Automatic detection of COVID-19 from chest CT scan and chest X-Rays images using deep learning, transfer learning and stacking

• Published in: Applied intelligence (Dordrecht, Netherlands) Netherlands), 2022-01, Vol.52 (2), p.2243-2259
• Main Authors: Jangam, Ebenezer, Barreto, Aaron Antonio Dias, Annavarapu, Chandra Sekhara Rao
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Artificial Intelligence Applications for COVID-19; Chest; Computed tomography; Computer Science; Computer vision; Control; Coronaviruses; COVID-19; Datasets; Deep learning; Detection; Diagnosis; Machines; Manufacturing; Mechanical Engineering; Medical imaging; Prediction; Processes; Recall; Viral diseases; X-rays
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-021-02393-4

One of the promising methods for early detection of Coronavirus Disease 2019 (COVID-19) among symptomatic patients is to analyze chest Computed Tomography (CT) scans or chest x-rays images of individuals using Deep Learning (DL) techniques. This paper proposes a novel stacked ensemble to detect COVID-19 either from chest CT scans or chest x-ray images of an individual. The proposed model is a stacked ensemble of heterogenous pre-trained computer vision models. Four pre-trained DL models were considered: Visual Geometry Group (VGG 19), Residual Network (ResNet 101), Densely Connected Convolutional Networks (DenseNet 169) and Wide Residual Network (WideResNet 50 2). From each pre-trained model, the potential candidates for base classifiers were obtained by varying the number of additional fully-connected layers. After an exhaustive search, three best-performing diverse models were selected to design a weighted average-based heterogeneous stacked ensemble. Five different chest CT scans and chest x-ray images were used to train and evaluate the proposed model. The performance of the proposed model was compared with two other ensemble models, baseline pre-trained computer vision models and existing models for COVID-19 detection. The proposed model achieved uniformly good performance on five different datasets, consisting of chest CT scans and chest x-rays images. In relevance to COVID-19, as the recall is more important than precision, the trade-offs between recall and precision at different thresholds were explored. Recommended threshold values which yielded a high recall and accuracy were obtained for each dataset.