Open Access Open Access  Restricted Access Subscription Access

AI-POWERED COVID-19 DIAGNOSIS: A SURVEY ON DEEP LEARNING AND CHEST X-RAY IMAGING

Raghu Ram Chowdary Velevela

Abstract


COVID-19 pandemic is a global health crisis that has already reached millions of people and led to the deaths of hundreds of thousands of people.The COVID-19 pandemic is causing a major outbreak in more than 150 countries around the world, having a severe impact on the health and life of many people globally. The daily life of human beings, their health, and the economy of a country are affected due to this deadly viral disease.Detecting this disease from radiography and radiology images is perhaps one of the fastest ways to diagnose the patients.Clinical studies of COVID-19 patients are mostly infected from a lung infection. Chest X-ray (i.e., radiography) and chest CT are a more effective imaging technique for diagnosing lunge related problems. ChestX-rayisalowercostprocessing comparisontochestCT (Computerized Tomography). Deep learning techniques are useful to study a large amount of chest X-ray images that can critically impact on Covid-19. The present study is targeted at constructing effective deep learning models, trained with chest X-ray images, for quick screening of COVID-19 patients. We used publicly available PA (Posteroanterior) chest X-ray pictures of COVID-19 affected individuals as well as healthy people. After cleaning up the images and applying data augmentation; we have used deep learning-based CNN models and compared their performance. Survey on some of the CNN models such as Inception NetV3, Xception, and ResNeXt models The Xception model gives the highest accuracy (i.e., 97.97%) for detecting Chest X-rays images as compared to other models.

Full Text:

PDF

References


World Health Organization, COVID-19 Health Topic –https://www.who.int/healthtopics/coronavirus

. WebMD, Coronavirus and COVID-19: What You Should know https://www.webmd.com/lung/coronavirus

. NarinA, Kaya C, Pamuk Z (2020) Automatic detection of corona virus disease (covid-19) using x-ray images and deep convolutional neural networks. arXiv preprint arXiv:2003.10849

. AlexKrizhevsky, IlyaSutskever, Geoffrey E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks" -

https://papers.nips.cc/paper/4824imagenet-classification-with-deepconvolutional-neural-networks.pdf

. Cosmin CERNAZANU-GLAVAN, Stefan HOLBAN, "Segmentation of Bone Structure in X-ray Images using Convolutional Neural Network," February 2013 - https://www.researchgate.net/publication/269978717_Segmentation_of_Bone_Structure_in_Xray_Images_using_Convolutional_Neural_Network

. Karl Weiss, TaghiKhoshgoftaar, DingDing Wang, "A survey of transfer learning,"December2016https://www.researchgate.net/publication/303600638_A_survey_of_transfer_learning

. X. Wu “Deep learning-based multi-view fusion model for screening 2019 novel coronavirus pneumonia: A multicentre study,” Eur. J. Radiol., vol. 128, p. 109041, Jul. 2020.

. X. Xu, X. Jiang, C. Ma et al., “A deep learning system to screen novelcoronavirus disease 2019 pneumonia,” Engineering,2020.

View at: Publisher Site | Google Scholar.

. Jin “Development and Evaluation of an AI System for COVID-19 Diagnosis,”2020. https://www.medrxiv.org/content/10.1101/2020.03.20.20039834v3

A. Abbas, M. M. Abdelsamea, and M. M. Gaber, “Classification of covid-19 in chest x-ray images using detrac deep convolutional neural network,” arXiv preprint arXiv:2003.13815, 2020.


Refbacks

  • There are currently no refbacks.