EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images
Abstract The Coronavirus has spread across the world and infected millions of people, causing devastating damage to the public health and global economies. To mitigate the impact of the coronavirus a reliable, fast, and accurate diagnostic system should be promptly implemented. In this study, we pro...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/04cc48e64d5b4808832af9d829d17ca5 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:04cc48e64d5b4808832af9d829d17ca5 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:04cc48e64d5b4808832af9d829d17ca52021-11-08T10:52:39ZEpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images10.1038/s41598-021-00524-y2045-2322https://doaj.org/article/04cc48e64d5b4808832af9d829d17ca52021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-00524-yhttps://doaj.org/toc/2045-2322Abstract The Coronavirus has spread across the world and infected millions of people, causing devastating damage to the public health and global economies. To mitigate the impact of the coronavirus a reliable, fast, and accurate diagnostic system should be promptly implemented. In this study, we propose EpistoNet, a decision tree-based ensemble model using two mixtures of discriminative experts to classify COVID-19 lung infection from chest X-ray images. To optimize the architecture and hyper-parameters of the designed neural networks, we employed Epistocracy algorithm, a recently proposed hyper-heuristic evolutionary method. Using 2500 chest X-ray images consisting of 1250 COVID-19 and 1250 non-COVID-19 cases, we left out 500 images for testing and partitioned the remaining 2000 images into 5 different clusters using K-means clustering algorithm. We trained multiple deep convolutional neural networks on each cluster to help build a mixture of strong discriminative experts from the top-performing models supervised by a gating network. The final ensemble model obtained 95% accuracy on COVID-19 images and 93% accuracy on non-COVID-19. The experimental results show that EpistoNet can accurately, and reliably be used to detect COVID-19 infection in the chest X-ray images, and Epistocracy algorithm can be effectively used to optimize the hyper-parameters of the proposed models.Seyed Ziae Mousavi MojabSeyedmohammad ShamsFarshad FotouhiHamid Soltanian-ZadehNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Seyed Ziae Mousavi Mojab Seyedmohammad Shams Farshad Fotouhi Hamid Soltanian-Zadeh EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images |
description |
Abstract The Coronavirus has spread across the world and infected millions of people, causing devastating damage to the public health and global economies. To mitigate the impact of the coronavirus a reliable, fast, and accurate diagnostic system should be promptly implemented. In this study, we propose EpistoNet, a decision tree-based ensemble model using two mixtures of discriminative experts to classify COVID-19 lung infection from chest X-ray images. To optimize the architecture and hyper-parameters of the designed neural networks, we employed Epistocracy algorithm, a recently proposed hyper-heuristic evolutionary method. Using 2500 chest X-ray images consisting of 1250 COVID-19 and 1250 non-COVID-19 cases, we left out 500 images for testing and partitioned the remaining 2000 images into 5 different clusters using K-means clustering algorithm. We trained multiple deep convolutional neural networks on each cluster to help build a mixture of strong discriminative experts from the top-performing models supervised by a gating network. The final ensemble model obtained 95% accuracy on COVID-19 images and 93% accuracy on non-COVID-19. The experimental results show that EpistoNet can accurately, and reliably be used to detect COVID-19 infection in the chest X-ray images, and Epistocracy algorithm can be effectively used to optimize the hyper-parameters of the proposed models. |
format |
article |
author |
Seyed Ziae Mousavi Mojab Seyedmohammad Shams Farshad Fotouhi Hamid Soltanian-Zadeh |
author_facet |
Seyed Ziae Mousavi Mojab Seyedmohammad Shams Farshad Fotouhi Hamid Soltanian-Zadeh |
author_sort |
Seyed Ziae Mousavi Mojab |
title |
EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images |
title_short |
EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images |
title_full |
EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images |
title_fullStr |
EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images |
title_full_unstemmed |
EpistoNet: an ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images |
title_sort |
epistonet: an ensemble of epistocracy-optimized mixture of experts for detecting covid-19 on chest x-ray images |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/04cc48e64d5b4808832af9d829d17ca5 |
work_keys_str_mv |
AT seyedziaemousavimojab epistonetanensembleofepistocracyoptimizedmixtureofexpertsfordetectingcovid19onchestxrayimages AT seyedmohammadshams epistonetanensembleofepistocracyoptimizedmixtureofexpertsfordetectingcovid19onchestxrayimages AT farshadfotouhi epistonetanensembleofepistocracyoptimizedmixtureofexpertsfordetectingcovid19onchestxrayimages AT hamidsoltanianzadeh epistonetanensembleofepistocracyoptimizedmixtureofexpertsfordetectingcovid19onchestxrayimages |
_version_ |
1718442491683799040 |