Wodzinski, Marek, Burti, Silvia, Osti, Valentina Longhin, Rossoni, Valentina, Atzori, Manfredo, Zotti, Alessandro
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7889925/
https://www.ncbi.nlm.nih.gov/pubmed/33597566
http://dx.doi.org/10.1038/s41598-021-83515-3
_version_ 1783652404598669312
author Banzato, Tommaso
Wodzinski, Marek
Burti, Silvia
Osti, Valentina Longhin
Rossoni, Valentina
Atzori, Manfredo
Zotti, Alessandro
author_facet Banzato, Tommaso
Wodzinski, Marek
Burti, Silvia
Osti, Valentina Longhin
Rossoni, Valentina
Atzori, Manfredo
Zotti, Alessandro
author_sort Banzato, Tommaso
collection PubMed
description The interpretation of thoracic radiographs is a challenging and error-prone task for veterinarians. Despite recent advancements in machine learning and computer vision, the development of computer-aided diagnostic systems for radiographs remains a challenging and unsolved problem, particularly in the context of veterinary medicine. In this study, a novel method, based on multi-label deep convolutional neural network (CNN), for the classification of thoracic radiographs in dogs was developed. All the thoracic radiographs of dogs performed between 2010 and 2020 in the institution were retrospectively collected. Radiographs were taken with two different radiograph acquisition systems and were divided into two data sets accordingly. One data set (Data Set 1) was used for training and testing and another data set (Data Set 2) was used to test the generalization ability of the CNNs. Radiographic findings used as non mutually exclusive labels to train the CNNs were: unremarkable, cardiomegaly, alveolar pattern, bronchial pattern, interstitial pattern, mass, pleural effusion, pneumothorax, and megaesophagus. Two different CNNs, based on ResNet-50 and DenseNet-121 architectures respectively, were developed and tested. The CNN based on ResNet-50 had an Area Under the Receive-Operator Curve (AUC) above 0.8 for all the included radiographic findings except for bronchial and interstitial patterns both on Data Set 1 and Data Set 2. The CNN based on DenseNet-121 had a lower overall performance. Statistically significant differences in the generalization ability between the two CNNs were evident, with the CNN based on ResNet-50 showing better performance for alveolar pattern, interstitial pattern, megaesophagus, and pneumothorax.
format Online
Article
Text
id pubmed-7889925
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-78899252021-02-22 Automatic classification of canine thoracic radiographs using deep learning Banzato, Tommaso Wodzinski, Marek Burti, Silvia Osti, Valentina Longhin Rossoni, Valentina Atzori, Manfredo Zotti, Alessandro Sci Rep Article The interpretation of thoracic radiographs is a challenging and error-prone task for veterinarians. Despite recent advancements in machine learning and computer vision, the development of computer-aided diagnostic systems for radiographs remains a challenging and unsolved problem, particularly in the context of veterinary medicine. In this study, a novel method, based on multi-label deep convolutional neural network (CNN), for the classification of thoracic radiographs in dogs was developed. All the thoracic radiographs of dogs performed between 2010 and 2020 in the institution were retrospectively collected. Radiographs were taken with two different radiograph acquisition systems and were divided into two data sets accordingly. One data set (Data Set 1) was used for training and testing and another data set (Data Set 2) was used to test the generalization ability of the CNNs. Radiographic findings used as non mutually exclusive labels to train the CNNs were: unremarkable, cardiomegaly, alveolar pattern, bronchial pattern, interstitial pattern, mass, pleural effusion, pneumothorax, and megaesophagus. Two different CNNs, based on ResNet-50 and DenseNet-121 architectures respectively, were developed and tested. The CNN based on ResNet-50 had an Area Under the Receive-Operator Curve (AUC) above 0.8 for all the included radiographic findings except for bronchial and interstitial patterns both on Data Set 1 and Data Set 2. The CNN based on DenseNet-121 had a lower overall performance. Statistically significant differences in the generalization ability between the two CNNs were evident, with the CNN based on ResNet-50 showing better performance for alveolar pattern, interstitial pattern, megaesophagus, and pneumothorax. Nature Publishing Group UK 2021-02-17 /pmc/articles/PMC7889925/ /pubmed/33597566 http://dx.doi.org/10.1038/s41598-021-83515-3 Text en © The Author(s) 2021 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/.
spellingShingle Article
Banzato, Tommaso
Wodzinski, Marek
Burti, Silvia
Osti, Valentina Longhin
Rossoni, Valentina
Atzori, Manfredo
Zotti, Alessandro
Automatic classification of canine thoracic radiographs using deep learning
title Automatic classification of canine thoracic radiographs using deep learning
title_full Automatic classification of canine thoracic radiographs using deep learning
title_fullStr Automatic classification of canine thoracic radiographs using deep learning
title_full_unstemmed Automatic classification of canine thoracic radiographs using deep learning
title_short Automatic classification of canine thoracic radiographs using deep learning
title_sort automatic classification of canine thoracic radiographs using deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7889925/
https://www.ncbi.nlm.nih.gov/pubmed/33597566
http://dx.doi.org/10.1038/s41598-021-83515-3
work_keys_str_mv AT banzatotommaso automaticclassificationofcaninethoracicradiographsusingdeeplearning
AT wodzinskimarek automaticclassificationofcaninethoracicradiographsusingdeeplearning
AT burtisilvia automaticclassificationofcaninethoracicradiographsusingdeeplearning
AT ostivalentinalonghin automaticclassificationofcaninethoracicradiographsusingdeeplearning
AT rossonivalentina automaticclassificationofcaninethoracicradiographsusingdeeplearning
AT atzorimanfredo automaticclassificationofcaninethoracicradiographsusingdeeplearning
AT zottialessandro automaticclassificationofcaninethoracicradiographsusingdeeplearning