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

Abstract

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.

Fusion of Moment Invariant Method and Deep Learning Algorithm for COVID-19 Classification

“…All the models reported in Table 6 uses the SARS-CoV-2 dataset for their experiments. Based on the findings, VGG16 + MI gives a higher accuracy value than VGG19 + DenseNet169 [46], COVID-Net [47], and DenseNet121 [48]. Furthermore, VGG16 + MI also has a higher sensitivity rate than the COVID-Net model by Wang et al [47].…”

Emerging technologies for the management of COVID19: A review

“…Elakkiya, Pandi Vijayakumar and Marimuthu Karuppiah” [24] “Automatic detection of COVID-19 from chest CT scan and chest X-Rays images using deep learning, transfer learning and stacking” [46] “Ebenezer Jangam, Aaron Antonio Dias Barreto and Chandra Sekhara Rao Annavarapu” [44] “Rapid COVID‑19 diagnosis using ensemble deep transfer learning models from chest radiographic images” [42] “Neha Gianchandani, Aayush Jaiswal, Dilbag Singh, Vijay Kumar and Manjit Kaur” [41] “A Study of the Neutrosophic Set Significance on Deep Transfer Learning Models: an Experimental Case on a Limited COVID‑19 Chest X‑ray Dataset” [47] “Nour Eldeen M. Khalifa, FlorentinSmarandache, Gunasekaran Manogaran and Mohamed Loey” [45] “Novel deep transfer learning model for COVID‑19 patient detection using X‑ray chest images” [48] “N. Kumar, M. Gupta, D. Gupta and S. Tiwari” [46] “Res-CovNet: an internet of medical health things driven COVID-19 framework using transfer learning” [65] “Mangena VenuMadhavan, Aditya Khamparia, Deepak Gupta, Sagar Pande, Prayag Tiwari and M. Shamim Hossain” [62] “Transfer learning–based ensemble support vector machine model for automated COVID-19 detection using lung computerized tomography scan data” [66] “Mukul Sing,Shrey Bansal1, Sakshi Ahuja2, Rahul Kumar Dubey3,Bijaya Ketan Panigrahi2,Nilanjan Dey4” [63] Random Forest, Support Vector Machine (SVM) and KNN “Predicting the Probability of Covid-19 Recovered in South Asian Countries Based on Healthy Diet Pattern Using a Machine Learning Approach” [67] Md. ShowrovHossenand Dip Karmoker [64] “PRELIMINARY DIAGNOSIS OF COVID-19 BASED ON COUGH SOUNDS USING MACHINELEARNING ALGORITHMS” [68] Arup Anupam Deptt.…”

“…Transfer learning is a deep learning technique that employs a deep convolutional neural network that has been trained to perform one task to perform another. The original model's parameters are fine-tuned for the second task [46] .Transfer learning (TL) has simplified the process of rapidly retraining neural networks on selected datasets with high accuracy [39] . DTLs such as “VGG, ResNet, and DenseNets” are now becoming an essential process in image/video detection and diagnosis for the time being.…”

Outbreak COVID-19 in Medical Image Processing Using Deep Learning: A State-of-the-Art Review

“…Jangam et al [25] proposed new heterogeneous stacked ensemble models such as VGG, ResNet101, DenseNet169, and Wide ResNet50-2. From every CNN pre-trained model, the additional elements of base classifiers were obtained by changing the fully connected layers.…”