公开(公告)号：US20240037733A1

公开(公告)日：2024-02-01

申请号：US18260245

申请日：2022-01-05

申请人： INDUSTRY ACADEMIC COOPERATION FOUNDATION, HALLYM UNIVERSITY

发明人： Chang Seok BANG ,  Jae Jun LEE ,  Bum Joo CHO

IPC分类号： G06T7/00 ,  G06V20/40 ,  G06V20/50 ,  G06V10/94 ,  G06V10/82 ,  A61B1/00

CPC分类号： G06T7/0012 ,  G06V20/49 ,  G06V20/41 ,  G06V20/50 ,  G06V10/95 ,  G06V10/945 ,  G06V10/82 ,  A61B1/000094 ,  A61B1/00016 ,  A61B1/0004 ,  G06T2207/10016 ,  G06T2200/24 ,  G06T2207/10068 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/30096 ,  G06T2207/30092 ,  G06T2207/30104

摘要： Provided is a control method for a system for determining a lesion obtained via a real-time image. The control method comprises the steps of: an endoscope device obtaining a stomach endoscopy image; the endoscope device transmitting the obtained stomach endoscopy image to a server; the server determining a lesion included in the stomach endoscopy image, by inputting the stomach endoscopy image into a first artificial intelligence model; when it is determined that a lesion is detected in the stomach endoscopy image, the server obtaining an image including the lesion and transmitting the image to a database of the server; the server determining the type of the lesion included in the image, by inputting the image into a second artificial intelligence model; and when it is determined that a lesion is detected in the stomach endoscopy image, a display device displaying a UI for guiding the location of the lesion in the stomach endoscopy image.

公开(公告)号：US20220031227A1

公开(公告)日：2022-02-03

申请号：US17278962

申请日：2019-09-25

申请人： INDUSTRY ACADEMIC COOPERATION FOUNDATION, HALLYM UNIVERSITY

发明人： Bum-Joo CHO ,  Chang Seok BANG ,  Se Woo PARK ,  Jae-Jun LEE ,  Jae-Ho CHOI ,  Seok-Hwan HONG ,  Yong-Tak YOO

IPC分类号： A61B5/00 ,  G06T7/00 ,  G06K9/62 ,  A61B1/273 ,  G06N3/04 ,  G16H30/40 ,  G16H50/20

摘要： A method for diagnosing a gastric lesion from endoscopic images is provided. The method comprises: acquiring a plurality of gastric lesion images; generating a dataset by linking the plurality of gastric lesion images with patient information; preprocessing the dataset in a way that is applicable to a deep learning algorithm; and building an artificial neural network by training the artificial neural network by using the preprocessed dataset as input and gastric lesion classification results as output.