Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture
The coronavirus pandemic is spreading around the world. Medical imaging modalities such as radiography play an important role in the fight against COVID-19. Deep learning (DL) techniques have been able to improve medical imaging tools and help radiologists to make clinical decisions for the diagnosi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/5/4/73 |
| _version_ | 1797506623432818688 |
|---|---|
| author | Mohamed Chetoui Moulay A. Akhloufi Bardia Yousefi El Mostafa Bouattane |
| author_facet | Mohamed Chetoui Moulay A. Akhloufi Bardia Yousefi El Mostafa Bouattane |
| author_sort | Mohamed Chetoui |
| collection | DOAJ |
| description | The coronavirus pandemic is spreading around the world. Medical imaging modalities such as radiography play an important role in the fight against COVID-19. Deep learning (DL) techniques have been able to improve medical imaging tools and help radiologists to make clinical decisions for the diagnosis, monitoring and prognosis of different diseases. Computer-Aided Diagnostic (CAD) systems can improve work efficiency by precisely delineating infections in chest X-ray (CXR) images, thus facilitating subsequent quantification. CAD can also help automate the scanning process and reshape the workflow with minimal patient contact, providing the best protection for imaging technicians. The objective of this study is to develop a deep learning algorithm to detect COVID-19, pneumonia and normal cases on CXR images. We propose two classifications problems, (i) a binary classification to classify COVID-19 and normal cases and (ii) a multiclass classification for COVID-19, pneumonia and normal. Nine datasets and more than 3200 COVID-19 CXR images are used to assess the efficiency of the proposed technique. The model is trained on a subset of the National Institute of Health (NIH) dataset using swish activation, thus improving the training accuracy to detect COVID-19 and other pneumonia. The models are tested on eight merged datasets and on individual test sets in order to confirm the degree of generalization of the proposed algorithms. An explainability algorithm is also developed to visually show the location of the lung-infected areas detected by the model. Moreover, we provide a detailed analysis of the misclassified images. The obtained results achieve high performances with an Area Under Curve (AUC) of 0.97 for multi-class classification (COVID-19 vs. other pneumonia vs. normal) and 0.98 for the binary model (COVID-19 vs. normal). The average sensitivity and specificity are 0.97 and 0.98, respectively. The sensitivity of the COVID-19 class achieves 0.99. The results outperformed the comparable state-of-the-art models for the detection of COVID-19 on CXR images. The explainability model shows that our model is able to efficiently identify the signs of COVID-19. |
| first_indexed | 2024-03-10T04:35:11Z |
| format | Article |
| id | doaj.art-e444bfe41dd04ae1a8283436fed90aad |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-10T04:35:11Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-e444bfe41dd04ae1a8283436fed90aad2023-11-23T03:51:18ZengMDPI AGBig Data and Cognitive Computing2504-22892021-12-01547310.3390/bdcc5040073Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network ArchitectureMohamed Chetoui0Moulay A. Akhloufi1Bardia Yousefi2El Mostafa Bouattane3Perception, Robotics, and Intelligent Machines Research Group (PRIME), Department of Computer Science, Université de Moncton, Moncton, NB E1A 3E9, CanadaPerception, Robotics, and Intelligent Machines Research Group (PRIME), Department of Computer Science, Université de Moncton, Moncton, NB E1A 3E9, CanadaFischell Department of Bioengineering, University of Maryland, College Park, MD 20742, USAMontfort Academic Hospital & Institut du Savoir Montfort, Ottawa, ON 61350, CanadaThe coronavirus pandemic is spreading around the world. Medical imaging modalities such as radiography play an important role in the fight against COVID-19. Deep learning (DL) techniques have been able to improve medical imaging tools and help radiologists to make clinical decisions for the diagnosis, monitoring and prognosis of different diseases. Computer-Aided Diagnostic (CAD) systems can improve work efficiency by precisely delineating infections in chest X-ray (CXR) images, thus facilitating subsequent quantification. CAD can also help automate the scanning process and reshape the workflow with minimal patient contact, providing the best protection for imaging technicians. The objective of this study is to develop a deep learning algorithm to detect COVID-19, pneumonia and normal cases on CXR images. We propose two classifications problems, (i) a binary classification to classify COVID-19 and normal cases and (ii) a multiclass classification for COVID-19, pneumonia and normal. Nine datasets and more than 3200 COVID-19 CXR images are used to assess the efficiency of the proposed technique. The model is trained on a subset of the National Institute of Health (NIH) dataset using swish activation, thus improving the training accuracy to detect COVID-19 and other pneumonia. The models are tested on eight merged datasets and on individual test sets in order to confirm the degree of generalization of the proposed algorithms. An explainability algorithm is also developed to visually show the location of the lung-infected areas detected by the model. Moreover, we provide a detailed analysis of the misclassified images. The obtained results achieve high performances with an Area Under Curve (AUC) of 0.97 for multi-class classification (COVID-19 vs. other pneumonia vs. normal) and 0.98 for the binary model (COVID-19 vs. normal). The average sensitivity and specificity are 0.97 and 0.98, respectively. The sensitivity of the COVID-19 class achieves 0.99. The results outperformed the comparable state-of-the-art models for the detection of COVID-19 on CXR images. The explainability model shows that our model is able to efficiently identify the signs of COVID-19.https://www.mdpi.com/2504-2289/5/4/73COVID-19convolutional neural networksefficientnetchest X-raypneumoniaradiology |
| spellingShingle | Mohamed Chetoui Moulay A. Akhloufi Bardia Yousefi El Mostafa Bouattane Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture Big Data and Cognitive Computing COVID-19 convolutional neural networks efficientnet chest X-ray pneumonia radiology |
| title | Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture |
| title_full | Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture |
| title_fullStr | Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture |
| title_full_unstemmed | Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture |
| title_short | Explainable COVID-19 Detection on Chest X-rays Using an End-to-End Deep Convolutional Neural Network Architecture |
| title_sort | explainable covid 19 detection on chest x rays using an end to end deep convolutional neural network architecture |
| topic | COVID-19 convolutional neural networks efficientnet chest X-ray pneumonia radiology |
| url | https://www.mdpi.com/2504-2289/5/4/73 |
| work_keys_str_mv | AT mohamedchetoui explainablecovid19detectiononchestxraysusinganendtoenddeepconvolutionalneuralnetworkarchitecture AT moulayaakhloufi explainablecovid19detectiononchestxraysusinganendtoenddeepconvolutionalneuralnetworkarchitecture AT bardiayousefi explainablecovid19detectiononchestxraysusinganendtoenddeepconvolutionalneuralnetworkarchitecture AT elmostafabouattane explainablecovid19detectiononchestxraysusinganendtoenddeepconvolutionalneuralnetworkarchitecture |