Hybrid Labels for Brain Tumor Segmentation

被引：7

作者：

Ahmad, Parvez ^{[1
]}

Qamar, Saqib ^{[2
]}

Hashemi, Seyed Raein ^{[3
]}

Shen, Linlin ^{[2
]}

机构：

[1] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Natl Engn Res Ctr Big Data Technol & Syst, Serv Comp Technol & Syst Lab, Wuhan 430074, Peoples R China

[2] Shenzhen Univ, Comp Vis Inst, Sch Comp Sci & Software Engn, Shenzhen, Peoples R China

[3] Brigham & Womens Hosp, 75 Francis St, Boston, MA 02115 USA

来源：

BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2019), PT II | 2020年 / 11993卷

基金：

中国国家自然科学基金;

关键词：

Deep learning; Convolutional neural networks; Residual-dense connections; Atrous rates; Brain tumor segmentation;

D O I：

10.1007/978-3-030-46643-5_15

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The accurate automatic segmentation of brain tumors enhances the probability of survival rate. Convolutional Neural Network (CNN) is a popular automatic approach for image evaluations. CNN provides excellent results against classical machine learning algorithms. In this paper, we present a unique approach to incorporate contexual information from multiple brain MRI labels. To address the problems of brain tumor segmentation, we implement combined strategies of residual-dense connections, multiple rates of an atrous convolutional layer on popular 3D U-Net architecture. To train and validate our proposed algorithm, we used BRATS 2019 different datasets. The results are promising on the different evaluation metrics.

引用

页码：158 / 166

页数：9

共 25 条

[1] 3D Dense Dilated Hierarchical Architecture for Brain Tumor Segmentation [J].

Ahmad, Parvez ;

Jin, Hai ;

Qamar, Saqib ;

Zheng, Ran ;

Jiang, Wenbin ;

Ahmad, Belal ;

Usama, Mohd .

ICBDC 2019: PROCEEDINGS OF 2019 4TH INTERNATIONAL CONFERENCE ON BIG DATA AND COMPUTING, 2019, :304-307

[2]

Bakas S, 2019, Arxiv, DOI arXiv:1811.02629

[3]

Bakas Spyridon, 2017, TCIA

[4]

Bakas Spyridon, 2017, TCIA

[5] Data Descriptor: Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features [J].

Bakas, Spyridon ;

Akbari, Hamed ;

Sotiras, Aristeidis ;

Bilello, Michel ;

Rozycki, Martin ;

Kirby, Justin S. ;

Freymann, John B. ;

Farahani, Keyvan ;

Davatzikos, Christos .

SCIENTIFIC DATA, 2017, 4

[6] MRI Tumor Segmentation with Densely Connected 3D CNN [J].

Chen, Lele ;

Wu, Yue ;

DSouza, Adora M. ;

Abidin, Anas Z. ;

Wismueller, Axel ;

Xu, Chenliang .

MEDICAL IMAGING 2018: IMAGE PROCESSING, 2018, 10574

[7]

Chen LC, 2017, Arxiv, DOI arXiv:1706.05587

[8] S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation [J].

Chen, Wei ;

Liu, Boqiang ;

Peng, Suting ;

Sun, Jiawei ;

Qiao, Xu .

BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2018, PT II, 2019, 11384 :358-368

[9]

Dolz J, 2019, Arxiv, DOI arXiv:1804.02967

[10]

Feng X, 2018, Arxiv, DOI arXiv:1812.01049

← 1 2 3 →