METHOD FOR ESTIMATING BODY COMPOSITION VOLUME OF SUBJECT PROGRAM AND APPARATUS THEREFOR

The purpose of the present invention is to provide a method for estimating the volume of muscle or fat of a subject based on deep learning for early diagnosis of cancer cachexia. A body composition volume estimation method comprises the steps of: inputting abdominal and pelvic CT (computed tomograph...

Full description

Saved in:
Bibliographic Details
Main Authors JINSIK YOON, MOON JAE CHUNG, JONGEUN CHOI, HEEJIN YU
Format Patent
LanguageEnglish
Korean
Published 10.05.2024
Subjects
CALCULATING
COMPUTING
COUNTING
DIAGNOSIS
HUMAN NECESSITIES
HYGIENE
IDENTIFICATION
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
MEDICAL OR VETERINARY SCIENCE
PHYSICS
SURGERY
Online AccessGet full text

Cover

More Information
Summary:The purpose of the present invention is to provide a method for estimating the volume of muscle or fat of a subject based on deep learning for early diagnosis of cancer cachexia. A body composition volume estimation method comprises the steps of: inputting abdominal and pelvic CT (computed tomography) images of a subject into a pre-learned deep learning-based body composition mask estimation model; obtaining an output image for estimating the volume of a specific body composition corresponding to the abdominal and pelvic CT images of the subject through the body composition mask estimation model; performing post-correction on the bone and thoracic cavity and post-correction on the psoas muscle for the acquired output image and reflecting the same in the acquired output image; and estimating the volume of the specific body component based on the output image to which the post-correction is reflected. 피검자의 체성분 볼륨을 추정하는 장치가 개시된다. 본 장치는 미리 학습된 딥러닝 기반의 체성분 마스크 추정 모델이 저장된 메모리 및 제어부를 포함할 수 있다. 본 장치가 제공됨으로써, 효율적으로 피검자 체성분의 볼륨이 추정될 수 있다.
Bibliography:Application Number: KR20220145360