Title:
METHOD AND APPARATUS FOR AUTOMATICALLY DETECTING FEATURE POINTS OF THREE-DIMENSIONAL MEDICAL IMAGE DATA BY USING DEEP LEARNING
Document Type and Number:
WIPO Patent Application WO/2021/210723
Kind Code:
A1
Abstract:
A method for automatically detecting feature points of three-dimensional medical image data by using deep learning comprises the steps of: receiving an input of a three-dimensional volume medical image; generating a two-dimensional brightness value projection image on the basis of the three-dimensional volume medical image; automatically detecting initial anatomical feature points by using a first convolutional neural network, on the basis of the two-dimensional brightness value projection image; generating a three-dimensional volume-of-interest region on the basis of the initial anatomical feature points; and automatically detecting detailed anatomical feature points by using a second convolutional neural network, which is different from the first convolutional neural network, on the basis of the three-dimensional volume-of-interest region.
Inventors:
KIM HANNAH (KR)
KIM YOUNGJUN (KR)
KIM YOUNGJUN (KR)
Application Number:
PCT/KR2020/006789
Publication Date:
October 21, 2021
Filing Date:
May 26, 2020
Export Citation:
Assignee:
IMAGOWORKS INC (KR)
International Classes:
A61B6/00; A61B6/14; G06N3/04; G06T7/00; G06T15/08; G16H30/40; G16H50/20
Foreign References:
| KR102015223B1 | 2019-10-21 | |||
| KR20120086084A | 2012-08-02 | |||
| KR20200023703A | 2020-03-06 | |||
| KR101952887B1 | 2019-06-11 | |||
| CN101882326A | 2010-11-10 |
Other References:
See also references of EP 4074259A4
Attorney, Agent or Firm:
CHOI, Young-Han (KR)
Download PDF: