公开(公告)号：US20230368388A1

公开(公告)日：2023-11-16

申请号：US18196126

申请日：2023-05-11

申请人： SHANDONG NORMAL UNIVERSITY

发明人： Jie XUE ,  Dengwang LI ,  Xiyu LIU ,  Qi LI ,  Guanzhong GONG ,  Jianbo WANG ,  Pu HUANG

IPC分类号： G06T7/11 ,  G06T9/00 ,  G06T7/00

CPC分类号： G06T7/11 ,  G06T9/002 ,  G06T7/0012 ,  G06T2207/20132 ,  G06T2207/20081 ,  G06T2207/30096 ,  G06T2207/30092 ,  G06T2207/20084 ,  G06T2207/10081 ,  G06T2207/10088

摘要： A method and system for segmenting three-dimensional images of pancreases and tumors, including: acquiring 3D images of the pancreas and the tumor and preprocessing same with a soft tissue window to control the intensity value of the image within a set range; cropping all images into block-shaped regions of a set size and feeding same into a trained convolutional neural network model, and when training a network, dynamically adjusting the learning weight between the pancreas and the tumor under the guidance of temperature to learn the features of the pancreas and the tumor; and after performing data preprocessing on the 3D images of the pancreas and labels, using the trained network model for online testing and evaluating, and outputting the segmentation result.