期刊论文

Zeng, Junying

英文

BMC Medical Imaging

1471-2342

2022

22

1

1-15

10.1186/s12880-022-00738-0

This work was partially supported by the National Natural Science Foundation of China (No.62071213, No.61771347), the Guangdong foundation for basic and applied basic research (No.2021A1515011576), the Special Programs in Key Areas of Artificial Intelligence in Guangdong Universities (No.2019KZDZX1017), and the Open fund of Guangdong Key Laboratory of digital signal and image processing technology (2020GDDSIPL-03), and 2021 Jiangmen basic and theoretical science research science and technology plan project (〔2021〕N0.87), Basic Research and Applied Basic Research Key Project in General Colleges and Universities of Guangdong Province (2021ZDZX1032), 2021 Guangdong Provincial Education Department Graduate Education Innovation Program Project (Guangdong Education and Research Letter [2021] No. 2).

本校为其他机构

Background: For the encoding part of U-Net3+,the ability of brain tumor feature extraction is insufficient, as a result, the features can not be fused well during up-sampling, and the accuracy of segmentation will reduce. Methods: In this study, we put forward an improved U-Net3+ segmentation network based on stage residual. In the encoder part, the encoder based on the stage residual structure is used to solve the vanishing gradient problem caused by the increasing in network depth, and enhances the feature extraction ability of the encoder wh...