A Novel Method for Multivariant Pneumonia Classification Based on Hybrid CNN-PCA Based Feature Extraction Using Extreme Learning Machine With CXR Images

被引:25
作者
Nahiduzzaman, Md [1 ]
Goni, Md Omaer Faruq [1 ]
Anower, Md Shamim [2 ]
Islam, Md Robiul [1 ]
Ahsan, Mominul [3 ]
Haider, Julfikar [4 ]
Gurusamy, Saravanakumar [5 ]
Hassan, Rakibul [1 ]
Islam, Md Rakibul [1 ]
机构
[1] Rajshahi Univ Engn & Technol, Dept Elect & Comp Engn, Rajshahi 6204, Bangladesh
[2] Rajshahi Univ Engn & Technol, Dept Elect & Elect Engn, Rajshahi 6204, Bangladesh
[3] Univ York, Dept Comp Sci, York YO10 5GH, N Yorkshire, England
[4] Manchester Metropolitan Univ, Dept Engn, Manchester M1 5GD, Lancs, England
[5] Ethiopian Tech Univ, Dept Elect & Elect Technol, Addis Ababa 190310, Ethiopia
关键词
Pulmonary diseases; Feature extraction; Convolutional neural networks; Biomedical imaging; X-ray imaging; COVID-19; Extreme learning machines; Chest X-Ray (CXR); convolutional neural network (CNN); contrast limited adaptive histogram equalization (CLAHE); extreme learning machine (ELM); feature extraction; principal component analysis (PCA); pneumonia;
D O I
10.1109/ACCESS.2021.3123782
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this era of COVID19, proper diagnosis and treatment of pneumonia are very important. Chest X-Ray (CXR) image analysis plays a vital role in the reliable diagnosis of pneumonia. An experienced radiologist is required for this. However, even for an experienced radiographer, it is quite challenging and time-consuming to diagnose accurately due to the fuzziness of CXR images. Also, identification can be erroneous due to the involvement of human judgement. Hence, an authentic and automated system can play an important role here. In this era of cutting-edge technology, deep learning (DL) is highly used in every sector. There are several existing methods to diagnose pneumonia but they have accuracy problems. In this study, an automatic pneumonia detection system has been proposed by applying the extreme learning machine (ELM) on the Kaggle CXR images (Pneumonia). Three models have been studied: classification using extreme learning machine (ELM), ELM with a hybrid convolutional neural network-principal component analysis (CNN-PCA) based feature extraction, and CNN-PCA-ELM with the CXR images which are contrast-enhanced by contrast limited adaptive histogram equalization (CLAHE). Among these three proposed methods, the final model provides an optimistic result. It achieves the recall score of 98% and accuracy score of 98.32% for multiclass pneumonia classification. On the other hand, a binary classification achieves 100% recall and 99.83% accuracy. The proposed method also outperforms the existing methods. The outcome has been compared using several benchmarks that include accuracy, precision, recall, etc.
引用
收藏
页码:147512 / 147526
页数:15
相关论文
共 49 条
[1]  
Abin D., 2021, 2021 2nd International Conference for Emerging Technology (INCET), P1
[2]  
Abosamra G., 2019, INT J COMPUT APPL, V181, P8887
[4]  
[Anonymous], 2020, D TRIBUNE 11
[5]  
[Anonymous], 2015, Committing to Child Survival: A Promise Renewed: Progress Report 2015
[6]  
Aschwanden C, 2015, NOT EVEN SCI CAN EAS
[7]  
Asuncion L. V. R., 2018, I C HUMANOID NANOTEC, P1
[8]   Diagnosis of Pneumonia from Chest X-Ray Images using Deep Learning [J].
Ayan, Enes ;
Unver, Halil Murat .
2019 SCIENTIFIC MEETING ON ELECTRICAL-ELECTRONICS & BIOMEDICAL ENGINEERING AND COMPUTER SCIENCE (EBBT), 2019,
[9]  
Chen TY, 2004, QSIC 2004: PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON QUALITY SOFTWARE, P146
[10]   A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images [J].
Chouhan, Vikash ;
Singh, Sanjay Kumar ;
Khamparia, Aditya ;
Gupta, Deepak ;
Tiwari, Prayag ;
Moreira, Catarina ;
Damasevicius, Robertas ;
de Albuquerque, Victor Hugo C. .
APPLIED SCIENCES-BASEL, 2020, 10 (02)