Naseer A, Tamoor M, Azhar A. Computer-aided COVID-19 diagnosis and a comparison of deep learners using augmented CXRs.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY 2022;
30:89-109. [PMID:
34842222 PMCID:
PMC8842762 DOI:
10.3233/xst-211047]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 10/26/2021] [Accepted: 11/09/2021] [Indexed: 06/13/2023]
Abstract
BACKGROUND
Coronavirus Disease 2019 (COVID-19) is contagious, producing respiratory tract infection, caused by a newly discovered coronavirus. Its death toll is too high, and early diagnosis is the main problem nowadays. Infected people show a variety of symptoms such as fatigue, fever, tastelessness, dry cough, etc. Some other symptoms may also be manifested by radiographic visual identification. Therefore, Chest X-Rays (CXR) play a key role in the diagnosis of COVID-19.
METHODS
In this study, we use Chest X-Rays images to develop a computer-aided diagnosis (CAD) of the disease. These images are used to train two deep networks, the Convolution Neural Network (CNN), and the Long Short-Term Memory Network (LSTM) which is an artificial Recurrent Neural Network (RNN). The proposed study involves three phases. First, the CNN model is trained on raw CXR images. Next, it is trained on pre-processed CXR images and finally enhanced CXR images are used for deep network CNN training. Geometric transformations, color transformations, image enhancement, and noise injection techniques are used for augmentation. From augmentation, we get 3,220 augmented CXRs as training datasets. In the final phase, CNN is used to extract the features of CXR imagery that are fed to the LSTM model. The performance of the four trained models is evaluated by the evaluation techniques of different models, including accuracy, specificity, sensitivity, false-positive rate, and receiver operating characteristic (ROC) curve.
RESULTS
We compare our results with other benchmark CNN models. Our proposed CNN-LSTM model gives superior accuracy (99.02%) than the other state-of-the-art models. Our method to get improved input, helped the CNN model to produce a very high true positive rate (TPR 1) and no false-negative result whereas false negative was a major problem while using Raw CXR images.
CONCLUSIONS
We conclude after performing different experiments that some image pre-processing and augmentation, remarkably improves the results of CNN-based models. It will help a better early detection of the disease that will eventually reduce the mortality rate of COVID.
Collapse