Improved U-Net3+ with stage residual for brain tumor segmentation

Qin, Chuanbo; Yu-jie, WU; Liao, Wenbin; Zeng, Junying; Liang, Sheng; Zhang, Xiaozhi

doi:10.1186/s12880-022-00738-0

Cited by 15 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the features of the decoder are fused with the lower and sibling features of the encoder and the higher features of the decoder. Qin et al [19] proposed an improved UNet3+ network. In the encoder stage, phase residual network was adopted to replace the original convolution layer, which improved the performance of network feature extraction to a certain extent and avoided the phenomenon of gradient disappearance.…”

Section: Related Work a Unet And Its Variantsmentioning

confidence: 99%

DenseTrans: Multimodal Brain Tumor Segmentation Using Swin Transformer

et al. 2023

View full text Add to dashboard Cite

Aiming at the task of automatic brain tumor segmentation, this paper proposes a new DenseTrans network. In order to alleviate the problem that convolutional neural networks(CNN) cannot establish long-distance dependence and obtain global context information, swin transformer is introduced into UNet++ network, and local feature information is extracted by convolutional layer in UNet++. then, in the high resolution layer, shift window operation of swin transformer is utilized and self-attention learning windows are stacked to obtain global feature information and the capability of long-distance dependency modeling. meanwhile, in order to alleviate the secondary increase of computational complexity caused by full self-attention learning in transformer, deep separable convolution and control of swin transformer layers are adopted to achieve a balance between the increase of accuracy of brain tumor segmentation and the increase of computational complexity. on BraTs2021 data validation set, model performance is as follows: the dice dimilarity score was 93.2%,86.2%,88.3% in the whole tumor,tumor core and enhancing tumor, hausdorff distance(95%) values of 4.58mm,14.8mm and 12.2mm, and a lightweight model with 21.3M parameters and 212G flops was obtained by depth-separable convolution and other operations. in conclusion, the proposed model effectively improves the segmentation accuracy of brain tumors and has high clinical value.INDEX TERMS Brain tumor segmentation, convolutional neural networks, swin transformer, UNet++.

show abstract

Section: Related Work a Unet And Its Variantsmentioning

confidence: 99%

DenseTrans: Multimodal Brain Tumor Segmentation Using Swin Transformer

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Experiments are designed to demonstrate the effectiveness of the multi-task deep learning model proposed in this study. The ResNet [ 33 ], DeSeg [ 23 ], UNet3+ [ 34 ], radiomics model [ 14 ], RN-GAP [ 35 ], DenseNet [ 36 ], SE-Net [ 37 ], UNet [ 38 ], RA-UNet [ 39 ], Swin-UNet [ 40 ], TransUNet [ 41 ] deep learning models are set to implement separate single-task training for the classification and segmentation tasks.…”

Section: Experiments and Analysismentioning

confidence: 99%

A multi-task deep learning model for EGFR genotyping prediction and GTV segmentation of brain metastasis

Zhou,

Wang,

Zhao

et al. 2023

J Transl Med

View full text Add to dashboard Cite

Background The precise prediction of epidermal growth factor receptor (EGFR) mutation status and gross tumor volume (GTV) segmentation are crucial goals in computer-aided lung adenocarcinoma brain metastasis diagnosis. However, these two tasks present continuous difficulties due to the nonuniform intensity distributions, ambiguous boundaries, and variable shapes of brain metastasis (BM) in MR images.The existing approaches for tackling these challenges mainly rely on single-task algorithms, which overlook the interdependence between these two tasks. Methods To comprehensively address these challenges, we propose a multi-task deep learning model that simultaneously enables GTV segmentation and EGFR subtype classification. Specifically, a multi-scale self-attention encoder that consists of a convolutional self-attention module is designed to extract the shared spatial and global information for a GTV segmentation decoder and an EGFR genotype classifier. Then, a hybrid CNN-Transformer classifier consisting of a convolutional block and a Transformer block is designed to combine the global and local information. Furthermore, the task correlation and heterogeneity issues are solved with a multi-task loss function, aiming to balance the above two tasks by incorporating segmentation and classification loss functions with learnable weights. Results The experimental results demonstrate that our proposed model achieves excellent performance, surpassing that of single-task learning approaches. Our proposed model achieves a mean Dice score of 0.89 for GTV segmentation and an EGFR genotyping accuracy of 0.88 on an internal testing set, and attains an accuracy of 0.81 in the EGFR genotype prediction task and an average Dice score of 0.85 in the GTV segmentation task on the external testing set. This shows that our proposed method has outstanding performance and generalization. Conclusion With the introduction of an efficient feature extraction module, a hybrid CNN-Transformer classifier, and a multi-task loss function, the proposed multi-task deep learning network significantly enhances the performance achieved in both GTV segmentation and EGFR genotyping tasks. Thus, the model can serve as a noninvasive tool for facilitating clinical treatment.

show abstract

“…Three-dimensional-based segmentation approaches seem to be the natural way to approach the problem because it allows to exploit the three-dimensional nature of MRI by considering each voxel and its relationship to neighbors at different acquisition planes (sagittal, coronal, and axial). However, the 3D approach still has limitations, mainly related to the high computational cost in computers with limited memory, the increase in the complexity of the models and the number of parameters, making the learning process slower [ 20 , 21 , 22 ]. Therefore, researchers usually use the 2D representation of a brain MRI to avoid memory restraints and computational limitations of the 3D representation.…”

Section: Introductionmentioning

confidence: 99%

Deep 3D Neural Network for Brain Structures Segmentation Using Self-Attention Modules in MRI Images

Laiton-Bonadiez

Sánchez-Torres

Bedoya

2022

Sensors

View full text Add to dashboard Cite

In recent years, the use of deep learning-based models for developing advanced healthcare systems has been growing due to the results they can achieve. However, the majority of the proposed deep learning-models largely use convolutional and pooling operations, causing a loss in valuable data and focusing on local information. In this paper, we propose a deep learning-based approach that uses global and local features which are of importance in the medical image segmentation process. In order to train the architecture, we used extracted three-dimensional (3D) blocks from the full magnetic resonance image resolution, which were sent through a set of successive convolutional neural network (CNN) layers free of pooling operations to extract local information. Later, we sent the resulting feature maps to successive layers of self-attention modules to obtain the global context, whose output was later dispatched to the decoder pipeline composed mostly of upsampling layers. The model was trained using the Mindboggle-101 dataset. The experimental results showed that the self-attention modules allow segmentation with a higher Mean Dice Score of 0.90 ± 0.036 compared with other UNet-based approaches. The average segmentation time was approximately 0.038 s per brain structure. The proposed model allows tackling the brain structure segmentation task properly. Exploiting the global context that the self-attention modules incorporate allows for more precise and faster segmentation. We segmented 37 brain structures and, to the best of our knowledge, it is the largest number of structures under a 3D approach using attention mechanisms.

show abstract

Improved U-Net3+ with stage residual for brain tumor segmentation

Cited by 15 publications

References 17 publications

DenseTrans: Multimodal Brain Tumor Segmentation Using Swin Transformer

DenseTrans: Multimodal Brain Tumor Segmentation Using Swin Transformer

A multi-task deep learning model for EGFR genotyping prediction and GTV segmentation of brain metastasis

Deep 3D Neural Network for Brain Structures Segmentation Using Self-Attention Modules in MRI Images

Contact Info

Product

Resources

About