An aspect of the present invention relates to a method for transforming medical images, and more particularly, to an image transformation method that converts medical images using a Generative Adversarial Network (GAN).
According to one embodiment of the present invention, a novel model training method is provided that enables the generation of output images with improved sharpness. In this method, the learning model intentionally generates a blurred target image from a target image and is trained to distinguish the blurred target image from the original target image through comparison.
Application / Registration Date
2023.08.31
Application / Registration Number
10-2574756
Country
Republic of Korea/PCT
Status
Granted
Summary
An aspect of the present invention relates to a method for transforming medical images, and more particularly, to an image transformation method that converts medical images using a Generative Adversarial Network (GAN).
According to one embodiment of the present invention, a novel model training method is provided that enables the generation of output images with improved sharpness. In this method, the learning model intentionally generates a blurred target image from a target image and is trained to distinguish the blurred target image from the original target image through comparison.
Link
https://doi.org/10.8080/1020220158715