Abstract
The coronavirus is not the only virus that can cause pneumonia, but pneumonia caused by COVID-19 is more likely to be severe than other types of pneumonia. Pneumonia is a dangerous consequence that occurs when the virus enters the lung tissue of the lower respiratory tract. This may occur when the infection is absorbed. The images of the internal organs of the chest are obtained during an X-ray examination. The main objective of this study is to classify the three classes: COVID-19, normal, and pneumonia. The data set used in this study includes 6432 radiographs. Using transfer learning, image classification for deep features analyses the input image and generates results based on categories. Since deep features are the most important part of medical image categorization, a model that converts the raw image into a format that in-depth features can understand is required. In this study, several deep features are studied by using pre-trained CNN models with transfer learning such as InceptionResNetV2, InceptionV3, and NasNetMobile. Accuracy, precision, recall, sensitivity, specificity, and AUC are the few metrics used to check the model's efficiency. The Xception performs better at classifying COVID-19 with 98.26% accuracy. The InceptionResNetV2 model achieved the highest overall accuracy of 92.80% for pneumonia and normal classes. The model concludes that it correctly categorized the diseases in 92.80% of pneumonia and normal classes. The proposed technique is useful in clinical practice and helps physicians identify diseases from chest radiographs. This enables physicians to help patients promptly.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jayasingh BB, Patra MR, Mahesh DB (2016) Security issues and challenges of big data analytics and visualization. In: 2016 2nd international conference on contemporary computing and informatics (IC3I) 5(6):216–221
Umar Ibrahim A, Ozsoz M, Sale S, Al‐Turjman F, Habeeb Kolapo S (2021) Convolutional neural network for diagnosis of viral pneumonia and COVID‐19 alike & diseases. Expert Syst 13(7)
Rahim Zadeh M, Attar A (2020) A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Inf Med Unlocked 19:5
Elshennawy NM, Ibrahim DM (2020) Deep-pneumonia framework using deep learning models based on chest X-ray images. Diagnostics 10(9):649
Mporas I, Naronglerdrit P (2020) COVID-19 identification from chest X-rays. Int Conf Biomed Innov Appl (BIA) 12(4)
Sharma S, Tiwari S (2021) COVID-19 diagnosis using X-ray images and deep learning. Int Conf Artif Intell Smart Syst 23(6)
Shah S, Mehta H, Sona wane P (2020) Pneumonia detection using Convolutional neural networks. Third Int Conf Smart Syst Inventive Technol (ICSSIT) 43(12)
Sai Krishna D, Rao MM, Dhanush BS, Harshvardhan S, Prudhvi B, Rana P, Mittal U (2021) Pneumonia detection using deep learning algorithms. 2nd Int Conf Intell Eng Manag (ICIEM) 12(4)
Bhardwaj P, Kaur A (2021) A novel and efficient deep learning approach for COVID-19 detection using an X-ray imaging modality. Int J Imaging Syst Technol 31(4):1775–1791
Cengil E, Çınar A (2021) The effect of deep feature concatenation on the classification problem: an approach to COVID-19 disease detection. Int J Imaging Syst Technol 32(6):26–40
Chilakalapudi HP, Venkatesan R, Kamatham Y (2021) Parameter-based performance evaluation of deep learning models for classification of CoViD and pneumonia CT images. In: 2021 IEEE 4th international conference on computing, power and communication technologies (GUCON)
Militante SV, Dionisio NV, Sibbaluca BG (2020) Pneumonia and COVID-19 detection using Convolutional neural networks. Third Int Conf Vocat Educ Elect Eng (ICVEE) 32(5)
Heidari M, Mirniaharikandehei S, Khuzani AZ, danala G, Qiu Y, Zheng B (2020) Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with pre-processing algorithms. Int J Med Inf 144(34):104–284
EFiky A (2021) HDeep COVID-19: deep learning for COVID-19 detection from X-ray images. Int J Innov Technol Exploring Eng 11(7):1–6
Gupta P (2021) Pneumonia detection using convolutional neural networks 7(7):77–80
David Raju K, Jayasingh BB (2019) Influence of syntactic, semantic and stylistic features for sentiment identification of messages using SVM classifier. Int J Sci Technol Res 8(10):2551–2557. ISSN 2277-8616
https://www.kaggle.com/datasets/prashant268/chest xray-covid19-pneumonia
Jayasingh BB (2016) A data mining approach to inquiry-based inductive learning practice in engineering education. In: 2016 IEEE 6th international conference on advanced computing, pp 845–850
Ponnampalli S, Venkata Suryanarayana Birudukota N, Kamal A (2022) COVID-19: vaccines and therapeutics. Bioorg Med Chem Lett 75(5):128987
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jayasingh, B.B., Jyothi, T. (2023). COVID-19, Normal, and Pneumonia Classification Based on Deep Features Using Transfer Learning. In: Seetha, M., Peddoju, S.K., Pendyala, V., Chakravarthy, V.V.S.S.S. (eds) Intelligent Computing and Communication. ICICC 2022. Advances in Intelligent Systems and Computing, vol 1447. Springer, Singapore. https://doi.org/10.1007/978-981-99-1588-0_35
Download citation
DOI: https://doi.org/10.1007/978-981-99-1588-0_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1587-3
Online ISBN: 978-981-99-1588-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)