Brain Tumor Segmentation based on 3D Unet with Multi-class Focal Loss

被引：0

作者：

Chang, Jie ^{[1
,2
]}

Ye, Minquan ^{[2
]}

Zhang, Xiaoci ^{[1
]}

Huang, Daobin ^{[2
]}

Wang, Peipei ^{[2
]}

Yao, Chuanwen ^{[2
]}

机构：

[1] Univ Sci & Technol China, Sch Comp Sci & Technol, Hefei, Anhui, Peoples R China

[2] Wannan Med Coll, Res Ctr Hlth Big Data Min & Applicat, Sch Med Informat, Wuhu, Peoples R China

来源：

2018 11TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2018) | 2018年

基金：

中国国家自然科学基金;

关键词：

focal loss; MR images; brain tumor segmentation;

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

Brain tumor segmentation on MR images has significant clinical meaning due to glioblastomas which are the most lethal form of these tumors. Compared to manual segmentation, automatic segmentation system is superior in timesaving and experience-insensitivity for doctors during clinical practice. However, its inherent contradiction is not addressed yet. i.e. imbalance of multi-class of different brain tissues. As such, we proposed a multi-class focal loss to make the loss function emphasis on bad-classified voxels in MR images. Our experiments based on the 3D UNet model proved that this method can significantly improve labeling and segmentation accuracy as compared to other loss layers.

引用

页数：5

共 15 条

[1]

[Anonymous], 2016, TOMCCAP, DOI DOI 10.1016/J.YMPEV.2016.12.037

[2]

[Anonymous], IEEE T PATTERN ANAL

[3] A survey of MRI-based medical image analysis for brain tumor studies [J].

Bauer, Stefan ;

Wiest, Roland ;

Nolte, Lutz-P ;

Reyes, Mauricio .

PHYSICS IN MEDICINE AND BIOLOGY, 2013, 58 (13) :R97-R129

[4] 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

[5] Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge [J].

Isensee, Fabian ;

Kickingereder, Philipp ;

Wick, Wolfgang ;

Bendszus, Martin ;

Maier-Hein, Klaus H. .

BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2017, 2018, 10670 :287-297

[6] Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation [J].

Kamnitsas, Konstantinos ;

Ledig, Christian ;

Newcombe, Virginia F. J. ;

Sirnpson, Joanna P. ;

Kane, Andrew D. ;

Menon, David K. ;

Rueckert, Daniel ;

Glocker, Ben .

MEDICAL IMAGE ANALYSIS, 2017, 36 :61-78

[7] Deep MRI brain extraction: A 3D convolutional neural network for skull stripping [J].

Kleesiek, Jens ;

Urban, Gregor ;

Hubert, Alexander ;

Schwarz, Daniel ;

Maier-Hein, Klaus ;

Bendszus, Martin ;

Biller, Armin .

NEUROIMAGE, 2016, 129 :460-469

[8] Gradient-based learning applied to document recognition [J].

Lecun, Y ;

Bottou, L ;

Bengio, Y ;

Haffner, P .

PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2278-2324

[9] V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation [J].

Milletari, Fausto ;

Navab, Nassir ;

Ahmadi, Seyed-Ahmad .

PROCEEDINGS OF 2016 FOURTH INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2016, :565-571

[10] Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images [J].

Pereira, Sergio ;

Pinto, Adriano ;

Alves, Victor ;

Silva, Carlos A. .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (05) :1240-1251

← 1 2 →