A fuzzy-enhanced deep learning approach for early detection of Covid-19 pneumonia from portable chest X-ray images

被引:77
作者
Ieracitano, Cosimo [1 ]
Mammone, Nadia [1 ]
Versaci, Mario [1 ]
Varone, Giuseppe [2 ]
Ali, Abder-Rahman [3 ]
Armentano, Antonio [4 ]
Calabrese, Grazia [4 ]
Ferrarelli, Anna [4 ]
Turano, Lorena [4 ]
Tebala, Carmela [4 ]
Hussain, Zain [5 ]
Sheikh, Zakariya [5 ]
Sheikh, Aziz [6 ]
Sceni, Giuseppe [4 ]
Hussain, Amir [7 ]
Morabito, Francesco Carlo [1 ]
机构
[1] Univ Meditenanea Reggio Calabria, DICEAM, Via Graziella, I-89124 Reggio Di Calabria, Italy
[2] Univ G dAnnunzio Chieti & Pescara, Dept Neurosci & Imaging, Pescara, Italy
[3] Univ Stirling, Fac Nat Sci, Dept Comp Sci & Math, Stirling, Scotland
[4] Grande Osped Metropolitano GOM Bianchi Melacrino, Adv Diagnost & Therapeut Technol Dept, Reggio Di Calabria, RC, Italy
[5] Univ Edinburgh, Coll Med & Vet Med, Edinburgh Med Sch, Edinburgh, Midlothian, Scotland
[6] Univ Edinburgh, Edinburgh Med Sch, Usher Inst, Edinburgh, Midlothian, Scotland
[7] Edinburgh Napier Univ, Sch Comp, Edinburgh, Midlothian, Scotland
基金
英国工程与自然科学研究理事会;
关键词
Chest X-ray; Convolutional Neural Network; Covid-19; explainable Artificial Intelligence; Fuzzy logic; Portable systems; FEATURES;
D O I
10.1016/j.neucom.2022.01.055
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The Covid-19 pandemic is the defining global health crisis of our time. Chest X-Rays (CXR) have been an important imaging modality for assisting in the diagnosis and management of hospitalised Covid-19 patients. However, their interpretation is time intensive for radiologists. Accurate computer aided systems can facilitate early diagnosis of Covid-19 and effective triaging. In this paper, we propose a fuzzy logic based deep learning (DL) approach to differentiate between CXR images of patients with Covid19 pneumonia and with interstitial pneumonias not related to Covid-19. The developed model here, referred to as CovNNet, is used to extract some relevant features from CXR images, combined with fuzzy images generated by a fuzzy edge detection algorithm. Experimental results show that using a combination of CXR and fuzzy features, within a deep learning approach by developing a deep network inputed to a Multilayer Perceptron (MLP), results in a higher classification performance (accuracy rate up to 81%), compared to benchmark deep learning approaches. The approach has been validated through additional datasets which are continously generated due to the spread of the virus and would help triage patients in acute settings. A permutation analysis is carried out, and a simple occlusion methodology for explaining decisions is also proposed. The proposed pipeline can be easily embedded into present clinical decision support systems. (c) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页码:202 / 215
页数:14
相关论文
共 54 条
[11]   Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms [J].
Heidari, Morteza ;
Mirniaharikandehei, Seyedehnafiseh ;
Khuzani, Abolfazl Zargari ;
Danala, Gopichandh ;
Qiu, Yuchen ;
Zheng, Bin .
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2020, 144
[12]  
Holzinger A, 2014, BIOMEDICAL INFORMATI
[13]   Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI [J].
Holzinger, Andreas ;
Malle, Bernd ;
Saranti, Anna ;
Pfeifer, Bastian .
INFORMATION FUSION, 2021, 71 :28-37
[14]   Causability and explainability of artificial intelligence in medicine [J].
Holzinger, Andreas ;
Langs, Georg ;
Denk, Helmut ;
Zatloukal, Kurt ;
Mueller, Heimo .
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2019, 9 (04)
[15]   Interactive machine learning: experimental evidence for the human in the algorithmic loop: A case study on Ant Colony Optimization [J].
Holzinger, Andreas ;
Plass, Markus ;
Kickmeier-Rust, Michael ;
Holzinger, Katharina ;
Crisan, Gloria Cerasela ;
Pintea, Camelia-M. ;
Palade, Vasile .
APPLIED INTELLIGENCE, 2019, 49 (07) :2401-2414
[17]   CoroDet: A deep learning based classification for COVID-19 detection using chest X-ray images [J].
Hussain, Emtiaz ;
Hasan, Mahmudul ;
Rahman, Md Anisur ;
Lee, Ickjai ;
Tamanna, Tasmi ;
Parvez, Mohammad Zavid .
CHAOS SOLITONS & FRACTALS, 2021, 142
[18]   A Hybrid-Domain Deep Learning-Based BCI For Discriminating Hand Motion Planning From EEG Sources [J].
Ieracitano, Cosimo ;
Morabito, Francesco Carlo ;
Hussain, Amir ;
Mammone, Nadia .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2021, 31 (09)
[19]   A novel multi-modal machine learning based approach for automatic classification of EEG recordings in dementia [J].
Ieracitano, Cosimo ;
Mammone, Nadia ;
Hussain, Amir ;
Morabito, Francesco C. .
NEURAL NETWORKS, 2020, 123 :176-190
[20]  
Islam Md Zabirul, 2020, Inform Med Unlocked, V20, P100412, DOI 10.1016/j.imu.2020.100412