COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

Hybridization of particle swarm optimization algorithm with neural network for COVID‐19 using computerized tomography scan and clinical parameters

“…We compared the proposed PSO-ANN with the previous methods to assess its superiority based on the patients' numbers or images used for a database that feeds into the models, modality, adopted models or learning techniques and performance metrics in terms of accuracy (Table 6). Our research differs from other recent studies [25][26][27][28][29][30][31][32][33][34][35][36] in two main ways. First, we used several physiological and clinical parameters along with CT scan images to improve COVID-19 diagnostic accuracy over previous studies that only used CT or X-ray image datasets.…”

“…The proposed approach achieved a diagnostic accuracy of 85.5% for COVID-19. Gaur et al [30] Several studies [31][32][33][34][35] have used a multiscale deep CNN model for COVID detection based on X-ray images. Muralidharan et al [31] proposed an approach for detecting COVID-19 from chest X-ray images.…”

“…Several studies [31–35] have used a multiscale deep CNN model for COVID detection based on X‐ray images. Muralidharan et al.…”

Stratification of tumour cell radiation response and metabolic signatures visualization with Raman spectroscopy and explainable convolutional neural network

“…To address this limitation, we use the individual gradients as the importance weights w ik c for every single spatial location i in the feature maps and calculate the Grad-CAM variable/wavenumber classification importance over the input spectrum by performing an element-wise multiplication of the feature map activations with their corresponding weights followed by a summation of the weighted maps, as previously proposed by other authors. 20,39,[43][44][45]47,48 The output sum is upsampled to the input size via interpolation 29 to obtain an importance value for each wavenumber in the spectrum. 4.…”

Cluster analysis and forecasting of viruses incidence growth curves: Application to SARS-CoV-2

“…Clustering techniques were also applied in Mittal, Pandey, Pal, and Tripathi (2021) , in order to improve the results of supervised techniques caused by the limited size of chest X-ray images (CXR), chest computed tomography (CT) scan, and lung ultrasound data. CXR images are also used in Liu, Cai, Tang, Zhang, and Wang (2022) , where class residual attention networks are proposed in combination with an image preprocessing step, obtaining good accuracy in the diagnosis of positive cases. Furthermore, it is worth of mention that chest CT image features have been very useful in the creation of ML models to support the diagnosis of COVID-19 cases ( Li, 2020 , Ufuk and Savaş, 2020 ).…”