SEResU-Net for Multimodal Brain Tumor Segmentation

被引:9
作者
Yan, Chengdong [1 ,2 ]
Ding, Jurong [1 ,2 ]
Zhang, Hui [1 ,2 ]
Tong, Ke [1 ,2 ]
Hua, Bo [1 ,2 ]
Shi, Shaolong [3 ,4 ,5 ]
机构
[1] Sichuan Univ Sci & Engn, Sch Automat & Informat Engn, Zigong 643099, Peoples R China
[2] Sichuan Univ Sci & Engn, Artificial Intelligence Key Lab Sichuan Prov, Zigong 643009, Peoples R China
[3] Univ Elect Sci & Technol China, Yangtze Delta Reg Inst Quzhou, Quzhou 324000, Peoples R China
[4] Univ Elect Sci & Technol China, Sch Life Sci & Technol, Chengdu 610056, Peoples R China
[5] City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
基金
中国国家自然科学基金;
关键词
Tumors; Image segmentation; Feature extraction; Magnetic resonance imaging; Residual neural networks; Deep learning; Neural networks; Brain; MRI; brain tumor segmentation; deep learning; U-Net; residual network; squeeze-and-excitation network; U-NET;
D O I
10.1109/ACCESS.2022.3214309
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Glioma is the most common type of brain tumor, and it has a high mortality rate. Accurate tumor segmentation based on magnetic resonance imaging (MRI) is of great significance for the diagnosis and treatment of brain tumors. Recently, the automatic segmentation of brain tumors based on U-Net has gained considerable attention. However, brain tumor segmentation is a challenging task due to the structural variations and inhomogeneous intensity of tumors. Existing brain tumor segmentation studies have shown that the problems of insufficient down-sampling feature extraction and loss of up-sampling information arise when using U-Net to segment brain tumors. In this study, we proposed an improved U-Net model, SEResU-Net, which combines the deep residual network and the Squeeze-and-Excitation Network. The deep residual network solves the problem of network degradation so that SEResU-Net can extract more feature information. The Squeeze-and-Excitation Network avoids information loss and enables the network to focus on the useful feature map, which solves the problem of insufficient segmentation accuracy of small-scale brain tumors. Furthermore, a fusion loss function combining Dice loss and cross-entropy loss was proposed to solve the problems of network convergence and data imbalance. The performance of SEResU-Net was evaluated on the dataset of BraTS2018 and BraTS2019. Experimental results revealed that the mean Dice similarity coefficients of SEResU-Net were 0.9373, 0.9108, and 0.8758 for the whole tumor, the tumor core, and the enhanced tumor, which were 7.10%, 11.88%, and 15.33% greater than those of the U-Net benchmark network, respectively. Our findings demonstrate that the proposed SEResU-Net has a competitive effect in segmenting multimodal brain tumors.
引用
收藏
页码:117033 / 117044
页数:12
相关论文
共 43 条
  • [1] HTTU-Net: Hybrid Two Track U-Net for Automatic Brain Tumor Segmentation
    Aboelenein, Nagwa M.
    Piao Songhao
    Koubaa, Anis
    Noor, Alam
    Afifi, Ahmed
    [J]. IEEE ACCESS, 2020, 8 : 101406 - 101415
  • [2] SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
    Badrinarayanan, Vijay
    Kendall, Alex
    Cipolla, Roberto
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) : 2481 - 2495
  • [3] Bakas S, 2019, Arxiv, DOI [arXiv:1811.02629, 10.48550/arXiv.1811.02629, DOI 10.48550/ARXIV.1811.02629]
  • [4] Data Descriptor: Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features
    Bakas, Spyridon
    Akbari, Hamed
    Sotiras, Aristeidis
    Bilello, Michel
    Rozycki, Martin
    Kirby, Justin S.
    Freymann, John B.
    Farahani, Keyvan
    Davatzikos, Christos
    [J]. SCIENTIFIC DATA, 2017, 4
  • [5] A survey of MRI-based medical image analysis for brain tumor studies
    Bauer, Stefan
    Wiest, Roland
    Nolte, Lutz-P
    Reyes, Mauricio
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2013, 58 (13) : R97 - R129
  • [6] MSENet: Multi-Modal Squeeze-and-Excitation Network for Brain Tumor Severity Prediction
    Bodapati, Jyostna Devi
    Shareef, Shaik Nagur
    Naralasetti, Veeranjaneyulu
    Mundukur, Nirupama Bhat
    [J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2021, 35 (07)
  • [7] Botev ZI, 2013, HANDB STAT, V31, P35, DOI 10.1016/B978-0-444-53859-8.00003-5
  • [8] RFDCR: Automated brain lesion segmentation using cascaded random forests with dense conditional random fields
    Chen, Gaoxiang
    Li, Qun
    Shi, Fuqian
    Rekik, Islem
    Pan, Zhifang
    [J]. NEUROIMAGE, 2020, 211
  • [9] Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks
    Dong, Hao
    Yang, Guang
    Liu, Fangde
    Mo, Yuanhan
    Guo, Yike
    [J]. MEDICAL IMAGE UNDERSTANDING AND ANALYSIS (MIUA 2017), 2017, 723 : 506 - 517
  • [10] Medical Image Segmentation based on U-Net: A Review
    Du, Getao
    Cao, Xu
    Liang, Jimin
    Chen, Xueli
    Zhan, Yonghua
    [J]. JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY, 2020, 64 (02)