SpiCoNET: A Hybrid Deep Learning Model to Diagnose COVID-19 and Pneumonia Using Chest X-Ray Images

Abstract

Using deep learning techniques on radiological lung images for detecting COVID-19 is a promising technique in shortening the diagnosis time. In this study, we propose a hybrid deep learning model, detecting the COVID-19 and Pneumonia virus using Chest X-ray images. The proposed model, named SpiCoNET, first runs multiple well-known deep learning models combined with Spiking Neural Network (SNN) in order to identify the models with higher accuracy rates. Then, SpiCoNET combines the features of the two models with the highest accuracy rates among the well-known models and hands the combined features over to a different SNN layer as an input. Finally, the features are classified by using the SEFRON learning algorithm. The proposed hybrid deep learning model takes advantage of the features of the well-known models combined with SNN providing the highest accuracy rate. Moreover, the proposed model makes use of the SEFRON learning algorithm to provide better classification. The proposed model provides an accuracy rate of 97.09% for the classification of images of the COVID-19, Pneumonia and Normal, which outperforms AlexNet (91.27%) and DenseNet201 (90.40%). The results reveal that deep learning based systems for the identification of COVID-19 and Pneumonia can help healthcare professionals control the COVID-19 pandemic in an effective manner.

Detection of Tonsillopharyngitis with Grad-Cam and Optimization-Based Model Using Oropharyngeal Images

“…Different evaluation metrics were used to measure the performance of the models used in the study to diagnose tonsillopharyngitis disease using oropharyngeal images. Accuracy, Sensitivity, Specificity, Negative Predictive Value(NPV), False Positive Rate(FPR), False Negative Rate(FNR), False Discovery Rate(FDR), F1 score, and Matthews Correlation Coefficient(MCC) are the leading performance measurement metrics used in the study [28][29][30].…”

DeepMaizeNet: A novel hybrid approach based on CBAM for implementing the doubled haploid technique

“…The entire region of the image matrix is multiplied throughout the scan. The main purpose of the applied filter is feature extraction (Başaran, 2022; Tümen, 2022). The pooling layer is a technique used to reduce the size of the feature maps obtained after the convolution operation.…”

“…To avoid these problems, pooling layers are used. After the convolution process, the pooling process is applied to the large number of parameters in the matrix obtained, and the summarization process is performed (Başaran, 2022; Cömert, 2019; Tümen, 2022). The fully connected layer, usually between the pooling and the output layer, vectorizes the multidimensional neurons in the preceding convolution layer.…”

Enhanced Pneumonia Diagnosis Using Chest X-Ray Image Features and Multilayer Perceptron and k-NN Machine Learning Algorithms

“…Chest X-ray images are routinely employed to diagnose pneumonia [2]. In clinical settings, radiologists examine these images in detail to determine the presence of pneumonia [3]. However, this diagnostic approach can be challenging when a radiologist is inexperienced or when faced with high patient density, resulting in increased workload, delayed diagnosis, and a higher error rate [4] (New Reference).…”

“…However, this diagnostic approach can be challenging when a radiologist is inexperienced or when faced with high patient density, resulting in increased workload, delayed diagnosis, and a higher error rate [4] (New Reference). The use of machine learning methods, a sub-branch of artificial intelligence, for X-ray image analysis and disease diagnosis may alleviate the workload of radiologists [3]. As a result, the accuracy and speed of pneumonia diagnosis could be enhanced by employing intelligent systems, thereby supporting the battle against pneumonia.…”