A Seven-Layer Convolutional Neural Network for Chest CT-Based COVID-19 Diagnosis Using Stochastic Pooling

• Published in: IEEE sensors journal 2022-09, Vol.22 (18), p.17573-17582
• Main Authors: Zhang, Yudong, Satapathy, Suresh Chandra, Zhu, Li-Yao, Gorriz, Juan Manuel, Wang, Shuihua
• Format: Article
• Language: English
• Subjects: Agriculture; Algorithms; Artificial neural networks; Computed tomography; Convolutional neural network; Convolutional neural networks; COVID-19; Data augmentation; deep learning; Diagnosis; Gray-scale; Sensors; stochastic pooling; Stochastic processes; Training
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2020.3025855

(Aim) COVID-19 pandemic causes numerous death tolls till now. Chest CT is an effective imaging sensor system to make accurate diagnosis. (Method) This article proposed a novel seven layer convolutional neural network based smart diagnosis model for COVID-19 diagnosis (7L-CNN-CD). We proposed a 14-way data augmentation to enhance the training set, and introduced stochastic pooling to replace traditional pooling methods. (Results) The 10 runs of 10-fold cross validation experiment show that our 7L-CNN-CD approach achieves a sensitivity of 94.44±0.73, a specificity of 93.63±1.60, and an accuracy of 94.03±0.80. (Conclusion) Our proposed 7L-CNN-CD is effective in diagnosing COVID-19 in chest CT images. It gives better performance than several state-of-the-art algorithms. The data augmentation and stochastic pooling methods are proven to be effective.