Double attention U-Net for brain tumor MR image segmentation

PurposeAutomatic segmentation of brain tumor from medical images is a challenging task because of tumor's uneven and irregular shapes. In this paper, the authors propose an attention-based nested segmentation network, named DAU-Net. In total, two types of attention mechanisms are introduced to make the U-Net network focus on the key feature regions. The proposed network has a deep supervised encoder–decoder architecture and a redesigned dense skip connection. DAU-Net introduces an attention mechanism between convolutional blocks so that the features extracted at different levels can be merged with a task-related selection.Design/methodology/approachIn the coding layer, the authors designed a channel attention module. It marks the importance of each feature graph in the segmentation task. In the decoding layer, the authors designed a spatial attention module. It marks the importance of different regional features. And by fusing features at different scales in the same coding layer, the network can fully extract the detailed information of the original image and learn more tumor boundary information.FindingsTo verify the effectiveness of the DAU-Net, experiments were carried out on the BRATS 2018 brain tumor magnetic resonance imaging (MRI) database. The segmentation results show that the proposed method has a high accuracy, with a Dice similarity coefficient (DSC) of 89% in the complete tumor, which is an improvement of 8.04 and 4.02%, compared with fully convolutional network (FCN) and U-Net, respectively.Originality/valueThe experimental results show that the proposed method has good performance in the segmentation of brain tumors. The proposed method has potential clinical applicability.

[1]  Carlos Alberto Silva,et al.  Automatic brain tissue segmentation in MR images using Random Forests and Conditional Random Fields , 2016, Journal of Neuroscience Methods.

[2]  Qun Li,et al.  RFDCR: Automated brain lesion segmentation using cascaded random forests with dense conditional random fields , 2020, NeuroImage.

[3]  Jiangtao Xu,et al.  Attention fusion network for multi-spectral semantic segmentation , 2021, Pattern Recognit. Lett..

[4]  Zhong Ji,et al.  Fusion-Attention Network for person search with free-form natural language , 2018, Pattern Recognit. Lett..

[5]  Syed Muhammad Anwar,et al.  Segmentation of Glioma Tumors in Brain Using Deep Convolutional Neural Network , 2017, Neurocomputing.

[6]  Mohammad Sohel Rahman,et al.  MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation , 2019, Neural Networks.

[7]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[8]  Rostom Kachouri,et al.  Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy , 2020, Medical Image Anal..

[9]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Mohamed Akil,et al.  Fully Automatic Brain Tumor Segmentation using End-To-End Incremental Deep Neural Networks in MRI images , 2018, Comput. Methods Programs Biomed..

[11]  Yoshua Bengio,et al.  Fine-grained attention mechanism for neural machine translation , 2018, Neurocomputing.

[12]  Zexun Zhou,et al.  AFPNet: A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumor segmentation via MRI images , 2020, Neurocomputing.

[13]  Jianchao Zeng,et al.  Brain tumor segmentation of multi-modality MR images via triple intersecting U-Nets , 2021, Neurocomputing.

[14]  B. S. Manjunath,et al.  Brain Tumor Segmentation and Tractographic Feature Extraction from Structural MR Images for Overall Survival Prediction , 2018, BrainLes@MICCAI.

[15]  O. Algın,et al.  Exploiting Lamina Terminalis Appearance and Motion in Prediction of Hydrocephalus Using Convolutional LSTM Network. , 2021, Journal of neuroradiology = Journal de neuroradiologie.

[16]  Nima Tajbakhsh,et al.  UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation , 2020, IEEE Transactions on Medical Imaging.

[17]  ChangShui Zhang,et al.  Challenges in machine learning , 2013 .

[18]  Fanhua Shang,et al.  CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation , 2019, MBIA/MFCA@MICCAI.

[19]  Yuan Wang,et al.  Hypergraph membrane system based F2 fully convolutional neural network for brain tumor segmentation , 2020, Appl. Soft Comput..

[20]  Yanjun Peng,et al.  Segmentation of the multimodal brain tumor image used the multi-pathway architecture method based on 3D FCN , 2021, Neurocomputing.

[21]  Youling Li,et al.  A calibration method of computer vision system based on dual attention mechanism , 2020, Image Vis. Comput..

[22]  Vijayan K. Asari,et al.  Nuclei Segmentation with Recurrent Residual Convolutional Neural Networks based U-Net (R2U-Net) , 2018, NAECON 2018 - IEEE National Aerospace and Electronics Conference.

[23]  Jianxin Wang,et al.  A survey on U-shaped networks in medical image segmentations , 2020, Neurocomputing.

[24]  Christos Davatzikos,et al.  Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features , 2017, Scientific Data.

[25]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[26]  Millie Pant,et al.  Brain tumor segmentation and classification from magnetic resonance images: Review of selected methods from 2014 to 2019 , 2020, Pattern Recognit. Lett..

[27]  Ao Li,et al.  A novel end-to-end brain tumor segmentation method using improved fully convolutional networks , 2019, Comput. Biol. Medicine.

[28]  Ren Kai,et al.  Automated brain tumor segmentation from multimodal MRI data based on Tamura texture feature and an ensemble SVM classifier , 2019, Int. J. Intell. Comput. Cybern..