A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis
Over the past year, the AI community has constructed several deep learning models for diagnosing COVID-19 based on the visual features of chest X-rays. While deep learning researchers have commonly focused much of their attention on designing deep learning classifiers, only a fraction of these same...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Biomedical Engineering Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667099222000172 |
| _version_ | 1811257971388186624 |
|---|---|
| author | Robert Hertel Rachid Benlamri |
| author_facet | Robert Hertel Rachid Benlamri |
| author_sort | Robert Hertel |
| collection | DOAJ |
| description | Over the past year, the AI community has constructed several deep learning models for diagnosing COVID-19 based on the visual features of chest X-rays. While deep learning researchers have commonly focused much of their attention on designing deep learning classifiers, only a fraction of these same researchers have dedicated effort to including a segmentation module in their system. This is unfortunate since other applications in radiology typically require segmentation as a necessary prerequisite step in building truly deployable clinical models. Differentiating COVID-19 from other pulmonary diseases can be challenging as various lung diseases share common visual features with COVID-19. To help clarify the diagnosis of suspected COVID-19 patients, we have designed our deep learning pipeline with a segmentation module and ensemble classifier. Following a detailed description of our deep learning pipeline, we present the strengths and shortcomings of our approach and compare our model with other similarly constructed models. While doing so, we focus our attention on widely circulated public datasets and describe several fallacies we have noticed in the literature concerning them. After performing a thorough comparative analysis, we demonstrate that our best model can successfully obtain an accuracy of 91 percent and sensitivity of 92 percent. |
| first_indexed | 2024-04-12T18:05:55Z |
| format | Article |
| id | doaj.art-137c2094ea4f4c80846c4778b2960a4a |
| institution | Directory Open Access Journal |
| issn | 2667-0992 |
| language | English |
| last_indexed | 2024-04-12T18:05:55Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Biomedical Engineering Advances |
| spelling | doaj.art-137c2094ea4f4c80846c4778b2960a4a2022-12-22T03:21:59ZengElsevierBiomedical Engineering Advances2667-09922022-06-013100041A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosisRobert Hertel0Rachid Benlamri1Lakehead University, 955 Oliver Rd, Thunder Bay, ON P7B 5E1, Canada; Corresponding author.University of Doha for Science and Technology - Qatar, 24449 Arab League St, Doha, QatarOver the past year, the AI community has constructed several deep learning models for diagnosing COVID-19 based on the visual features of chest X-rays. While deep learning researchers have commonly focused much of their attention on designing deep learning classifiers, only a fraction of these same researchers have dedicated effort to including a segmentation module in their system. This is unfortunate since other applications in radiology typically require segmentation as a necessary prerequisite step in building truly deployable clinical models. Differentiating COVID-19 from other pulmonary diseases can be challenging as various lung diseases share common visual features with COVID-19. To help clarify the diagnosis of suspected COVID-19 patients, we have designed our deep learning pipeline with a segmentation module and ensemble classifier. Following a detailed description of our deep learning pipeline, we present the strengths and shortcomings of our approach and compare our model with other similarly constructed models. While doing so, we focus our attention on widely circulated public datasets and describe several fallacies we have noticed in the literature concerning them. After performing a thorough comparative analysis, we demonstrate that our best model can successfully obtain an accuracy of 91 percent and sensitivity of 92 percent.http://www.sciencedirect.com/science/article/pii/S2667099222000172CoronavirusCOVID-19Convolutional neural networkDeep learningChest X-rayComputer vision |
| spellingShingle | Robert Hertel Rachid Benlamri A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis Biomedical Engineering Advances Coronavirus COVID-19 Convolutional neural network Deep learning Chest X-ray Computer vision |
| title | A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis |
| title_full | A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis |
| title_fullStr | A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis |
| title_full_unstemmed | A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis |
| title_short | A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis |
| title_sort | deep learning segmentation classification pipeline for x ray based covid 19 diagnosis |
| topic | Coronavirus COVID-19 Convolutional neural network Deep learning Chest X-ray Computer vision |
| url | http://www.sciencedirect.com/science/article/pii/S2667099222000172 |
| work_keys_str_mv | AT roberthertel adeeplearningsegmentationclassificationpipelineforxraybasedcovid19diagnosis AT rachidbenlamri adeeplearningsegmentationclassificationpipelineforxraybasedcovid19diagnosis AT roberthertel deeplearningsegmentationclassificationpipelineforxraybasedcovid19diagnosis AT rachidbenlamri deeplearningsegmentationclassificationpipelineforxraybasedcovid19diagnosis |