Deep learning based detection and analysis of COVID-19 on chest X-ray images

Jain, Rachna; Gupta, Meenu; Taneja, Soham; Hemanth, D. Jude

doi:10.1007/s10489-020-01902-1

Cited by 425 publications

(302 citation statements)

References 44 publications

(38 reference statements)

Supporting

Mentioning

294

Contrasting

Unclassified

Order By: Relevance

“…Also, to demonstrate the efficacy of the proposed ensemble based algorithm, a comparison of the proposed algorithm with a number of recent works on COVID detection using Chest X-Ray images have been presented in Table 4. It can be observed that the proposed method integrates the capabilities of state-of-the-art deep learning models to yield comparable or better results that the works where vanilla state-of-the-art deep learning models have been used [12,27,28]. Some of the new methods [29][30][31] show very promising results, though they may suffer from criticism due to the small size of the data used in the experimental set-up.…”

Section: Experiments and Resultsmentioning

confidence: 83%

“…There have been multiple works done by researchers in the area of COVID-19 patient detection using CXR images [4,5,7,12,[26][27][28][29][30][31][32]. In one such work by Makris et al [4], transfer learning has been used with the Inception-v3 network to classify normal, pneumonia and COVID-19 patients using CXR images.…”

Section: Related Workmentioning

confidence: 99%

“…As can be observed, most of the works related to COVID-19 detection from CXR images have utilized individual deep learning models e.g., DenseNet, ResNet, Xception, etc. [12,27,28]. None of the works have tried to combine the models to multiply their capability of classification.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic COVID-19 detection from X-ray images using ensemble learning with convolutional neural network

Das

Ghosh

Thunder

et al. 2021

Pattern Anal Applic

173

View full text Add to dashboard Cite

COVID-19 continues to have catastrophic effects on the lives of human beings throughout the world. To combat this disease it is necessary to screen the affected patients in a fast and inexpensive way. One of the most viable steps towards achieving this goal is through radiological examination, Chest X-Ray being the most easily available and least expensive option. In this paper, we have proposed a Deep Convolutional Neural Network-based solution which can detect the COVID-19 +ve patients using chest X-Ray images. Multiple state-of-the-art CNN models-DenseNet201, Resnet50V2 and Inceptionv3, have been adopted in the proposed work. They have been trained individually to make independent predictions. Then the models are combined, using a new method of weighted average ensembling technique, to predict a class value. To test the efficacy of the solution we have used publicly available chest X-ray images of COVID +ve and-ve cases. 538 images of COVID +ve patients and 468 images of COVID-ve patients have been divided into training, test and validation sets. The proposed approach gave a classification accuracy of 91.62% which is higher than the state-of-the-art CNN models as well the compared benchmark algorithm. We have developed a GUI-based application for public use. This application can be used on any computer by any medical personnel to detect COVID +ve patients using Chest X-Ray images within a few seconds.

show abstract

Section: Experiments and Resultsmentioning

confidence: 83%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic COVID-19 detection from X-ray images using ensemble learning with convolutional neural network

Das

Ghosh

Thunder

et al. 2021

Pattern Anal Applic

173

View full text Add to dashboard Cite

show abstract

“…This type of human reasoning is accommodated by the ProtoPNet model, where comparison of image parts with learned prototypes is integral to the reasoning process of the model. Recently, some deep learning/machine learning models have been developed to classify the X-ray images of Covid-19 patients, normal people and pneumonia patients, see [1], [7], [16], [17], [19], [25], [28], [44]. A survey article is also written that summarizes the research works related to deep learning applications on COVID-19 medical image processing [2].…”

Section: Literature Reviewmentioning

confidence: 99%

These do not Look Like Those: An Interpretable Deep Learning Model for Image Recognition

Singh

Yow

2021

IEEE Access

View full text Add to dashboard Cite

Interpretation of the reasoning process of a prediction made by a deep learning model is always desired. However, when it comes to the predictions of a deep learning model that directly impacts on the lives of people then the interpretation becomes a necessity. In this paper, we introduce a deep learning model: negative-positive prototypical part network (NP-ProtoPNet). This model attempts to imitate human reasoning for image recognition while comparing the parts of a test image with the corresponding parts of the images from known classes. We demonstrate our model on the dataset of chest X-ray images of Covid-19 patients, pneumonia patients and normal people. The accuracy and precision that our model receives is on par with the best performing non-interpretable deep learning models.INDEX TERMS Covid-19, pneumonia, image recognition, X-ray, prototypical part.

show abstract

“…4 ). Like other pneumonia types, a CT scan may be a reliable test for screening SARS-COV 2 cases [ 184 , 185 ]. However, the analysis required specialized equipment and failed to meet a large scale of requirement, and it may not provide benefit for point-of-care (POC) diagnosis of COVID-19.…”

Section: Introductionmentioning

confidence: 99%

Nanobiotechnology as a platform for the diagnosis of COVID-19: a review

Abdelhamid

Badr

2021

Nanotechnol. Environ. Eng.

View full text Add to dashboard Cite

A sensitive method for diagnosing coronavirus disease 2019 (COVID-19) is highly required to fight the current and future global health threats due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV 2). However, most of the current methods exhibited high false-negative rates, resulting in patient misdiagnosis and impeding early treatment. Nanoparticles show promising performance and great potential to serve as a platform for diagnosing viral infection in a short time and with high sensitivity. This review highlighted the potential of nanoparticles as platforms for the diagnosis of COVID-19. Nanoparticles such as gold nanoparticles, magnetic nanoparticles, and graphene (G) were applied to detect SARS-CoV 2. They have been used for molecular-based diagnosis methods and serological methods. Nanoparticles improved specificity and shorten the time required for the diagnosis. They may be implemented into small devices that facilitate the self-diagnosis at home or in places such as airports and shops. Nanoparticles-based methods can be used for the analysis of virus-contaminated samples from a patient, surface, and air. The advantages and challenges were discussed to introduce useful information for designing a sensitive, fast, and low-cost diagnostic method. This review aims to present a helpful survey for the lesson learned from handling this outbreak to prepare ourself for future pandemic.

show abstract

Deep learning based detection and analysis of COVID-19 on chest X-ray images

Cited by 425 publications

References 44 publications

Automatic COVID-19 detection from X-ray images using ensemble learning with convolutional neural network

Automatic COVID-19 detection from X-ray images using ensemble learning with convolutional neural network

These do not Look Like Those: An Interpretable Deep Learning Model for Image Recognition

Nanobiotechnology as a platform for the diagnosis of COVID-19: a review

Contact Info

Product

Resources

About