A Transfer Learning Method for Pneumonia Classification and Visualization
Pneumonia is an infectious disease that affects the lungs and is one of the principal causes of death in children under five years old. The Chest X-ray images technique is one of the most used for diagnosing pneumonia. Several Machine Learning algorithms have been successfully used in order to provi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/8/2908 |
_version_ | 1797569879612588032 |
---|---|
author | Juan Eduardo Luján-García Cornelio Yáñez-Márquez Yenny Villuendas-Rey Oscar Camacho-Nieto |
author_facet | Juan Eduardo Luján-García Cornelio Yáñez-Márquez Yenny Villuendas-Rey Oscar Camacho-Nieto |
author_sort | Juan Eduardo Luján-García |
collection | DOAJ |
description | Pneumonia is an infectious disease that affects the lungs and is one of the principal causes of death in children under five years old. The Chest X-ray images technique is one of the most used for diagnosing pneumonia. Several Machine Learning algorithms have been successfully used in order to provide computer-aided diagnosis by automatic classification of medical images. For its remarkable results, the Convolutional Neural Networks (models based on Deep Learning) that are widely used in Computer Vision tasks, such as classification of injuries and brain abnormalities, among others, stand out. In this paper, we present a transfer learning method that automatically classifies between 3883 chest X-ray images characterized as depicting pneumonia and 1349 labeled as normal. The proposed method uses the Xception Network pre-trained weights on ImageNet as an initialization. Our model is competitive with respect to state-of-the-art proposals. To make comparisons with other models, we have used four well-known performance measures, obtaining the following results: precision (0.84), recall (0.99), F1-score (0.91) and area under the ROC curve (0.97). These positive results allow us to consider our proposal as an alternative that can be useful in countries with a lack of equipment and specialized radiologists. |
first_indexed | 2024-03-10T20:17:33Z |
format | Article |
id | doaj.art-a4e72fe1b38f4ac19982ee9d16a23a83 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T20:17:33Z |
publishDate | 2020-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-a4e72fe1b38f4ac19982ee9d16a23a832023-11-19T22:27:47ZengMDPI AGApplied Sciences2076-34172020-04-01108290810.3390/app10082908A Transfer Learning Method for Pneumonia Classification and VisualizationJuan Eduardo Luján-García0Cornelio Yáñez-Márquez1Yenny Villuendas-Rey2Oscar Camacho-Nieto3Centro de Investigación en Computación, Instituto Politécnico Nacional, Mexico City 07700, MexicoCentro de Investigación en Computación, Instituto Politécnico Nacional, Mexico City 07700, MexicoCentro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional, Mexico City 07700, MexicoCentro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional, Mexico City 07700, MexicoPneumonia is an infectious disease that affects the lungs and is one of the principal causes of death in children under five years old. The Chest X-ray images technique is one of the most used for diagnosing pneumonia. Several Machine Learning algorithms have been successfully used in order to provide computer-aided diagnosis by automatic classification of medical images. For its remarkable results, the Convolutional Neural Networks (models based on Deep Learning) that are widely used in Computer Vision tasks, such as classification of injuries and brain abnormalities, among others, stand out. In this paper, we present a transfer learning method that automatically classifies between 3883 chest X-ray images characterized as depicting pneumonia and 1349 labeled as normal. The proposed method uses the Xception Network pre-trained weights on ImageNet as an initialization. Our model is competitive with respect to state-of-the-art proposals. To make comparisons with other models, we have used four well-known performance measures, obtaining the following results: precision (0.84), recall (0.99), F1-score (0.91) and area under the ROC curve (0.97). These positive results allow us to consider our proposal as an alternative that can be useful in countries with a lack of equipment and specialized radiologists.https://www.mdpi.com/2076-3417/10/8/2908transfer learningpneumoniaclassificationX-rayconvolutionaldeep learning |
spellingShingle | Juan Eduardo Luján-García Cornelio Yáñez-Márquez Yenny Villuendas-Rey Oscar Camacho-Nieto A Transfer Learning Method for Pneumonia Classification and Visualization Applied Sciences transfer learning pneumonia classification X-ray convolutional deep learning |
title | A Transfer Learning Method for Pneumonia Classification and Visualization |
title_full | A Transfer Learning Method for Pneumonia Classification and Visualization |
title_fullStr | A Transfer Learning Method for Pneumonia Classification and Visualization |
title_full_unstemmed | A Transfer Learning Method for Pneumonia Classification and Visualization |
title_short | A Transfer Learning Method for Pneumonia Classification and Visualization |
title_sort | transfer learning method for pneumonia classification and visualization |
topic | transfer learning pneumonia classification X-ray convolutional deep learning |
url | https://www.mdpi.com/2076-3417/10/8/2908 |
work_keys_str_mv | AT juaneduardolujangarcia atransferlearningmethodforpneumoniaclassificationandvisualization AT cornelioyanezmarquez atransferlearningmethodforpneumoniaclassificationandvisualization AT yennyvilluendasrey atransferlearningmethodforpneumoniaclassificationandvisualization AT oscarcamachonieto atransferlearningmethodforpneumoniaclassificationandvisualization AT juaneduardolujangarcia transferlearningmethodforpneumoniaclassificationandvisualization AT cornelioyanezmarquez transferlearningmethodforpneumoniaclassificationandvisualization AT yennyvilluendasrey transferlearningmethodforpneumoniaclassificationandvisualization AT oscarcamachonieto transferlearningmethodforpneumoniaclassificationandvisualization |