公开(公告)号：US20240013510A1

公开(公告)日：2024-01-11

申请号：US17858663

申请日：2022-07-06

Applicant: Shanghai United Imaging Intelligence Co., Ltd.

Inventor： Yikang Liu ,  Luojie Huang ,  Zhang Chen ,  Xiao Chen ,  Shanhui Sun

IPC: G06V10/75 ,  G06V10/764 ,  G06T7/73 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06V10/751 ,  G06V10/764 ,  G06T7/73 ,  G06N3/0454 ,  G06N3/08 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: Described herein are systems, methods, and instrumentalities associated with tracking groups of small objects in medical images. The tracking may be accomplished by, for each one of a sequence of medical images, determining a plurality of candidate objects captured in the medical image, grouping the plurality of candidate objects into a plurality of groups of candidate objects and dividing the medical image into a plurality of regions that each surrounds a corresponding group of candidate objects. Each of the plurality of regions may be examined to extract respective features associated with each corresponding group of candidate objects. A match between a first group of candidate objects in a first medical image and a second group of candidate objects in a second medical image may be determined based on first features associated with the first group and second features associated with the second group.

公开(公告)号：US20230206429A1

公开(公告)日：2023-06-29

申请号：US17564317

申请日：2021-12-29

Applicant: Shanghai United Imaging Intelligence Co., Ltd.

Inventor： Yikang Liu ,  Luojie Huang ,  Shanhui Sun ,  Zhang Chen ,  Xiao Chen

IPC: G06T7/00 ,  G06V10/762 ,  G06V10/82 ,  G06N3/02

CPC classification number: G06T7/0012 ,  G06V10/762 ,  G06V10/82 ,  G06N3/02 ,  G06T2207/10121 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30104

Abstract: Described herein are systems, methods, and instrumentalities associated with automatically detecting and enhancing multiple objects in medical scan images. The detection and/or enhancement may be accomplished utilizing artificial neural networks such as one or more classification neural networks and/or one or more graph neural networks. The neural networks may be used to detect areas in the medical scan images that may correspond to the objects of interest and cluster the areas belonging to a same object into a respective cluster. These tasks may be accomplished, for example, by representing the areas corresponding to the objects of interest and their interrelationships with a graph and processing the graph through the one or more graph neural networks so that the areas belonging to each object may be properly labeled and clustered. The clusters may then be used to enhance the objects of interests in one or more output scan images.