Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays

Tsiknakis, Nikos; Trivizakis, Eleftherios; Vassalou, Evangelia E.; Papadakis, Georgios Z.; Spandidos, Demetrios A.; Tsatsakis, Aristidis; Sánchez-García, José; López‐González, Rafael; Papanikolaou, Nikolaos; Karantanas, Apostolos H.; Marias, Kostas

doi:10.3892/etm.2020.8797

Cited by 103 publications

(121 citation statements)

References 24 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…In [147] , an already existing deep learning algorithm that is used for detection of tuberculosis via CT images is generalized to identify covid-19 cases as well. In order to manage small data set problem, transfer learning techniques are used in [148] . A transfer learning based on the Residual Network (RESNET-50) was proposed in [149] to model the development of CT images.…”

Section: Chest Computed Tomography and X-ray Image Processingmentioning

confidence: 99%

Applications of artificial intelligence in battling against covid-19: A literature review

2021

Chaos, Solitons & Fractals

156

View full text Add to dashboard Cite

show abstract

Section: Chest Computed Tomography and X-ray Image Processingmentioning

confidence: 99%

Applications of artificial intelligence in battling against covid-19: A literature review

2021

Chaos, Solitons & Fractals

156

View full text Add to dashboard Cite

show abstract

“… FC-Densenet103, Unet, DenseNet, and DenseNet121-FPN. References References [ 137 ] [ 138 ] [ 139 ] [ 140 ] [ 141 ] [ 142 ] [ 143 ] [ 129 ] [ 144 ] [ 145 ] [ 146 ] [ 147 ] [ 148 ] [ 149 ] [ 150 ] [ 151 ] [ 152 ] [ 153 ] [ 154 ] [ 155 ] [ 156 ] [ 157 ] [ 158 ] [ 159 ] [ 160 ] [ 161 ] [ 162 ] [ 163 ] [ 164 ] [ 165 ] Classification Characteristics Characteristics Gray scale feature extraction and ML classifier, and model-based techniques. Resnet-50, CNN, SVM, ResNet101, VGG16, and VGG19.…”

Section: Artificial Intelligence Architectures For Ards Characterizatmentioning

confidence: 99%

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

Suri¹,

Agarwal²,

Gupta

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…The research article from [27] involves a variation of the CheXNet [70] deep learning model to build COVID-CXNet which is then used to detect COVID-19-based pneumonia from chest radiographs. The study from [83] introduces an AI framework for the detection of COVID-19 from chest X-rays which used a standard version of the Inception-V3 network architecture pre-trained on ImageNet [21] dataset. The study also introduces attention maps to validate detected regions of interest in chest radiographs.…”

Section: Related Workmentioning

confidence: 99%

COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays

Singh

Pandey

Babu

2021

Neural Comput & Applic

View full text Add to dashboard Cite

COVID-19 has emerged as a global crisis with unprecedented socioeconomic challenges, jeopardizing our lives and livelihoods for years to come. The unavailability of vaccines for COVID-19 has rendered rapid testing of the population instrumental in order to contain the exponential rise in cases of infection. Shortage of RT-PCR test kits and delays in obtaining test results calls for alternative methods of rapid and reliable diagnosis. In this article, we propose a novel deep learning-based solution using chest X-rays which can help in rapid triaging of COVID-19 patients. The proposed solution uses image enhancement, image segmentation, and employs a modified stacked ensemble model consisting of four CNN base-learners along with Naive Bayes as meta-learner to classify chest X-rays into three classes viz. COVID-19, pneumonia, and normal. An effective pruning strategy as introduced in the proposed framework results in increased model performance, generalizability, and decreased model complexity. We incorporate explainability in our article by using Grad-CAM visualization in order to establish trust in the medical AI system. Furthermore, we evaluate multiple state-ofthe-art GAN architectures and their ability to generate realistic synthetic samples of COVID-19 chest X-rays to deal with limited numbers of training samples. The proposed solution significantly outperforms existing methods, with 98.67% accuracy, 0.98 Kappa score, and F-1 scores of 100, 98, and 98 for COVID-19, normal, and pneumonia classes, respectively, on standard datasets. The proposed solution can be used as one element of patient evaluation along with goldstandard clinical and laboratory testing.

show abstract

Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays

Cited by 103 publications

References 24 publications

Applications of artificial intelligence in battling against covid-19: A literature review

Applications of artificial intelligence in battling against covid-19: A literature review

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays

Contact Info

Product

Resources

About