A deep transfer learning based model for automatic detection of COVID-19 from chest X-ray

Abstract

Deep learning in medical imaging has revolutionized the way we interpret medical data, as high computational devices' capabilities are far more than their creators. With the pandemic causing havoc for the second straight year, the findings in our paper will allow researchers worldwide to use and create state-of-the-art models to detect affected persons before it reaches the R number. The paper proposes an automated diagnostic tool using the deep learning models on chest x-rays as an input to reach a point where we surpass this pandemic (COVID-19 disease). A deep transfer learning-based model for automatic detection of COVID-19 from chest x-rays using the Inception-V3 model is proposed, in which we added flattening, node dropping, normalization, and dense layer. The proposed architecture is compared with existing state-of-the-art ImageNet models. The model's efficacy is tested on three different COVID-19 radiography datasets with three classes: COVID, normal, and viral pneumonia. The proposed model has reached an accuracy of 97.7%, 84.95%, and 97.03% on the mentioned datasets, respectively. The proposed work introduces the deep neural networks applied to medical images to analyze image enhancement techniques and emphasize the field's clinical aspects.

A Novel CovidDetNet Deep Learning Model for Effective COVID-19 Infection Detection Using Chest Radiograph Images

“…This experiment aims to recover the performance of the proposed CovidDetNet framework in identifying and classifying COVID-19 from chest radiograph images compared to existing state-of-the-art deep learning approaches in the literature. We compared the proposed classification model performance to various approaches [43,44,68,69]. Prateek et al [68] proposed an automated diagnostic method for COVID-19 detection and classification using the DL model on chest radiograph images.…”

“…We compared the proposed classification model performance to various approaches [43,44,68,69]. Prateek et al [68] proposed an automated diagnostic method for COVID-19 detection and classification using the DL model on chest radiograph images. The Inception-V3 model, with node dropping, flattening, dense layer, and normalization, was used to automatically present a transfer learning-based algorithm for detecting COVID-19 from chest radiographs.…”

SEL-COVIDNET: An intelligent application for the diagnosis of COVID-19 from chest X-rays and CT-scans

“…Chhikara et al. [35] built a deep transfer learning-based model using Inception-V3-Net to detect COVID-19 from chest X-rays and CT scans. Apostolopoulos et al.…”

COVID-19 Detection on Chest X-Ray Images: A comparison of CNN architectures and ensembles

“…They also made an ensemble of the four best models (ResNet50V2, Xception, MobileNet, and DenseNet121) with the final output obtained by majority voting, raising the accuracy to 99.26%. Chhikara et al (2021) proposed a InceptionV3 based-model and applied it to three different datasets with 11, 244, 8, 246, and 14, 486 CXR images, respectively. The model has reached an accuracy of 97.7%, 84.95%, and 97.03% on the mentioned datasets, respectively.…”

“…Many studies concerning the application of CNNs to COVID-19 diagnostic on CXR images were published since the last year (Khan et al, 2021;Nigam et al, 2021;Ismael and S ¸engür, 2021;Abbas et al, 2021;Hira et al, 2021;Alawad et al, 2021;Narin et al, 2021;Monshi et al, 2021;Heidari et al, 2020;Jia et al, 2021;Karthik et al, 2021;Mostafiz et al, 2020;Mohammad Shorfuzzaman, 2020;Chhikara et al, 2021). However, most of them used relatively small and more homogeneous datasets.…”