AUTHOR=Zhang Guangming , Mao Yujie , Li Mingliang , Peng Li , Ling Yunfei , Zhou Xiaobo 

TITLE=The Optimal Tetralogy of Fallot Repair Using Generative Adversarial Networks

JOURNAL=Frontiers in Physiology

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2021.613330

DOI=10.3389/fphys.2021.613330

ISSN=1664-042X

ABSTRACT=Background: Tetralogy of Fallot (TOF) is a type of congenital cardiac disease with pulmonary artery stenosis being the most common defect. Repair surgery needs an appropriate patch to enlarge the narrowed artery from the right ventricular (RV) to the pulmonary artery (PA). 
Methods: In this work, we proposed a Generative Adversarial Networks (GANs) based method to optimize the patch size, shape and location. Firstly, we built the 3D pulmonary artery of patients by segmentation from cardiac CT angiography. After that, the area of pulmonic stenosis is detected, and the pulmonary artery was resliced into two groups: normal and stenosis. Then a GAN was trained based on these resliced images. Finally, an optimal prediction model was utilized to repair the pulmonary artery with patch augmentation in the new patient. 
Results: The fivefold cross-validation (CV) was performed for optimal patch prediction based on GANs in the repair of TOF and the CV accuracy was 93.33%, followed by the clinical outcome. This showed that the GAN model has a significant advantage in finding the best balance point of patch optimization. 
Conclusions: This approach has the potential to reduce the intraoperative misjudgment rate, thereby providing a detailed surgical plan in patients with TOF.