Title:
DATA GENERATION METHOD, AND TRAINING METHOD AND APPARATUS USING SAME
Document Type and Number:
WIPO Patent Application WO/2023/027248
Kind Code:
A1
Abstract:
Disclosed are a method by which various computing apparatuses provide data for an artificial neural network, and an apparatus therefor. Disclosed are a method and an apparatus therefor, the method comprising the steps of: training a generative adversarial network (GAN) so that a loss function of the GAN including a term for a first noise is minimized on the basis of real medical data including real normal medical data; and generating similar event medical data by adding a second noise generated using the trained GAN to real event medical data.
Inventors:
CHO KYUNGJAE (KR)
CHOI JAEWOO (KR)
SHIN YUNSEOB (KR)
TAE YUNWON (KR)
CHOI JAEWOO (KR)
SHIN YUNSEOB (KR)
TAE YUNWON (KR)
Application Number:
PCT/KR2021/016322
Publication Date:
March 02, 2023
Filing Date:
November 10, 2021
Export Citation:
Assignee:
VUNO INC (KR)
International Classes:
G06N3/04; G16H50/70; G06N3/08; G06N5/02; G16H50/20; G16H50/50; G16H70/00
Foreign References:
| US20190198156A1 | 2019-06-27 | |||
| KR101975186B1 | 2019-05-07 | |||
| KR102283416B1 | 2021-07-28 | |||
| KR20210035381A | 2021-04-01 |
Other References:
SWIECICKI ALBERT, KONZ NICHOLAS, BUDA MATEUSZ, MAZUROWSKI MACIEJ A.: "A generative adversarial network-based abnormality detection using only normal images for model training with application to digital breast tomosynthesis", SCIENTIFIC REPORTS, vol. 11, no. 1, XP093039589, DOI: 10.1038/s41598-021-89626-1
Attorney, Agent or Firm:
KBK & ASSOCIATES (KR)
Download PDF: