PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN

Abstract

Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65% ± 1.86%, a specificity of 94.32% ± 2.07%, a precision of 94.30% ± 2.04%, an accuracy of 93.99% ± 1.78%, an F1-score of 93.97% ± 1.78%, Matthews Correlation Coefficient of 87.99% ± 3.56%, and Fowlkes-Mallows Index of 93.97% ± 1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective.

An automatic gastric polyp detection technique using deep learning

“…It can barely exceed 76.07%, implying that one in every five gastric polyps was missed. In 2022 and 2023, the study uses wavelet entropy for feature extraction 33 and PSO‐guided self‐tuning CNN technique 34 for COVID‐19 diagnoses.…”

Feature selection and classification using bio‐inspired algorithms for the diagnosis of pulmonary emphysema subtypes

“…The authors claimed that employing an optimization approach to tune the model's hyperparameters is quicker and more efficient than using conventional techniques. 24 Aljarah et al proposed an approach for training the multilayer perceptron (MLP) based on whale optimization algorithm (WOA) to optimize the connection weights and biases in a NN. MLP was trained through WOA with one hidden layer.…”

Automatic diagnosis of ureteral stone and degree of hydronephrosis with proposed convolutional neural network, RelieF, and gradient‐weighted class activation mapping based deep hybrid model

“…Deep architectures have been frequently used in the biomedical field, especially in recent years. [3][4][5][6] In addition, another important advantage is to provide pre-diagnosis to sick people in underdeveloped regions where there are no specialists or the number of specialists is insufficient, thanks to these technologies.…”

“…The most important advantages are that it allows the early diagnosis of the disease, increasing the chance of treatment of the patient, as well as getting rid of the treatment costs, which are highly likely to occur in the advanced stages of the disease. Deep architectures have been frequently used in the biomedical field, especially in recent years 3–6 . In addition, another important advantage is to provide pre‐diagnosis to sick people in underdeveloped regions where there are no specialists or the number of specialists is insufficient, thanks to these technologies.…”