Two-Stage Cascaded U-Net: 1st Place Solution to BraTS Challenge 2019 Segmentation Task

被引：267

作者：

Jiang, Zeyu ^{[1
]}

Ding, Changxing ^{[1
]}

Liu, Minfeng ^{[2
]}

Tao, Dacheng ^{[3
]}

机构：

[1] South China Univ Technol, Sch Elect & Informat Engn, Guangzhou, Peoples R China

[2] Southern Med Univ, Nanfang Hosp, Guangzhou 510515, Guangdong, Peoples R China

[3] Univ Sydney, UBTECH Sydney AI Ctr, SIT, FEIT, Sydney, NSW, Australia

来源：

BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2019), PT I | 2020年 / 11992卷

基金：

澳大利亚研究理事会; 中国国家自然科学基金;

关键词：

Deep learning; Brain tumor segmentation; U-Net; BRAIN-TUMOR SEGMENTATION;

D O I：

10.1007/978-3-030-46640-4_22

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we devise a novel two-stage cascaded U-Net to segment the substructures of brain tumors from coarse to fine. The network is trained end-to-end on the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019 training dataset. Experimental results on the testing set demonstrate that the proposed method achieved average Dice scores of 0.83267, 0.88796 and 0.83697, as well as Hausdorff distances (95%) of 2.65056, 4.61809 and 4.13071, for the enhancing tumor, whole tumor and tumor core, respectively. The approach won the 1st place in the BraTS 2019 challenge segmentation task, with more than 70 teams participating in the challenge.

引用

页码：231 / 241

页数：11

共 27 条

[1]

Bakas S., 2017, Cancer Imaging Arch., DOI [DOI 10.7937/K9/TCIA.2017.GJQ7R0EF, 10.1038/sdata.2017.117]

[2]

Bakas S, 2019, Arxiv, DOI arXiv:1811.02629

[3]

Bakas Spyridon, 2017, TCIA

[4] 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

[5]

Boski M, 2017, 2017 10TH INTERNATIONAL WORKSHOP ON MULTIDIMENSIONAL (ND) SYSTEMS (NDS)

[6]

Doersch C, 2021, Arxiv, DOI [arXiv:1606.05908, DOI 10.48550/ARXIV.1606.05908]

[7]

Haocheng Shen, 2017, Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017. 20th International Conference. Proceedings: LNCS 10434, P433, DOI 10.1007/978-3-319-66185-8_49

[8] Brain tumor segmentation with Deep Neural Networks [J].

Havaei, Mohammad ;

Davy, Axel ;

Warde-Farley, David ;

Biard, Antoine ;

Courville, Aaron ;

Bengio, Yoshua ;

Pal, Chris ;

Jodoin, Pierre-Marc ;

Larochelle, Hugo .

MEDICAL IMAGE ANALYSIS, 2017, 35 :18-31

[9] Identity Mappings in Deep Residual Networks [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 :630-645

[10] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

← 1 2 3 →