Shui-Hua Wang1, Kaihong Wu2, Tianshu Chu3, Steven L Fernandes4, Qinghua Zhou1, Yu-Dong Zhang1,3, Jian Sun2. 1. School of Informatics, University of Leicester, Leicester, LE1 7RH, UK. 2. The Affiliated Children's Hospital of Nanjing Medical University, Nanjing, China. 3. Nanjing Yirongda Institute of Intelligent Medicine and Additive Manufacturing, Nanjing, China. 4. Department of Computer Science, Design & Journalism, Creighton University, Omaha, Nebraska, USA.
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 cross-validation show that our SOSPCNN model yields a sensitivity of 92.25±2.19, a specificity of 92.75±2.49, a precision of 92.79±2.29, an accuracy of 92.50±1.18, an F1 score of 92.48±1.17, an MCC of 85.06±2.38, an FMI of 92.50±1.17, and an AUC of 0.9587. Conclusion: The SOSPCNN method performed better than three state-of-the-art TOF recognition approaches.
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 cross-validation show that our SOSPCNN model yields a sensitivity of 92.25±2.19, a specificity of 92.75±2.49, a precision of 92.79±2.29, an accuracy of 92.50±1.18, an F1 score of 92.48±1.17, an MCC of 85.06±2.38, an FMI of 92.50±1.17, and an AUC of 0.9587. Conclusion: The SOSPCNN method performed better than three state-of-the-art TOF recognition approaches.
Entities:
Keywords:
Grad-CAM; Tetralogy of Fallot; artificial intelligence; computed tomography; convolutional neural network; cross-validation; deep learning; deep neural network; machine learning; multiple-way data augmentation; stochastic pooling; structural optimization
Authors: Claudia E Coipan; Timothy J Dallman; Derek Brown; Hassan Hartman; Menno van der Voort; Redmar R van den Berg; Daniel Palm; Saara Kotila; Tom van Wijk; Eelco Franz Journal: Microb Genom Date: 2020-02-26