Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network.

Abbas A, Abdelsamea MM, Abdelsamea MM, Gaber MM. · 2021

Read Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. by Abbas A, Abdelsamea MM, Abdelsamea MM, Gaber MM. (2021) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc7474514.txt.

Introduction

Abbas, Abdelsamea, and Gaber test a deep learning method to classify COVID-19 in chest X-ray images. Chest X-ray is a first imaging step in diagnosis. Labeled medical images are scarce, which makes training hard.

Their method, DeTraC, stands for Decompose, Transfer, and Compose. It borrows knowledge from general image tasks through transfer learning. A class decomposition step handles uneven or messy image sets. The team tested it on images gathered from hospitals around the world. DeTraC reached an accuracy of 93.1 percent in detecting COVID-19 cases among normal and SARS cases with strong sensitivity results. The authors say the method copes well with irregular data. It may aid fast screening where expert readers are few.

Catalog record

CREATORAbbas A, Abdelsamea MM, Abdelsamea MM, Gaber MM.
YEAR2021
COLLECTIONPAPERS
FORMATTXT
FILE SIZE35 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC7474514

Browse the full library · About the Tower of Babel

Full text

The opening of the work, from the library's hosted text:

Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network By Asmaa Abbas, Mohammed M Abdelsamea, Mohamed Medhat Gaber Published in: Applied Intelligence (Dordrecht, Netherlands) DOI: 10.1007/s10489-020-01829-7 ABSTRACT Abstract Chest X-ray is the first imaging technique that plays an important role in the diagnosis of COVID-19 disease. Due to the high availability of large-scale annotated image datasets, great success has been achieved using convolutional neural networks (CNN s) for image recognition and classification. However, due to the limited availability of annotated medical images, the classification of medical images remains the biggest challenge in medical diagnosis. Thanks to transfer learning, an effective mechanism that can provide a promising solution by transferring knowledge from generic object recognition tasks to domain-specific tasks. In this paper, we validate and a deep CNN, called Decompose, Transfer, and Compose (DeTraC), for the classification of COVID-19 chest X-ray images. DeTraC can deal with any irregularities in the image dataset by investigating its class boundaries using a class decomposition mechanism. The experimental results showed the capability of DeTraC in the detection of COVID-19 cases from a comprehensive image dataset collected from several hospitals around the world. High accuracy of 93.1% (with a sensitivity of 100%) was achieved by DeTraC in the detection of COVID-19 X-ray images from normal, and severe acute respiratory syndrome cases. Keywords: DeTraC, Covolutional neural networks, COVID-19 detection, Chest X-ray images, Data irregularities INTRODUCTION Diagnosis of COVID-19 is typically associated with both the symptoms of pneumonia and Chest X-ray tests [25]. Chest X-ray is the first imaging technique that plays an important role in the diagnosis of COVID-19 disease. Figure 1 shows a negative example of a normal chest X-ray, a positive one with COVID-19, and a positive one with the severe acute respiratory syndrome (SARS). [Figure: Examples of a) normal, b) COVID-19, and c) SARS chest X-ray images] Several classical machine learning approaches have been previously used for automatic classification of digitised chest images [7, 13]. For example, in [17], three statistical features were calculated from lung texture to discriminate between malignant and benign lung nodules using a Support Vector Machine SVM classifier. A grey-level co-occurrence matrix method was used with Backpropagation Network [22] to classify images from being normal or cancerous. With the availability of enough annotated images, deep learning approaches [1, 3, 30] have demonstrated their superiority over the classical machine learning approaches. CNN architecture is one of the most popular deep learning approaches with superior achievements in the medical imaging domain [14]. The primary success of CNN is due to its ability to learn features automatically from domain-specific images, unlike the classical machine learning methods. The popular strategy for training CNN architecture is to transfer learned knowledge from a pre-trained network that fulfilled one task into a new task [19]. This method is faster and easy to apply without the need for a huge annotated dataset for training; therefore many researchers tend to apply this strategy especially with medical imaging. Transfer learning can be