Brain Tumor Segmentation Using Concurrent Fully Convolutional Networks and Conditional Random Fields

被引：9

作者：

Shen, Guangyu ^{[1
]}

Ding, Yi ^{[1
]}

Lan, Tian ^{[1
]}

Chen, Hao ^{[1
]}

Qin, Zhiguang ^{[1
]}

机构：

[1] Univ Elect Sci & Technol, Sch Software & Engn, Chengdu, Sichuan, Peoples R China

来源：

PROCEEDINGS OF 2018 THE 3RD INTERNATIONAL CONFERENCE ON MULTIMEDIA AND IMAGE PROCESSING (ICMIP 2018) | 2018年

基金：

中国国家自然科学基金;

关键词：

component; Deep Learning; concurrent fully convolutional networks; conditional random fields; multimodal MRI; brain tumor segmentation; MEDICAL IMAGE SEGMENTATION;

D O I：

10.1145/3195588.3195590

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

We propose a concurrent Fully Convolutional Networks(CFCN) structure which contains three Fully Convolutional Networks(FCN). Gaussian filter, Mean filter and Median filter are chosen to pre-process the original multimodal MR images. Then, we fuse the results from three networks. Finally, a Fully Connected Conditional Random Field (Fully Connected CRF) is used to accomplish the post-processing, improving the model's ability of detecting minute structures. Our model was trained and evaluated on BRATS 2015 challenge dataset. The results show that our model provides promising segmentations.

引用

页码：24 / 30

页数：7

共 50 条

[31] Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
Pereira, Sergio
Pinto, Adriano
Alves, Victor
Silva, Carlos A.
[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (05) : 1240 - 1251
[32] Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
M. Mohammed Thaha
K. Pradeep Mohan Kumar
B. S. Murugan
S. Dhanasekeran
P. Vijayakarthick
A. Senthil Selvi
[J]. Journal of Medical Systems, 2019, 43
[33] Segmentation and labeling of documents using Conditional Random Fields
Shetty, Shravya
Srinivasan, Harish
Beal, Matthew
Srihari, Sargur
[J]. DOCUMENT RECOGNITION AND RETRIEVAL XIV, 2007, 6500
[34] 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
[35] INFINET: FULLY CONVOLUTIONAL NETWORKS FOR INFANT BRAIN MRI SEGMENTATION
Kumar, Shubham
Conjeti, Sailesh
Roy, Abhijit Guha
Wachinger, Christian
Navab, Nassir
[J]. 2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018), 2018, : 145 - 148
[36] SEGMENTATION LABEL PROPAGATION USING DEEP CONVOLUTIONAL NEURAL NETWORKS AND DENSE CONDITIONAL RANDOM FIELD
Gao, Mingchen
Xu, Ziyue
Lu, Le
Wu, Aaron
Nogues, Isabella
Summers, Ronald M.
Mollura, Daniel J.
[J]. 2016 IEEE 13TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2016, : 1265 - 1268
[37] Effective Semantic Pixel labelling with Convolutional Networks and Conditional Random Fields
Paisitkriangkrai, Sakrapee
Sherrah, Jamie
Janney, Pranam
Hengel, Anton Van-Den
[J]. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2015,
[38] Fully automatic person segmentation in unconstrained video using spatio-temporal conditional random fields
Bhole, Chetan
Pal, Christopher
[J]. IMAGE AND VISION COMPUTING, 2016, 51 : 58 - 68
[39] Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks
Sugino, Takaaki
Kawase, Toshihiro
Onogi, Shinya
Kin, Taichi
Saito, Nobuhito
Nakajima, Yoshikazu
[J]. HEALTHCARE, 2021, 9 (08)
[40] Accurate Estimation of Left Ventricle Ejection Fraction Using Fully Convolutional Networks and Fully Connected Conditional Random Field
Liu, Xiaoming
Lei, Zhen
He, Kan
Zhang, Huimao
Guo, Shuxu
Zhang, Xindong
Li, Xueyan
[J]. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2019, 31 (03): : 431 - 438

← 1 2 3 4 5 →