Artificial-intelligence-based medical image conversion method
AssigneePolestar Healthcare Co., Ltd.
InventorsYeo Dong YOON, Eun Chong LEE
Life of this patent
Estimating the term…
Abstract
One aspect of the present invention relates to a method for converting a medical image by using artificial intelligence and, more specifically, to a medical image conversion method using artificial intelligence, the method using a generative adversarial network (GAN), which is one of deep learning technologies, thereby generating an MR image on the basis of a CT image, or the CT image on the basis of the MR image. According to one embodiment of the present invention, provided is the medical image conversion method, which can generate an MR image on the basis of a CT image and, conversely, the CT image on the basis of the MT image.
Claims10
A medical image conversion method in which an artificial intelligence (AI) learning part performs conversion between medical images of different domains while performing learning, the medical image conversion method comprising:
- receiving, by the AI learning part, a first medical image;
- generating, by the AI learning part, a second medical image from the first medical image by learning, the domain of the second medical image being different from the domain of the first medical image;
- and
- first learning, wherein if the first medical image is one of a pair of paired data, the AI learning part compares a difference between the second medical image and another of the pair of paired data and performs the learning to reduce the difference.
Dependencies are inferred from the claim text.