COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings
The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aime...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2020/8828855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551241346973696 |
|---|---|
| author | Mohd Zulfaezal Che Azemin Radhiana Hassan Mohd Izzuddin Mohd Tamrin Mohd Adli Md Ali |
| author_facet | Mohd Zulfaezal Che Azemin Radhiana Hassan Mohd Izzuddin Mohd Tamrin Mohd Adli Md Ali |
| author_sort | Mohd Zulfaezal Che Azemin |
| collection | DOAJ |
| description | The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing. |
| format | Article |
| id | doaj-art-2c63171270974f0bb4537e8fa0f21f56 |
| institution | Kabale University |
| issn | 1687-4188 1687-4196 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-2c63171270974f0bb4537e8fa0f21f562025-02-03T06:04:37ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962020-01-01202010.1155/2020/88288558828855COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary FindingsMohd Zulfaezal Che Azemin0Radhiana Hassan1Mohd Izzuddin Mohd Tamrin2Mohd Adli Md Ali3Kulliyyah of Allied Health Sciences, International Islamic University Malaysia, Bandar Indera Mahkota, 25200 Kuantan, Pahang, MalaysiaKulliyyah of Medicine, International Islamic University Malaysia, Bandar Indera Mahkota, 25200 Kuantan, Pahang, MalaysiaKulliyyah of ICT, International Islamic University Malaysia, 50728 Gombak, Kuala Lumpur, MalaysiaKulliyyah of Science, International Islamic University Malaysia, Bandar Indera Mahkota, 25200 Kuantan, Pahang, MalaysiaThe key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing.http://dx.doi.org/10.1155/2020/8828855 |
| spellingShingle | Mohd Zulfaezal Che Azemin Radhiana Hassan Mohd Izzuddin Mohd Tamrin Mohd Adli Md Ali COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings International Journal of Biomedical Imaging |
| title | COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings |
| title_full | COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings |
| title_fullStr | COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings |
| title_full_unstemmed | COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings |
| title_short | COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings |
| title_sort | covid 19 deep learning prediction model using publicly available radiologist adjudicated chest x ray images as training data preliminary findings |
| url | http://dx.doi.org/10.1155/2020/8828855 |
| work_keys_str_mv | AT mohdzulfaezalcheazemin covid19deeplearningpredictionmodelusingpubliclyavailableradiologistadjudicatedchestxrayimagesastrainingdatapreliminaryfindings AT radhianahassan covid19deeplearningpredictionmodelusingpubliclyavailableradiologistadjudicatedchestxrayimagesastrainingdatapreliminaryfindings AT mohdizzuddinmohdtamrin covid19deeplearningpredictionmodelusingpubliclyavailableradiologistadjudicatedchestxrayimagesastrainingdatapreliminaryfindings AT mohdadlimdali covid19deeplearningpredictionmodelusingpubliclyavailableradiologistadjudicatedchestxrayimagesastrainingdatapreliminaryfindings |