SOSPCNN: Structurally Optimized Stochastic Pooling Convolutional Neural Network for Tetralogy of Fallot Recognition

Abstract

Aim. This study proposes a new artificial intelligence model based on cardiovascular computed tomography for more efficient and precise recognition of Tetralogy of Fallot (TOF). Methods. Our model is a structurally optimized stochastic pooling convolutional neural network (SOSPCNN), which combines stochastic pooling, structural optimization, and convolutional neural network. In addition, multiple-way data augmentation is used to overcome overfitting. Grad-CAM is employed to provide explainability to the proposed SOSPCNN model. Meanwhile, both desktop and web apps are developed based on this SOSPCNN model. Results. The results on ten runs of 10-fold crossvalidation show that our SOSPCNN model yields a sensitivity of $92.25\pm 2.19$ , a specificity of $92.75\pm 2.49$ , a precision of $92.79\pm 2.29$ , an accuracy of $92.50\pm 1.18$ , an F1 score of $92.48\pm 1.17$ , an MCC of $85.06\pm 2.38$ , an FMI of $92.50\pm 1.17$ , and an AUC of 0.9587. Conclusion. The SOSPCNN method performed better than three state-of-the-art TOF recognition approaches.