Cho, HC, Sun, S, Min Hyun, C, Kwon, JY, Kim, B, Park, Y, et al. Int J Comput Assist Radiol Surg 2020 15:1407–15. A preliminary study to quantitatively evaluate the development of maturation degree for fetal lung based on transfer learning deep model from ultrasound images. Chen, P, Chen, Y, Deng, Y, Wang, Y, He, P, Lv, X, et al. Int J Comput Assist Radiol Surg 2020 15:1303–12. Computer-aided diagnosis for fetal brain ultrasound images using deep convolutional neural networks. Xie, B, Lei, T, Wang, N, Cai, H, Xian, J, He, M, et al. Automatic prediction of COVID-19 from chest images using modified ResNet50. Int J Comput Assist Radiol Surg 2018 13:647–57. Convolution neural networks for real-time needle detection and localization in 2D ultrasound. Mwikirize, C, Nosher, JL, Hacihaliloglu, I.
ISUOG Practice Guidelines (updated): sonographic screening examination of the fetal heart. International Society of Ultrasound in Obstetrics and Gynecology, Carvalho, JS, Allan, LD, Chaoui, R, Copel, JA, DeVore, GR, et al. Prevalence of congenital heart disease at live birth in China. Zhao, QM, Liu, F, Wu, L, Ma, XJ, Niu, C, Huang, GY. Automated interpretation of congenital heart disease from multi-view echocardiograms. Wang, J, Liu, X, Wang, F, Zheng, L, Gao, F, Zhang, H, et al. Genetic contribution to congenital heart disease (CHD). Clinical application of targeted next-generation sequencing in fetuses with congenital heart defect. Hu, P, Qiao, F, Wang, Y, Meng, L, Ji, X, Luo, C, et al. Informed consent: Informed consent was obtained from all individuals included in this study.Įthical approval: This study was approved by the Medical Ethics Committee of the Second Affiliated Hospital of Fujian Medical University.ġ. YOLOv5 models are able to accurately distinguish normal and abnormal fetal heart ultrasound images, especially with respect to the identification of VSD, which have the potential to assist ultrasound in prenatal diagnosis.Īuthor contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.Ĭompeting interests: Authors state no conflict of interest. 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). 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. 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 validation set, YOLOv5n attained the highest overall accuracy (90.67 %). On the training set, YOLOv5n performed slightly better than the others. An excellent model was screened out after comparing YOLOv5 with other classic detection methods. You Only Look Once version 5 (YOLOv5) models were trained and tested. 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. No comparison has been made among the various types of algorithms that can assist in the prenatal diagnosis. Recently, artificial intelligence (AI) was used to assist in CHD diagnosis. Congenital heart defects (CHDs) are the most common birth defects.
0 kommentar(er)
