Learning method for generating multiphase collateral image and multiphase collateral image generating method using maching learning
AssigneesThe Catholic University of Korea Industry-Academic Cooperation Foundation, Konkuk University Glocal Industry-Academic Collaboration Foundation
InventorsJin Tae KWAK, Nhat To MINH NGUYEN, Hyun Jeong KIM, Hong Gee ROH
Life of this patent
Estimating the term…
Abstract
A learning method for generating a multiphase collateral image comprises the steps of: receiving inputs of an MRI image of a head part and a multiphase collateral image generated on the basis of the MRI image; generating a brain mask by using the MRI image; generating an MRI image and a multiphase collateral image which are masked by the brain mask; and learning the masked multiphase collateral image for the masked MRI image by using a learning network.
Claims9
A learning method for generating multiphase collateral images, the learning method comprising:
- receiving a magnetic resonance imaging (MRI) image of a head and multiphase collateral images generated on the basis of the MRI image;
- generating a brain mask using the MRI image;
- generating an MRI image and multiphase collateral images which are masked by the brain mask;
- and
- learning the masked multiphase collateral images for the masked MRI image using a learning network.
A method of generating multiphase collateral images using machine learning, the method comprising:
- receiving a magnetic resonance imaging (MRI) image of a subject's head;
- and
- generating multiphase collateral images for the MRI image using a learning network,
- wherein the learning network is a network which has learned reference multiphase collateral images for reference MRI images.
Dependencies are inferred from the claim text.