Title:
MEDICAL-IMAGE-BASED LESION ANALYSIS METHOD
Document Type and Number:
WIPO Patent Application WO/2022/186594
Kind Code:
A1
Abstract:
Disclosed is a medical-image-based lesion analysis method performed by a computing device, according to an embodiment of the present disclosure. The lesion analysis method may comprise the steps of: generating, by using a pre-processing module, an input image of a pre-trained detection module from a medical image including a chest region; generating, by using the detection module, a probability value regarding the presence of a nodule in at least one region of interest and first location information about the at least one region of interest, on the basis of the input image; and determining, by using a post-processing module, second location information about a suspected nodule present in the medical image from the first location information, on the basis of the probability value regarding the presence of the nodule.
More Like This:
Inventors:
PARK HYUNHO (KR)
PARK GWANGBEEN (KR)
LEE SEUNGHO (KR)
PARK GWANGBEEN (KR)
LEE SEUNGHO (KR)
Application Number:
PCT/KR2022/002928
Publication Date:
September 09, 2022
Filing Date:
March 02, 2022
Export Citation:
Assignee:
VUNO INC (KR)
International Classes:
G16H30/40; G06N3/08; G06N20/00; G06T3/00; G06T7/70; G16H30/20; G16H50/20; G16H50/30; G16H50/70
Foreign References:
KR102150682B1 | 2020-09-02 | |||
KR101981202B1 | 2019-05-22 | |||
KR20200085012A | 2020-07-14 | |||
KR20200062614A | 2020-06-04 | |||
KR20190094133A | 2019-08-12 |
Attorney, Agent or Firm:
LEE, Dae Ho et al. (KR)
Download PDF: