LIVER CT IMAGE SEGMENTATION SYSTEM AND ALGORITHM BASED ON HYBRID SUPERVISED LEARNING

Disclosed in the present invention are a liver CT image segmentation system and algorithm based on hybrid supervised learning. The image segmentation system comprises an image pre-processing unit, a feature extraction unit, a word vector segmentation unit and a single-layer convolutional classificat...

Full description

Saved in:
Bibliographic Details
Main Authors LIU, Lilu, XIONG, Rong, WANG, Yue, NIE, Xiuping
Format Patent
LanguageChinese
English
French
Published 20.04.2023
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Disclosed in the present invention are a liver CT image segmentation system and algorithm based on hybrid supervised learning. The image segmentation system comprises an image pre-processing unit, a feature extraction unit, a word vector segmentation unit and a single-layer convolutional classification unit, wherein the image pre-processing unit is in data connection with the feature extraction unit, and the feature extraction unit is respectively in data connection with the word vector segmentation unit and the single-layer convolutional classification unit. By means of the present invention, segmentation and classification tasks are respectively performed by using a multi-task framework, and relatively high segmentation precision is achieved by using a large amount of weak label data and a small number of strong labels; for the problem of there being many independent parameters between multiple tasks, network parameters shared between multiple tasks are increased to the greatest extent; and the segmentation
Bibliography:Application Number: WO2022CN101697