Abstract
BackgroundFor 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.MethodsIn 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 which is instrumental in full feature fusion when up-sampling in the network. What’s more, we replaced batch normalization (BN) layer with filter response normalization (FRN) layer to eliminate batch size impact on the network. Based on the improved U-Net3+ two-dimensional (2D) model with stage residual, IResUnet3+ three-dimensional (3D) model is constructed. We propose appropriate methods to deal with 3D data, which achieve accurate segmentation of the 3D network.ResultsThe experimental results showed that: the sensitivity of WT, TC, and ET increased by 1.34%, 4.6%, and 8.44%, respectively. And the Dice coefficients of ET and WT were further increased by 3.43% and 1.03%, respectively. To facilitate further research, source code can be found at: https://github.com/YuOnlyLookOne/IResUnet3Plus.ConclusionThe improved network has a significant improvement in the segmentation task of the brain tumor BraTS2018 dataset, compared with the classical networks u-net, v-net, resunet and u-net3+, the proposed network has smaller parameters and significantly improved accuracy.
Highlights
MethodsWe put forward an improved U-Net3+ segmentation network based on stage residual
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
Because of the insufficient feature extraction ability of the encoder part based on U-Net3+, which results in inadequate feature fusion during network up-sampling, reducing the segmentation accuracy, this study proposes an improved U-Net3+ segmentation network based on stage residual and presents its 2D and 3D segmentation models
Summary
The dataset The dataset used in this study is BraTs2018. There are 285 and 66 cases for training and validation set, respectively. Ablation study Comparing the segmentation effect of U-Net, U-Net++, and U-Net3+ models for brain tumors, we obtained that the classical network U-Net is based on its encoderdecoder network structure, and skip connection can connect encoder-decoder layer to merge low-level and high-level features to better perform basic segmentation of tumor lesions. Comparing 3DU-Net, 3DU-Net3+, 3D_FRN_Unet3+, and 3DIResUnet3+, we obtain that the full-scale skip connection proposed by U-Net3+ can provide more information for up-sampling by combining high-level and low-level semantics from different scales; improving the segmentation accuracy. The encoder is improved based on the stage residuals, which solves the problem of insufficient feature extraction ability of U-Net3+ encoder at the cost of adding a small number of parameters, and provides more semantic information for up-sampling to further improve the segmentation accuracy. This shows that the index HD sensitive to the difference of location information will be slightly affected while increasing the value of dice
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