accomplished with three major scenarios [16]: a) “shallow tuning”, which adapts only the last classification layer to cope with the new task, and freezes the parameters of the remaining layers without training; b) “deep tuning” which aims to retrain all the parameters of the pre-trained network from end-to-end manner; and (c) “fine-tuning” that aims to gradually train more layers by tuning the learning parameters until a significant performance boost is achieved. Transfer knowledge via fine-tuning mechanism showed outstanding performance in chest X-ray image classification [3, 9, 26]. Class decomposition [33] has been proposed with the aim of enhancing low variance classifiers facilitating more flexibility to their decision boundaries. It aims to the simplification of the local structure of a dataset in a way to cope with any irregularities in the data distribution. Class decomposition has been previously used in various automatic learning workbooks as a pre-processing step to improve the performance of different classification models. In the medical diagnostic domain, class decomposition has been applied to significantly enhance the classification performance of models such as Random Forests, Naive Bayes, C4.5, and SV M [20, 21, 37]. In this paper, we adapt our previously proposed convolutional neural network architecture based on class decomposition, which we term Decompose, Transfer, and Compose (DeTraC) model, to improve the performance of pre-trained models on the detection of COVID-19 cases from chest X-ray images.1 This is by adding a class decomposition layer to the pre-trained models. The class decomposition layer aims to partition each class within the image dataset into several sub-classes and then assign new labels to the new set, where each subset is treated as an independent class, then those subsets are assembled back to produce the final predictions. For the classification performance evaluation, we used images of chest X-ray collected from several hospitals and institutions. The dataset provides complicated computer vision challenging problems due to the intensity inhomogeneity in the images and irregularities in the data distribution. The paper is organised as follow. In Section 2, we review the state-of-the-art methods for COVID-19 detection. Section 3 discusses the main components of DeTraC and its adaptation to the detection of COVID-19 cases. Section 4 describes our experiments on several chest X-ray images collected from different hospitals. In Section 5, we discuss our findings. Finally, Section 6 concludes the work. RELATED WORK In the last few months, World Health Organization (WHO) has declared that a new virus called COVID-19 has been spread aggressively in several countries around the world [18]. Diagnosis of COVID-19 is typically associated with the symptoms of pneumonia, which can be revealed by genetic and imaging tests. Fast detection of the COVID-19 can be contributed to control the spread of the disease. Image tests can provide a fast detection of COVID-19, and consequently contribute to control the spread of the disease. Chest X-ray (CXR) and Computed Tomography (CT) are the imaging techniques that play an important role in the diagnosis of COVID-19 disease. The historical conception of image diagnostic systems has been comprehensively explored through several approaches ranging from feature engineering to feature learning. Convolutional neural network (CNN) is one of the most popular and effective approaches in the diagnosis of COVD-19 from digitised images. Several reviews have been carried out to highlight recent contributions to COVID-19 detection [8, 15, 24]. For example, in [35], a CNN was applied based on Inception network to detect COVID-19 disease within CT. In [29], a modified version of ResNet-50 pre-trained network has been provided to classify CT images into three classes: healthy, COVID-19 and bacterial pneumonia. CXR were used in [23] by a CNN constructed based on various ImageNet pre-trained models to extract the high level features. Those features were fed into SVM as a machine learning classifier in order to detect the COVID-19 cases. Moreover, in [34], a CNN architecture called COVID-Net based on transfer learning was applied to classify the CXR images into four classes: normal, bacterial infection, non-COVID and COVID-19 viral infection. In [4], a dataset of CXR images from patients with pneumonia, confirmed COVID-19 disease, and normal incidents, was used to evaluate the performance of state-of-the-art convolutional neural network architectures proposed previously for medical image classification. The study suggested that transfer learning can extract significant

Read the complete text