.png){kind=icon}
返回
An efficient neural network based method for medical image segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compbiomed.2013.10.029.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The aim of this research is to propose a new neural network based method for medical image segmentation. Firstly, a modified self-organizing map (SUM) network, named moving average SUM (MA-SUM), is utilized to segment medical images. After the initial segmentation stage, a merging process is designed to connect the objects of a joint cluster together. A two-dimensional (2D) discrete wavelet transform (DWT) is used to build the input feature space of the network. The experimental results show that MA-SUM is robust to noise and it determines the input image pattern properly. The segmentation results of breast ultrasound images (BUS) demonstrate that there is a significant correlation between the tumor region selected by a physician and the tumor region segmented by our proposed method. In addition, the proposed method segments X-ray computerized tomography (CT) and magnetic resonance (MR) head images much better than the incremental supervised neural network (ISNN) and SUM-based methods. (C) 2013 Elsevier Ltd. All rights reserved.
Keyword:
Artificial neural network (ANN)
Medical image segmentation
Computer aided diagnosis (CAD) systems
Pattern recognition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.3W
机构
暂无机构信息
引用论文
Prostate boundary detection in ultrasound images using biologically-inspired spiking neural network
PREAI
分享收藏The new ACR/EULAR classification criteria for RA: how are the new criteria performing in the clinic?.png)
Rheumatology
OAAI
RheumatologyIF0
OAAI分享收藏
查看更多内容