Brain Tumor Segmentation using Automatic 3D Multi-channel Feature Selection Convolutional Neural Network

Chengxiang Shan; Qiang Li; Ching-Hsin Wang

首页> 外文期刊>Journal of Imaging Science and Technology >Brain Tumor Segmentation using Automatic 3D Multi-channel Feature Selection Convolutional Neural Network

【24h】

Brain Tumor Segmentation using Automatic 3D Multi-channel Feature Selection Convolutional Neural Network

机译：Brain Tumor Segmentation using Automatic 3D Multi-channel Feature Selection Convolutional Neural Network

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Brain tumor segmentation is an important topic in medical image processing. Three-dimensional (3D) convolutional neural networks (CNN) make full use of feature information and have better segmentation performance. However, conventional 3D CNNs involve a significant number of parameters and has high hardware requirements, which is not conducive to clinical application. To solve these issues, this study proposes a lightweight highly-efficient 3D CNN for brain tumor magnetic resonance imaging segmentation. We first replaced the conventional CNN with improved depth-wise CNN to save computational resources. Next, we employed a multi-channel convolution approach using convolution kernels of different sizes to aggregate features from different receptive fields. Finally, we used a squeeze-and-excitation unit to automatically extract useful feature information in the network. Application of the proposed model to the Bra TS2019 validation set resulted in mean Dice scores of 0.9053, 0.8373, and 0.7847, with regard to whole tumor, tumor core, and enhanced tumor, respectively. This was achieved with 2.01 M parameters and 24.68 G floating point operations, and data training used 2.75 GB of video memory. The differences between our Dice scores and those derived using the network developed by the winner of the Bra TS2019 challenge were only 0.0041, 0.0174, and 0.0274. Furthermore, the number of parameters and floating point operations were 2.3 times and 8.1 times lower and data training used 4 times lower video memory than the winning network. This indicates that the proposed network offers a higher precision for brain tumor segmentation while reducing computational requirements and effectively lowering hardware requirements for clinical applications.

著录项

来源
《Journal of Imaging Science and Technology》 |2022年第6期|60502.1-60502.9|共9页
作者
Chengxiang Shan; Qiang Li; Ching-Hsin Wang;
展开▼
作者单位

School of Microelectronics, Tianjin University, Tianjin, 300072, China;

Department of Leisure Industry Management, National Chin-Yi University of Technology, Taiwan Institute of Innovation and Circular Economy, Asia University, Taiwan;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词

Brain Tumor Segmentation using Automatic 3D Multi-channel Feature Selection Convolutional Neural Network

摘要

著录项

相关主题

期刊订阅