COVID-19 deep classification network based on convolution and deconvolution local enhancement

Fang, Lingling; Wang, Xin

doi:10.1016/j.compbiomed.2021.104588

Cited by 9 publications

(5 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By introducing deformable convolution, Li et al [3] proposed a novel multitask network, and experiments on various types of multitask learning proved the e ectiveness of the method in this study. In order to e ectively improve the accuracy of doctors' manual judgment of COVID-19 positive and negative, Fang and Wang [4] proposed a novel coronavirus pneumonia deep classi cation network model based on convolution and deconvolution local enhancement. e experimental results show that the algorithm has good performance.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Chinese Image Discourse Based on Crawler Algorithms

Zhang¹

2022

Mobile Information Systems

View full text Add to dashboard Cite

The study explores the construction of China's image in the context of a major public health event such as the Newcastle pneumonia epidemic by crawling social media data in China during the epidemic prevention and control period. The study argues that, in the era of new media, especially self-media, the image of China in Chinese social media during the prevention and control of the Newcastle pneumonia epidemic presents multiple types of images, ranging from a “dual” image of those fighting and preventing the epidemic in their home country and their country of residence to a “dual” image of those being questioned and even those being “questioned” in their home country and their country of residence. “It is worth noting that in March 2020, the number of people who have been affected by the epidemic in their home countries will be increased to 3,000. It is worth mentioning that in mid to late March 2020, Chinese people in China had a serious negative image crisis, but it was quickly repaired through mechanisms such as government “stabilisers,” mainstream media “gatekeepers,” and audience “self-purification.” One of the lessons is that image repair relies on the “stabiliser,” the “gatekeeper” of mainstream media, and the “self-purification” of the audience. One of the lessons is that image repair relies on the triple factor of “real society—audience” working together. The second lesson is that while the open Internet environment can generate a lot of exaggerated and false information; at the same time, audiences, including Chinese people, can remove misunderstandings and bridge differences through active voices and debates and activate rational and healthy positive energy. The epidemic is a “danger” and an “opportunity” for China’s image.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of Chinese Image Discourse Based on Crawler Algorithms

Zhang¹

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Hasan et al [19] have presented a study that focuses on making it feasible for the 2DEMD-based modified CT-Scan and Chest-X-ray images to be utilized as performance amplification criteria using CNN to detect SARS-Cov-2 virus in patients by utilizing publically accessible radiology images of the three databases. Fang and wang [20] have introduced a particular region of lung infection-based deep network model. The localized ROI features of images are extracted to process images of Covid-19 by utilizing convolution and de-convolution techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

Covid 19 image classification using hybrid averaging transfer learning model

Abbas,

Mahmood,

Ur Rehman

et al. 2023

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

The outbreak of Corona Virus 2019(Covid-19) is a great threat to the whole world. It is crucial to early detect patients infected with covid-19 and treat them to mitigate the rapid spread of this disease. It is an immediate priority to overcome the traditional screening and develop an accurate as well as speedy covid-19 automatic diagnosis system. Computer Tomography (CT) and Chest X-Ray imaging coupled with deep learning models to develop and test Computer Aided Screening (CAS) of covid-19 images from the normal images. In this paper classification and screening of covid-19 disease are performed by using pre-trained convolutional neural networks and a proposed hybrid model on an available standard dataset of chest X-Ray images. The proposed hybrid model employs the pre-trained Convolutional Neural Network models and Transfer Learning models. Our proposed model consists of three stages where extraction of features is performed in first stage by using pre-trained machine learning model. Deep features are extracted by using the infusion of the Transfer Learning Technique in the second stage of the model. The third stage uses Flatten and Classification layers to diagnose of Covid-19 patients. In order to assure the consistency of the proposed model, by considering standard dataset X-Ray images. Simulation results of performance metrics of Accuracy, F1 Score, Precision, Recall, ROC, and AUC curve, and training and testing loss are used to evaluate and compare the proposed model with existing models. Experimental result demonstrates that the hybrid model improves the screening process for Covid-19 disease by achieving higher accuracy.

show abstract

“…There are many real-world challenges in computer vision, aiming to solve the problems of the COVID-19 dataset described above and classify slices. For example, Fang et al [5] proposed enhanced local features based on convolution and deconvolution in CT images to improve the classification accuracy. Singh et al [4] use multi-objective differential evolution-based convolutional neural networks to resolve the difference between infected patients.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Feature Learning Based on Two-Step LSTM and Transformer for CT Scans

Hsu¹,

Tsai²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Computed tomography (CT) imaging could be very practical for diagnosing various diseases. However, the nature of the CT images is even more diverse since the resolution and number of the slices of a CT scan are determined by the machine and its settings. Conventional deep learning models are hard to tickle such diverse data since the essential requirement of the deep neural network is the consistent shape of the input data. In this paper, we propose a novel, effective, two-step-wise approach to tickle this issue for COVID-19 symptom classification thoroughly. First, the semantic feature embedding of each slice for a CT scan is extracted by conventional backbone networks. Then, we proposed a long short-term memory (LSTM) and Transformer-based sub-network to deal with temporal feature learning, leading to spatiotemporal feature representation learning. In this fashion, the proposed two-step LSTM model could prevent overfitting, as well as increase performance. Comprehensive experiments reveal that the proposed two-step method not only shows excellent performance but also could be compensated for each other. More specifically, the two-step LSTM model has a lower false-negative rate, while the two-step Swin model has a lower false-positive rate. In summary, it is suggested that the model ensemble could be adopted to more stable and promising performance in real-world applications.

show abstract

COVID-19 deep classification network based on convolution and deconvolution local enhancement

Cited by 9 publications

References 64 publications

Analysis of Chinese Image Discourse Based on Crawler Algorithms

Analysis of Chinese Image Discourse Based on Crawler Algorithms

Covid 19 image classification using hybrid averaging transfer learning model

Spatiotemporal Feature Learning Based on Two-Step LSTM and Transformer for CT Scans

Contact Info

Product

Resources

About