TY - JOUR
T1 - COVID-19 lung infection detection using deep learning with transfer learning and ResNet101 features extraction and selection
AU - Khan, Raja Nadir
AU - Hussain, Lal
AU - Alluhaidan, Ala Saleh
AU - Majid, Abdul
AU - Lone, Kashif J.
AU - Verdiyev, Rufat
AU - Al-Wesabi, Fahd N.
AU - Duong, Tim Q.
N1 - Publisher Copyright:
© 2022 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2022
Y1 - 2022
N2 - Deep learning artificial intelligent (AI) methods have potential to help improve diagnostic efficiency and accuracy for reading portable CXRs. Public datasets taken from SIRM and Kaggle repositories comprised of COVID-19 (N = 130, 975), normal (N = 138, 1525), bacterial pneumonia (N = 145, 2521), non-COVID-19 viral pneumonia (N = 145, 1342) respectively CXRs were analyzed. On the first dataset, we first extracted 2048 features from last pooling layer of Residual Network 101 (ResNet101) which were fed into selected classifiers. The three-class (Covid-19, normal, viral) yielded highest accuracy of 97.30% using support vector machine linear (SVM-L). This accuracy was further improved to 98.20% by applying the chi-square feature selection method. The four-class using original ResNet101 features yielded highest accuracy of 85.06% which was further improved to 87.01% using chi-square and recursive feature elimination (RFE) feature selection methods. Moreover, using the second dataset, we utilized and optimized robust deep learning methods including densenet201, inception-V3, ResNet101, GoogleNet and VGG-19 using transfer learning approach. The densenet201 yielded the highest performance for three-class (Covid-19, normal, pneumonia) to detect Covid-19 with accuracy (99.92%).The results revealed that feature selection methods improved multiclass classification as dynamic deep feature may contains redundant information. Thus, proposed methods have the potential to improve diagnostic efficiency and accuracy for portable CXRs.
AB - Deep learning artificial intelligent (AI) methods have potential to help improve diagnostic efficiency and accuracy for reading portable CXRs. Public datasets taken from SIRM and Kaggle repositories comprised of COVID-19 (N = 130, 975), normal (N = 138, 1525), bacterial pneumonia (N = 145, 2521), non-COVID-19 viral pneumonia (N = 145, 1342) respectively CXRs were analyzed. On the first dataset, we first extracted 2048 features from last pooling layer of Residual Network 101 (ResNet101) which were fed into selected classifiers. The three-class (Covid-19, normal, viral) yielded highest accuracy of 97.30% using support vector machine linear (SVM-L). This accuracy was further improved to 98.20% by applying the chi-square feature selection method. The four-class using original ResNet101 features yielded highest accuracy of 85.06% which was further improved to 87.01% using chi-square and recursive feature elimination (RFE) feature selection methods. Moreover, using the second dataset, we utilized and optimized robust deep learning methods including densenet201, inception-V3, ResNet101, GoogleNet and VGG-19 using transfer learning approach. The densenet201 yielded the highest performance for three-class (Covid-19, normal, pneumonia) to detect Covid-19 with accuracy (99.92%).The results revealed that feature selection methods improved multiclass classification as dynamic deep feature may contains redundant information. Thus, proposed methods have the potential to improve diagnostic efficiency and accuracy for portable CXRs.
KW - COVID-19
KW - Convolutional neural network (CNN)
KW - chi-square
KW - deep learning (DL)
KW - fully connected (FC) layer
KW - lung infection
KW - support vector machine (SVM)
UR - http://www.scopus.com/inward/record.url?scp=85133183831&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85133183831&partnerID=8YFLogxK
U2 - 10.1080/17455030.2022.2091807
DO - 10.1080/17455030.2022.2091807
M3 - Article
AN - SCOPUS:85133183831
SN - 1745-5030
JO - Waves in Random and Complex Media
JF - Waves in Random and Complex Media
ER -