Abstract:In the current COVID-19 pandemic situation, there is an urgent need to screen infected patients quickly and accurately. Using deep learning models trained on chest X-ray images can become an efficient method for screening COVID-19 patients in these situations. Deep learning approaches are already widely used in the medical community. However, they require a large amount of data to be accurate. The open-source community 1 collectively has made efforts to collect and annotate the data, but it is not enough to tr… Show more
“…This dataset is available on the website: https://www.kaggle.com/tawsifurrahman/covid19-radiography-database/ . This dataset was created by a team of researchers from some universities and hospitals, which comprises 1200 COVID-19 cases, 1341 normal images, and 1345 viral pneumonia cases [ 9 ]. Figure 8 shows a few examples of chest X-ray images of three categories.…”
The worldwide outbreak of the new coronavirus disease (COVID-19) has been declared a pandemic by the World Health Organization (WHO). It has a devastating impact on daily life, public health, and global economy. Due to the highly infectiousness, it is urgent to early screening of suspected cases quickly and accurately. Chest X-ray medical image, as a diagnostic basis for COVID-19, arouses attention from medical engineering. However, due to small lesion difference and lack of training data, the accuracy of detection model is insufficient. In this work, a transfer learning strategy is introduced to hierarchical structure to enhance high-level features of deep convolutional neural networks. The proposed framework consisting of asymmetric pretrained DCNNs with attention networks integrates various information into a wider architecture to learn more discriminative and complementary features. Furthermore, a novel cross-entropy loss function with a penalty term weakens misclassification. Extensive experiments are implemented on the COVID-19 dataset. Compared with the state-of-the-arts, the effectiveness and high performance of the proposed method are demonstrated.
“…This dataset is available on the website: https://www.kaggle.com/tawsifurrahman/covid19-radiography-database/ . This dataset was created by a team of researchers from some universities and hospitals, which comprises 1200 COVID-19 cases, 1341 normal images, and 1345 viral pneumonia cases [ 9 ]. Figure 8 shows a few examples of chest X-ray images of three categories.…”
The worldwide outbreak of the new coronavirus disease (COVID-19) has been declared a pandemic by the World Health Organization (WHO). It has a devastating impact on daily life, public health, and global economy. Due to the highly infectiousness, it is urgent to early screening of suspected cases quickly and accurately. Chest X-ray medical image, as a diagnostic basis for COVID-19, arouses attention from medical engineering. However, due to small lesion difference and lack of training data, the accuracy of detection model is insufficient. In this work, a transfer learning strategy is introduced to hierarchical structure to enhance high-level features of deep convolutional neural networks. The proposed framework consisting of asymmetric pretrained DCNNs with attention networks integrates various information into a wider architecture to learn more discriminative and complementary features. Furthermore, a novel cross-entropy loss function with a penalty term weakens misclassification. Extensive experiments are implemented on the COVID-19 dataset. Compared with the state-of-the-arts, the effectiveness and high performance of the proposed method are demonstrated.
“…Figure 3 depicts the typical split of the available dataset. As COVID-19 is an ongoing and new pandemic, the available datasets are insufficient and imbalanced to train the model effectively [18] . To deal with the data scarcity problem two strategies are often used: Transfer Learning Data Augmentation Fig.…”
“…Ma et al [74] applied FSL, domain generalization, and knowledge transfer for segmentation tasks on a limited COVID19 dataset. Jadon and Shruti in [75] proposed FSL with siamese networks followed by contrastive loss function to detect COVID19 in CXR images. Authors achieved 96.4% accuracy vs. logistic regression baseline model that showed 83%.…”
Section: Emerging Issues In Covid19 Predictionmentioning
As the COVID19 pandemic evolves and coronavirus mutates to different variants, a high workload falls on the shoulders of doctors and radiologists. Identifying COVID19 through X-ray and Computed Tomography (CT) scanning in a short amount of time is vital because it helps doctors start the COVID19 treatment in the early stages. Deep Learning algorithms showed tremendous results in automating COVID19 detection using X-ray and CT scans. As there are not many survey papers on COVID19 detection using deep learning techniques, the goal of this paper is (1) to give a thorough discussion of COVID19 prediction considering Computer Vision problems like COVID19/pneumonia classification, detection, and segmentation, (2) to address new advances in deep learning like Transformers, GANs, and LSTMs, and (3) to cover technical issues like data security and data scarcity of X-ray and CT scans in COVID19.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
