PERIPHERAL ARTERY DIAGNOSIS-IMAGE LEARNING DEVICE AND METHOD, AND CONCERNING PERIPHERAL ARTERY DISEASE DIAGNOSIS DEVICE AND METHOD USING LEARNING MODEL CONSTRUCTED THROUGH LEARNING DEVICE AND METHOD

• Main Authors: LEE, Jae Goan, HWANG, Byung Hee, CHANG, Ki Yuk, LEE, Kwan Yong, KIM, Won Tae, KANG, Shin Uk, LEE, Myung Jae, KIM, Dong Min
• Format: Patent
• Language: English; French; Korean
• Published: 03.03.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; DIAGNOSIS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

According to the present invention, a device for diagnosing a peripheral artery disease on the basis of artificial intelligence can be provided. A peripheral artery stenosis diagnosis device based on artificial intelligence can comprise: a data input unit for inputting peripheral artery images on the basis of angiographic images in a diagnostic area including a peripheral artery; a peripheral artery image interpolation unit which has an interpolation image learning model having learning-based sub peripheral artery images on the basis of motion changes of the peripheral artery images acquired on the basis of predetermined time units, and which uses the interpolation image learning model to generate the sub peripheral artery images corresponding to the peripheral artery images; and a peripheral artery image analysis unit for analyzing a concerning peripheral artery disease by confirming information provided from the data input unit and the peripheral artery image interpolation unit. Selon la présente invention, un dispositif pour diagnostiquer une maladie artérielle périphérique sur la base d'une intelligence artificielle peut être fourni. Un dispositif de diagnostic de sténose artérielle périphérique basé sur une intelligence artificielle peut comprendre : une unité d'entrée de données pour entrer des images d'artère périphérique sur la base d'images angiographiques dans une zone de diagnostic comprenant une artère périphérique ; une unité d'interpolation d'image d'artère périphérique qui a un modèle d'apprentissage d'image d'interpolation ayant des images d'artère sous-périphérique basées sur l'apprentissage sur la base de changements de mouvement des images d'artère périphérique acquises sur la base d'unités de temps prédéterminées, et qui utilise le modèle d'apprentissage d'image d'interpolation pour générer les images d'artère sous-périphérique correspondant aux images d'artère périphérique ; et une unité d'analyse d'image d'artère périphérique pour analyser une maladie d'artère périphérique en confirmant des informations fournies par l'unité d'entrée de données et l'unité d'interpolation d'image d'artère périphérique. 본 발명에 따르면, 인공지능 기반으로 말초동맥 질환을 진단하는 장치가 제공될 수 있다. 상기 인공지능 기반의 말초동맥 협착 진단 장치는 말초동맥이 포함된 진단영역의 혈관조영 영상을 기반으로 하는 말초동맥 영상을 입력하는 데이터 입력부와, 미리 정해진 시간 단위를 기준으로 획득된 상기 말초동맥 영상의 모션 변화에 기초하여 학습기반 서브 말초동맥 영상을 구성하는 보간영상 학습모델을 구비하며, 상기 보간영상 학습모델을 사용하여 상기 말초동맥 영상에 대응되는 서브 말초동맥 영상을 생성하는 말초동맥 영상 보간부와, 상기 데이터 입력부 및 말초동맥 영상 보간부에서 제공되는 정보를 확인하여 유의한 말초동맥 질환을 분석하는 말초동맥 영상 분석부를 포함할 수 있다.