模式识别与人工智能
2025年4月2日 星期三   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2023, Vol. 36 Issue (2): 95-107    DOI: 10.16451/j.cnki.issn1003-6059.202302001
论文与报告 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于不确定性引导和尺度一致性的肾肿瘤图像分割方法
侯冰震1, 张桂梅1, 彭昆1
1.南昌航空大学 计算机视觉研究所 南昌 330063
Kidney Tumor Image Segmentation Method Based on Uncertainty Guidance and Scale Consistency
HOU Bingzhen1, ZHANG Guimei1, PENG Kun1
1. Institute of Computer Vision, Nanchang Hangkong University, Nanchang 330063

全文: PDF (1603 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对肾肿瘤图像分割中的边界模糊和特征丢失问题,在RAUNet(Residual Attention U-Net)的基础上,提出基于不确定性引导和尺度一致性的肾肿瘤图像分割方法.针对肾肿瘤图像边界模糊问题,在解码层引入不确定性引导模块,根据不确定性自适应分配权重,弱化错误像素点的影响,提高模型的边界定位能力.针对下采样引起的特征丢失问题,提出尺度注意力模块和特征一致性损失,利用多尺度融合策略融合不同尺度特征,并与编码器底部特征进行尺度一致性约束,缓解特征丢失问题.在公开数据集KiTS19上的肾脏和肾肿瘤的图像分割实验表明,文中方法提高肾肿瘤的分割精度.此外,由于文中方法引入不确定性引导模块,分割结果具有较好的可靠性.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
侯冰震
张桂梅
彭昆
关键词 图像分割不确定性引导尺度一致性注意力模块肾肿瘤    
Abstract:Aiming at the problems of boundary blurring and feature loss in kidney tumor image segmentation, a kidney tumor image segmentation method based on uncertainty guidance and scale consistency is proposed on the basis of residual attention U-net model. For blurred boundaries of kidney tumor images, an uncertainty guidance module is introduced into the decoding layer to allocate weights adaptively based on uncertainty. Thus, the effect of wrong pixels is reduced and the boundary localization ability of the model is improved. For the problem of feature loss caused by down-sampling, the scale attention module and feature consistency loss are proposed. The multi-scale fusion strategy is utilized to fuse features of different scales, and the scale consistency constraint is conducted with the features at the bottom of the encoder to alleviate the problem of feature loss. Finally, experiments of kidney and kidney tumor segmentation on the public dataset KiTS19 demonstrate that the proposed segmentation method greatly improves the segmentation accuracy. In addition, the segmentation results of the proposed method hold better reliability due to the uncertainty guidance module.
Key wordsImage Segmentation    Uncertainty Guidance    Scale Consistency    Attention Module    Kidney Tumor   
收稿日期: 2022-11-11     
ZTFLH: TP391.41  
基金资助:国家自然科学基金项目(No.62261039)资助
通讯作者: 张桂梅,博士,教授,主要研究方向为计算机视觉、图像处理、模式识别.E-mail:guimei.zh@163.com.   
作者简介: 侯冰震,硕士研究生,主要研究方向为计算机视觉、图像处理、模式识别.E-mail:hbz169678@163.com. 彭昆, 硕士研究生,主要研究方向为计算机视觉、图像处理、模式识别.E-mail:13077968561@163.com.
引用本文:   
侯冰震, 张桂梅, 彭昆. 基于不确定性引导和尺度一致性的肾肿瘤图像分割方法[J]. 模式识别与人工智能, 2023, 36(2): 95-107. HOU Bingzhen, ZHANG Guimei, PENG Kun. Kidney Tumor Image Segmentation Method Based on Uncertainty Guidance and Scale Consistency. Pattern Recognition and Artificial Intelligence, 2023, 36(2): 95-107.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202302001      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2023/V36/I2/95
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn