ERV-Net: An efficient 3D residual neural network for brain tumor segmentation | |
Zhou, Xinyu1; Li, Xuanya2; Hu, Kai1; Zhang, Yuan1; Chen, Zhineng3; Gao, Xieping1,4 | |
发表期刊 | EXPERT SYSTEMS WITH APPLICATIONS |
ISSN | 0957-4174 |
2021-05-15 | |
卷号 | 170页码:13 |
通讯作者 | Hu, Kai(kaihu@xtu.edu.cn) ; Chen, Zhineng(zhineng.chen@ia.ac.cn) |
摘要 | Brain tumors are the most aggressive and mortal cancers, which lead to short life expectancy. A reliable and efficient automatic or semi-automatic segmentation method is significant for clinical practice. In recent years, deep learning-based methods achieve great success in brain tumor segmentation. However, due to the limitation of parameters and computational complexity, there is still much room for improvement in these methods. In this paper, we propose an efficient 3D residual neural network (ERV-Net) for brain tumor segmentation, which has less computational complexity and GPU memory consumption. In ERV-Net, a computation-efficient network, 3D ShuffleNetV2, is firstly utilized as encoder to reduce GPU memory and improve the efficiency of ERV-Net, and then the decoder with residual blocks (Res-decoder) is introduced to avoid degradation. Furthermore, a fusion loss function, which is composed of Dice loss and Cross-entropy loss, is developed to solve the problems of network convergence and data imbalance. Moreover, a concise and effective post-processing method is proposed to refine the coarse segmentation result of ERV-Net. The experimental results on the dataset of multimodal brain tumor segmentation challenge 2018 (BRATS 2018) demonstrate that ERV-Net achieves the best performance with Dice of 81.8%, 91.21% and 86.62% and Hausdorff distance of 2.70 mm, 3.88 mm and 6.79 mm for enhancing tumor, whole tumor and tumor core, respectively. Besides, ERV-Net also achieves high efficiency compared to the state-of-the-art methods. |
关键词 | Brain tumor segmentation 3D convolutional neural network Encoder-decoder Efficiency Lightweight Residual block |
DOI | 10.1016/j.eswa.2021.114566 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61802328] ; National Natural Science Foundation of China[61972333] ; National Natural Science Foundation of China[61771415] ; Natural Science Foundation of Hunan Province of China[2019JJ50606] ; Research Foundation of Education Department of Hunan Province of China[19B561] ; Baidu Pinecone Program |
项目资助者 | National Natural Science Foundation of China ; Natural Science Foundation of Hunan Province of China ; Research Foundation of Education Department of Hunan Province of China ; Baidu Pinecone Program |
WOS研究方向 | Computer Science ; Engineering ; Operations Research & Management Science |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science |
WOS记录号 | WOS:000633042500007 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
七大方向——子方向分类 | 人工智能+医疗 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44135 |
专题 | 数字内容技术与服务研究中心_远程智能医疗 |
通讯作者 | Hu, Kai; Chen, Zhineng |
作者单位 | 1.Xiangtan Univ, Minist Educ, Key Lab Intelligent Comp & Informat Proc, Xiangtan 411105, Peoples R China 2.Baidu Inc, Beijing 100085, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 4.Xiangnan Univ, Coll Med Imaging & Inspect, Chenzhou, Peoples R China |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhou, Xinyu,Li, Xuanya,Hu, Kai,et al. ERV-Net: An efficient 3D residual neural network for brain tumor segmentation[J]. EXPERT SYSTEMS WITH APPLICATIONS,2021,170:13. |
APA | Zhou, Xinyu,Li, Xuanya,Hu, Kai,Zhang, Yuan,Chen, Zhineng,&Gao, Xieping.(2021).ERV-Net: An efficient 3D residual neural network for brain tumor segmentation.EXPERT SYSTEMS WITH APPLICATIONS,170,13. |
MLA | Zhou, Xinyu,et al."ERV-Net: An efficient 3D residual neural network for brain tumor segmentation".EXPERT SYSTEMS WITH APPLICATIONS 170(2021):13. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论