Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process

Abstract The purpose of this study was to evaluate the diagnostic performance achieved by using fully-connected small artificial neural networks (ANNs) and a simple training process, the Kim-Monte Carlo algorithm, to detect the location of pneumothorax in chest X-rays. A total of 1,000 chest X-ray i...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yongil Cho, Jong Soo Kim, Tae Ho Lim, Inhye Lee, Jongbong Choi
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/47512f2075b54dc1bb0fc62757da5de9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:47512f2075b54dc1bb0fc62757da5de9
record_format dspace
spelling oai:doaj.org-article:47512f2075b54dc1bb0fc62757da5de92021-12-02T16:06:10ZDetection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process10.1038/s41598-021-92523-22045-2322https://doaj.org/article/47512f2075b54dc1bb0fc62757da5de92021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-92523-2https://doaj.org/toc/2045-2322Abstract The purpose of this study was to evaluate the diagnostic performance achieved by using fully-connected small artificial neural networks (ANNs) and a simple training process, the Kim-Monte Carlo algorithm, to detect the location of pneumothorax in chest X-rays. A total of 1,000 chest X-ray images with pneumothorax were taken randomly from NIH (the National Institutes of Health) public image database and used as the training and test sets. Each X-ray image with pneumothorax was divided into 49 boxes for pneumothorax localization. For each of the boxes in the chest X-ray images contained in the test set, the area under the receiver operating characteristic (ROC) curve (AUC) was 0.882, and the sensitivity and specificity were 80.6% and 83.0%, respectively. In addition, a common currently used deep-learning method for image recognition, the convolution neural network (CNN), was also applied to the same dataset for comparison purposes. The performance of the fully-connected small ANN was better than that of the CNN. Regarding the diagnostic performances of the CNN with different activation functions, the CNN with a sigmoid activation function for fully-connected hidden nodes was better than the CNN with the rectified linear unit (RELU) activation function. This study showed that our approach can accurately detect the location of pneumothorax in chest X-rays, significantly reduce the time delay incurred when diagnosing urgent diseases such as pneumothorax, and increase the effectiveness of clinical practice and patient care.Yongil ChoJong Soo KimTae Ho LimInhye LeeJongbong ChoiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Yongil Cho
Jong Soo Kim
Tae Ho Lim
Inhye Lee
Jongbong Choi
Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process
description Abstract The purpose of this study was to evaluate the diagnostic performance achieved by using fully-connected small artificial neural networks (ANNs) and a simple training process, the Kim-Monte Carlo algorithm, to detect the location of pneumothorax in chest X-rays. A total of 1,000 chest X-ray images with pneumothorax were taken randomly from NIH (the National Institutes of Health) public image database and used as the training and test sets. Each X-ray image with pneumothorax was divided into 49 boxes for pneumothorax localization. For each of the boxes in the chest X-ray images contained in the test set, the area under the receiver operating characteristic (ROC) curve (AUC) was 0.882, and the sensitivity and specificity were 80.6% and 83.0%, respectively. In addition, a common currently used deep-learning method for image recognition, the convolution neural network (CNN), was also applied to the same dataset for comparison purposes. The performance of the fully-connected small ANN was better than that of the CNN. Regarding the diagnostic performances of the CNN with different activation functions, the CNN with a sigmoid activation function for fully-connected hidden nodes was better than the CNN with the rectified linear unit (RELU) activation function. This study showed that our approach can accurately detect the location of pneumothorax in chest X-rays, significantly reduce the time delay incurred when diagnosing urgent diseases such as pneumothorax, and increase the effectiveness of clinical practice and patient care.
format article
author Yongil Cho
Jong Soo Kim
Tae Ho Lim
Inhye Lee
Jongbong Choi
author_facet Yongil Cho
Jong Soo Kim
Tae Ho Lim
Inhye Lee
Jongbong Choi
author_sort Yongil Cho
title Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process
title_short Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process
title_full Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process
title_fullStr Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process
title_full_unstemmed Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process
title_sort detection of the location of pneumothorax in chest x-rays using small artificial neural networks and a simple training process
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/47512f2075b54dc1bb0fc62757da5de9
work_keys_str_mv AT yongilcho detectionofthelocationofpneumothoraxinchestxraysusingsmallartificialneuralnetworksandasimpletrainingprocess
AT jongsookim detectionofthelocationofpneumothoraxinchestxraysusingsmallartificialneuralnetworksandasimpletrainingprocess
AT taeholim detectionofthelocationofpneumothoraxinchestxraysusingsmallartificialneuralnetworksandasimpletrainingprocess
AT inhyelee detectionofthelocationofpneumothoraxinchestxraysusingsmallartificialneuralnetworksandasimpletrainingprocess
AT jongbongchoi detectionofthelocationofpneumothoraxinchestxraysusingsmallartificialneuralnetworksandasimpletrainingprocess
_version_ 1718385084215590912