EP01.51: Artificial intelligence in the optimisation of the quality of ultrasound images.

Autor:	Arbeláez, P., Sarmiento, A., Rodriguez, N., Escobar, M.C., Rodríguez, N., Castillo, A., Ramirez, N., Echeverry, L.M.
Předmět:	CONVOLUTIONAL neural networks GENERATIVE adversarial networks ULTRASONIC imaging ARTIFICIAL intelligence CONGENITAL heart disease
Zdroj:	Ultrasound in Obstetrics & Gynecology; Sep2024 Supplement 1, Vol. 64, p122-122, 1p
Abstrakt:	This article discusses the use of artificial intelligence (AI) to optimize the quality of cardiac ultrasound images. The study used a public database of ultrasound images called CAMUS and developed a method called UltraGAN, which uses AI to improve image quality. The method involves training a convolutional neural network (CNN) with high-quality image features and transferring this information to medium and low-quality images. The results showed that UltraGAN can automatically identify structures in ultrasounds with over 90% accuracy without compromising the anatomical characteristics of the original images. This research demonstrates the potential of AI as a complementary tool in screening for congenital heart diseases. [Extracted from the article]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu Plný text