MEDICAL IMAGE PROCESSING METHOD

• Main Authors: PARK, Jonghoon, PARK, Beomhee, KIM, Byung Mook
• Format: Patent
• Language: English; French; Korean
• Published: 06.10.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

Disclosed, according to one embodiment of the present disclosure, is a medical image processing method carried out by a computing device. The method may comprise the steps of: detecting a region of interest of a medical image by using a pre-trained deep learning model; determining contour information of the region of interest; and on the basis of the contour information, generating format information defining elements that determine the representation of the medical image. Selon un mode de réalisation de la présente divulgation, un procédé de traitement d'image médicale mis en œuvre par un dispositif informatique est divulgué. Le procédé peut comprendre les étapes suivantes consistant : à détecter une région d'intérêt d'une image médicale à l'aide d'un modèle d'apprentissage profond préformé ; à déterminer des informations de contour de la région d'intérêt ; et sur la base des informations de contour, à générer des informations de format définissant des éléments qui déterminent la représentation de l'image médicale. 본 개시의 일 실시예에 따라 컴퓨팅 장치에 의해 수행되는 의료 영상 처리 방법이 개시된다. 상기 방법은, 사전 학습된 딥러닝 모델을 사용하여 의료 영상의 관심 영역을 검출하는 단계, 관심 영역에 대한 외곽선(contour) 정보를 결정하는 단계, 및 외곽선 정보를 기초로, 의료 영상의 표현을 결정짓는 요소들을 정의한 포맷(format) 정보를 생성하는 단계를 포함할 수 있다.