摘要
CT图像肝脏肿瘤分割是进行肝癌前期诊断、肿瘤负荷分析和放射治疗的重要前提。为实现肿瘤的精确自动分割,提出一种融合残差模块和注意力机制的深度U形网络。该网络首先在跳跃连接层中引入一条带有反卷积与激活操作的残差路径和卷积模块,实现图像特征的分离传递以及高级表征,确保跳跃连接层主要传递图像边缘信息和小目标全局信息,其次在解码路径中引入注意力机制,通过将跳跃连接层与反卷积解码获得的特征信息赋予不同权重,进一步增强肿瘤特征,抑制其他无关信息。提出方法在LiTS数据集上获得的全局Dice值高达86.71%,明显高于其他多种现有方法,且相较于其他方法,该方法对于小尺寸、对比度低、边界模糊的肿瘤具有明显的分割优势。
Liver tumor segmentation from CT image is an important prerequisite for early diagnosis,tumor burden analysis,and radiotherapy of liver cancer.To segment tumors accurately and automatically,a deep U-shaped network based on the residual block and attention mechanism is proposed.In this network,a residual path with deconvolution and activation operations together with a convolution module is first introduced in the skip connection to separate image features and obtain their high-level representation,which ensures that the skip connections mainly transmit the information of image edges and global information of small targets.Then,the attention mechanism is introduced in the decoding path to further enhance tumor feature and suppress irrelevant information by assigning different weights to the feature information obtained by skip connections and deconvolution decoding.The global Dice coefficient achieved by the proposed method on LiTS dataset is as high as 86.71%,which is obviously higher than many other existing methods.Compared with other methods,the proposed method has obvious advantages in segmenting tumors with small size,low contrast,and blurred boundaries.
作者
邸拴虎
杨文瀚
廖苗
赵于前
杨振
Di Shuanhu;Yang Wenhan;Liao Miao;Zhao Yuqian;Yang Zhen(School of Automation,Central South University,Changsha 410083,China;School of Computer Science and Engineering,Hunan University of Science and Technology,Xiangtan 411100,China)
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2022年第8期65-72,共8页
Chinese Journal of Scientific Instrument
基金
国家自然科学基金(62272161,62076256)
湖南省自然科学基金(2021JJ30275)
湖南省教育厅资助科研项目(20B239)资助
关键词
医学图像分割
深度学习
残差模块
注意力机制
肝脏肿瘤
medical image segmentation
deep learning
residual block
attention mechanism
liver tumor
作者简介
邸拴虎,分别在2010年和2013年于中南大学获得学士学位和硕士学位,现为中南大学博士研究生,主要研究方向为医学图像处理。E-mail:dish0304@163.com;通信作者:廖苗,分别在2010年、2013年和2016年于中南大学获得学士学位、硕士学位和博士学位,现为湖南科技大学副教授,主要研究方向为图像处理与模式识别。E-mail:liaomiaohi@163.com
