Artificial intelligence diagnosis of patent foramen ovale in contrast transthoracic echocardiography
Yuanyuan Sheng,
Lixin Chen,
Mengjie Gu,
Shuyu Luo,
Yuxiang Huang,
Xiaoxuan Lin,
Xiaohua Liu,
Qian Liu,
Xiaofang Zhong,
Guijuan Peng,
Jian Li,
Bobo Shi,
Lin Wang,
Jinfeng Xu,
Zhaohui Ning,
Yingying Liu
Affiliations
Yuanyuan Sheng
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Lixin Chen
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Mengjie Gu
School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China
Shuyu Luo
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Yuxiang Huang
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Xiaoxuan Lin
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Xiaohua Liu
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Qian Liu
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Xiaofang Zhong
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Guijuan Peng
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Jian Li
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Bobo Shi
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China
Lin Wang
School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China
Jinfeng Xu
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China; Corresponding author
Zhaohui Ning
The First Afffiliated Hospital, Henan University of Science and Technology, Luoyang 471003, China; Corresponding author
Yingying Liu
Shenzhen Medical Ultrasound Engineering Center, Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, China; Corresponding author
Summary: Artificial intelligence (AI) is rarely directly used in patent foramen ovale (PFO) diagnosis. In this study, an AI model was developed to detect the presence of PFO automatically in both contrast transthoracic echocardiography (cTTE) images and videos. The whole intelligent diagnosis neural network framework consists of two functional modules of image segmentation (Unet, n = 1866) and image classification (ResNet 101, n = 9152). Finally, another test databases, including 20 cTTE videos (4609 cTTE images), was used to compare the RLS classification model accuracy between AI model and different levels of physicians. The Dice similarity coefficient of left chamber segmentation model of cTTE images was 91.41%, the accuracy of PFO-RLS classification model of cTTE images was 83.55%, the accuracy of PFO-RLS classification model of cTTE videos was 90%. Besides, the AI diagnosis time was significantly shorter than doctors (at only 1.3 s).
