Optimal hyperparameter selection of deep learning models for COVID-19 chest X-ray classification

• Published in: Intelligence-based medicine 2021, Vol.5, p.100034-100034, Article 100034
• Main Authors: Adedigba, Adeyinka P., Adeshina, Steve A., Aina, Oluwatomisin E., Aibinu, Abiodun M.
• Format: Article
• Language: English
• Subjects: Chest X-ray; Computer-aided diagnosis; COVID-19; Cyclical learning rate; Deep convolutional neural network (CNN); Discriminative fine-tuning; Hyperparameter optimisation; Memory and computation efficient; Mixed-precision training; Overfitting
• ISSN: 2666-5212; 2666-5212
• DOI: 10.1016/j.ibmed.2021.100034

The first and most critical response to curbing the spread of the novel coronavirus disease (COVID-19) is to deploy effective techniques to test potentially infected patients, isolate them and commence immediate treatment. However, several test kits currently in use are slow and in a shortage of supply. This paper presents techniques for diagnosing COVID-19 from chest X-ray (CXR) and address problems associated with training deep models with less voluminous datasets and class imbalance as obtained in most available CXR datasets on COVID-19. We used the discriminative fine-tuning approach, which dynamically assigns different learning rates to each layer of the network. The learning rate is set using the cyclical learning rate policy that changes per iteration. This flexibility ensured rapid convergence and avoided being stuck in saddle point plateau. In addition, we addressed the high computational demand of deep models by implementing our algorithm using the memory- and computational-efficient mixed-precision training. Despite the availability of scanty datasets, our model achieved high performance and generalisation. A Validation accuracy of 96.83%, sensitivity and specificity of 96.26% and 95.54% were obtained, respectively. When tested on an entirely new dataset, the model achieves 97% accuracy without further training. Lastly, we presented a visual interpretation of the model’s output to prove that the model can aid radiologists in rapidly screening for the symptoms of COVID-19. •The most critical response to curbing the spread of the novel COVID19 and its pandemic is an effective screening kit.•Computer-aided Diagnosis can provide a speedy and effective screen in curbing the coronavirus pandemic.•Discriminative fine-tuning and mixed-precision training are used to reduce computational cost and ensure rapid convergence.•The training time and accuracy were improved and a validation and test accuracy of 96.83% and 97% respectively were achieved.•The model’s output is accompanied by a visual clue to aid the radiologist in diagnosing the coronavirus.