Classification of normal and abnormal fetal heart ultrasound images and identification of ventricular septal defects based on deep learning

作者：Yiru Yang, Bingzheng Wu, Huiling Wu, Xu Wu, Guorong Lyu, Peizhong Liu, Shaozheng He · 发表于：Journal of Perinatal Medicine · 年份：2023 · DOI：10.1515/jpm-2023-0041 · 被引用次数：24 · 研究领域：Fetal and Pediatric Neurological Disorders、Congenital Heart Disease Studies、Congenital heart defects research

OBJECTIVES: Congenital heart defects (CHDs) are the most common birth defects. Recently, artificial intelligence (AI) was used to assist in CHD diagnosis. No comparison has been made among the various types of algorithms that can assist in the prenatal diagnosis. METHODS: Normal and abnormal fetal ultrasound heart images, including five standard views, were collected according to the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) Practice guidelines. You Only Look Once version 5 (YOLOv5) models were trained and tested. An excellent model was screened out after comparing YOLOv5 with other classic detection methods. RESULTS: On the training set, YOLOv5n performed slightly better than the others. On the validation set, YOLOv5n attained the highest overall accuracy (90.67 %). On the CHD test set, YOLOv5n, which only needed 0.007 s to recognize each image, had the highest overall accuracy (82.93 %), and YOLOv5l achieved the best accuracy on the abnormal dataset (71.93 %). On the VSD test set, YOLOv5l had the best performance, with a 92.79 % overall accuracy rate and 92.59 % accuracy on the abnormal dataset. The YOLOv5 models achieved better performance than the Fast region-based convolutional neural network (RCNN) & ResNet50 model and the Fast RCNN & MobileNetv2 model on the CHD test set (p<0.05) and VSD test set (p<0.01). CONCLUSIONS: YOLOv5 models are able to accurately distinguish normal and abnormal fetal heart ultrasound images, especially with respe...