论文信息 - Interpretable COVID-19 Classification Leveraging Ensemble Neural Network and XAI

Interpretable COVID-19 Classification Leveraging Ensemble Neural Network and XAI

COVID-19, also known as Corona Virus Disease, was first discovered in a city of China named Wuhan in December 2019 and it has been announced as a global pandemic in the middle of 2020. According to experts, this virus may also infect the upper respiratory system, which includes the sinuses, nose, and throat, and the lower respiratory system, which includes the windpipe and lungs. The disease can infect other people via respiratory droplets and come near to the COVID-19 infected people and a low rate of contamination is stated through surfaces and objects touch. Nowadays, millions of people across the globe are suffering from this disease, causing a huge death rate. Even after taking serious precaution measures, the number of patients dealing with this disease and the death toll are still rising at a drastic rate. In this paper, we approach a fast and effective measure to detect COVID-19 using CT scan images. First, we collected data and classified using VGG16, VGG19, EfficientNetB0, ResNet50, and ResNet101. From our result;we got an accuracy rate of 85.33% from VGG16, 87.86% from VGG19, and 82.35% from ResNet101. Then we formed an ensemble model with these best three classifiers and achieved a best overall accuracy rate of 90.89% from COV19EXAI V1 and 91.82% from COV19EXAI V2. Finally, we integrated XAI in our model to achieve a better understanding of our classification. © 2021, Springer Nature Switzerland AG.

[1] Yan Bai,et al. A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis , 2020, European Respiratory Journal.

[2] Deniz Korkmaz,et al. COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images , 2020, Medical Hypotheses.

[3] M. Chung,et al. Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review , 2020, Clinical Imaging.

[4] Piyush,et al. An Explainable Artificial Intelligence based Prospective Framework for COVID-19 Risk Prediction , 2021, medRxiv.

[5] Prabira Kumar Sethy,et al. Detection of Coronavirus Disease (COVID-19) Based on Deep Features , 2020 .

[6] Muhammet Fatih Aslan,et al. CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection , 2020, Applied Soft Computing.

[7] Hossein Baharvand,et al. Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception , 2018, International Conference on Machine Vision.

[8] U. Rajendra Acharya,et al. Automated detection of COVID-19 cases using deep neural networks with X-ray images , 2020, Computers in Biology and Medicine.