MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features

Abstract

COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR) which takes a significant amount of time to get the result. Computer based medical image analysis is more beneficial for the diagnosis of such disease as it can give better results in less time. Computed Tomography (CT) scans are used to monitor lung diseases including COVID-19. In this work, a hybrid model for COVID-19 detection has developed which has two key stages. In the first stage, we have fine-tuned the parameters of the pre-trained convolutional neural networks (CNNs) to extract some features from the COVID-19 affected lungs. As pre-trained CNNs, we have used two standard CNNs namely, GoogleNet and ResNet18. Then, we have proposed a hybrid meta-heuristic feature selection (FS) algorithm, named as Manta Ray Foraging based Golden Ratio Optimizer (MRFGRO) to select the most significant feature subset. The proposed model is implemented over three publicly available datasets, namely, COVID-CT dataset, SARS-COV-2 dataset, and MOSMED dataset, and attains state-of-the-art classification accuracies of 99.15%, 99.42% and 95.57% respectively. Obtained results confirm that the proposed approach is quite efficient when compared to the local texture descriptors used for COVID-19 detection from chest CT-scan images.

Improving Respiratory Infection Diagnosis with Deep Learning and Combinatorial Fusion: A Two-Stage Approach Using Chest X-ray Imaging

“…The quality of these CXRs can be enhanced by deploying some contrast enhancement procedures and increasing the image dataset. Hence, feature extraction from these CXRs can be executed proficiently and smoothly [ 33 ]. Our study centers on addressing the imbalance in chest X-ray (CXR) datasets and enhancing the accuracy of deep learning models.…”

A precise and timely graph‐based approach to identify SARS Covid19 infection from medical imaging data using IsoCovNet

“…Since this is primarily an issue of image classification, it is evident from the aforementioned research that predominant or inventive CNN 59 networks are often used as a classifier. In addition, CNNs [62][63][64] have several drawbacks like as overfitting if there is a class imbalance in the dataset. 12 When it comes to misclassification due to class disparity, graph 65 based neural network (GNN) 66 models are able to solve these issues.…”

Immunity-based Ebola optimization search algorithm for minimization of feature extraction with reduction in digital mammography using CNN models

“…While studies which have advanced research in this way are limited, several have limited their works only to using features extracted by CNN. For example, Jogin et al 80 extracted features to support classification using CNN, while 81 optimized the parameters of the CNN using a metaheuristic algorithm, namely Manta-Ray Foraging-Based Golden Ratio Optimizer (MRFGRO), to improve performance so that better features are extracted solely by the CNN architecture. The work in 82 experimented with using medical images of the chest, lung, brain, and liver to investigate how the fusion of extracted features would improve the accuracy of classifying abnormalities in the domain.…”