Advances in the Application of Artificial Intelligence in Fetal Echocardiography - 02/05/24
![](/templates/common/images/mail.png)
Abstract |
Congenital heart disease is a severe health risk for newborns. Early detection of abnormalities in fetal cardiac structure and function during pregnancy can help patients seek timely diagnostic and therapeutic advice, and early intervention planning can significantly improve fetal survival rates. Echocardiography is one of the most accessible and widely used diagnostic tools in the diagnosis of fetal congenital heart disease. However, traditional fetal echocardiography has limitations due to fetal, maternal, and ultrasound equipment factors and is highly dependent on the skill level of the operator. Artificial intelligence (AI) technology, with its rapid development utilizing advanced computer algorithms, has great potential to empower sonographers in time-saving and accurate diagnosis and to bridge the skill gap in different regions. In recent years, AI-assisted fetal echocardiography has been successfully applied to a wide range of ultrasound diagnoses. This review systematically reviews the applications of AI in the field of fetal echocardiography over the years in terms of image processing, biometrics, and disease diagnosis and provides an outlook for future research.
Le texte complet de cet article est disponible en PDF.Central Illustration |
Overview of the development and clinical application of fetal US combined with AI. Based on DL and other ML methods, US videos or images are collected as datasets, which are processed through several steps, including training, validation, and testing, to build AI models. The choice of algorithms mainly depends on the specific clinical application and the way in which the data are characterized. Several advanced models listed in the figure above are described later, such as DW-Net, U-Net, DGACNN (deep graph attention CNN), PSFFGAN (Pseudo-Siamese Feature Fusion Generative Adversarial Network), BP, and SOLO (segmenting objects by locations).
Overview of the development and clinical application of fetal US combined with AI. Based on DL and other ML methods, US videos or images are collected as datasets, which are processed through several steps, including training, validation, and testing, to build AI models. The choice of algorithms mainly depends on the specific clinical application and the way in which the data are characterized. Several advanced models listed in the figure above are described later, such as DW-Net, U-Net, DGACNN (deep graph attention CNN, PSFFGAN (Pseudo-Siamese Feature Fusion Generative Adversarial Network), BP, and SOLO (segmenting objects by locations.
Central IllustrationOverview of the development and clinical application of fetal US combined with AI. Based on DL and other ML methods, US videos or images are collected as datasets, which are processed through several steps, including training, validation, and testing, to build AI models. The choice of algorithms mainly depends on the specific clinical application and the way in which the data are characterized. Several advanced models listed in the figure above are described later, such as DW-Net, U-Net, DGACNN (deep graph attention CNN, PSFFGAN (Pseudo-Siamese Feature Fusion Generative Adversarial Network), BP, and SOLO (segmenting objects by locations.Le texte complet de cet article est disponible en PDF.
Highlights |
• | CHD is the most common cause of birth defects. |
• | AI-assisted fetal echocardiography has been widely used for image preprocessing. |
• | DL has excellent image extraction capability for medical imaging. |
• | AI models have provided new ideas for biometry measurement and disease diagnosis. |
Keywords : Ultrasonography, Fetal screening, Congenital heart disease, Deep learning
Abbreviations : 2D, 3D, 4D, A4C, AI, AUC, AVPD, AVSD, BP, CA-ISNet, CFP, CHD, CNN, CSC, d-TGA, DL, DORV, DSC, DUS, fECG, FINE, FASP, FFASP, FLDS, ICC, IoU, IUGR, LV, LVEF, mAP, ML, RNN, sonoAVC, STI, STIC, SV, SVM/HMM, TGA, TOF, T-RNN, US, VOCAL, VSD
Plan
Drs. Zhang and Xiao contributed equally to this work. |
|
This study was supported by the National Key Research and Development Program of China (2022YFF0706504), National Natural Science Foundation of China (82151316, 82171964 and 82202194), and Natural Science Foundation of Hubei Province (2021CFA046). |
Vol 37 - N° 5
P. 550-561 - mai 2024 Retour au numéroBienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?