Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (2): 343-349.DOI: 10.11772/j.issn.1001-9081.2020050725

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Semantic segmentation method based on edge attention model

SHE Yulong1,2,3, ZHANG Xiaolong1,2,3, CHENG Ruoqin4, DENG Chunhua1,2,3   

  1. 1. School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430065, China;
    2. Institute of Big Data Science and Engineering, Wuhan University of Science and Technology, Wuhan Hubei 430065, China;
    3. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System(Wuhan University of Science and Technology), Wuhan Hubei 430065, China;
    4. Tianyou Hospital Affiliated to Wuhan University of Science and Technology, Wuhan Hubei 430064, China
  • Received:2020-06-01 Revised:2020-07-19 Online:2021-02-10 Published:2020-08-14
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61972299, U1803262, 61702381).

基于边缘关注模型的语义分割方法

佘玉龙1,2,3, 张晓龙1,2,3, 程若勤4, 邓春华1,2,3   

  1. 1. 武汉科技大学 计算机科学与技术学院, 武汉 430065;
    2. 武汉科技大学 大数据科学与工程研究院, 武汉 430065;
    3. 智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学), 武汉 430065;
    4. 武汉科技大学附属天佑医院, 武汉 430064
  • 通讯作者: 张晓龙
  • 作者简介:佘玉龙(1995-),男,湖北孝感人,硕士研究生,主要研究方向:计算机视觉、深度学习;张晓龙(1963-),男,江西吉安人,教授,博士,主要研究方向:人工智能、机器学习、数据挖掘、生物信息处理;程若勤(1955-),男,湖北武汉人,主任医师,主要研究方向:消化系统、呼吸系统及中枢神经系统的影像学诊断;邓春华(1984-),男,湖南郴州人,副教授,博士,主要研究方向:计算机视觉、机器学习。
  • 基金资助:
    国家自然科学基金资助项目(61972299, U1803262, 61702381)。

Abstract: Liver is the main organ of human metabolic function. At present, the main problems of machine learning in the semantic segmentation of liver images are as follows:1) there are inferior vena cava, soft tissue and blood vessels in the middle of the liver, and even some necrosis or hepatic fissures; 2) the boundary between the liver and some adjacent organs is blurred and difficult to distinguish. In order to solve the problems mentioned above, the Edge Attention Model (EAM)and the Edge Attention Net (EANet) were proposed by using Encoder-Decoder framework. In the encoder, the residual network ResNet34 pre-trained on ImageNet and the EAM were utilized, so as to fully obtain the detailed feature information of liver edge; in the decoder, the deconvolution operation and the proposed EAM were used to perform the feature extraction to the useful information, thereby obtaining the semantic segmentation diagram of liver image. Finally, the smoothing was performed to the segmentation images with a lot of noise. Comparison experiments with AHCNet were conducted on three datasets, and the results showed that:on 3Dircadb dataset, the Volumetric Overlap Error (VOE) and Relative Volume Difference (RVD) of EANet were decreased by 1.95 percentage points and 0.11 percentage points respectively, and the DICE accuracy was increased by 1.58 percentage points; on Sliver07 dataset, the VOE, Maximum Surface Distance (MSD) and Root Mean Square Surface Distance (RMSD) of EANet were decreased approximately by 1 percentage points, 3.3 mm and 0.2 mm respectively; on clinical MRI liver image dataset of a hospital, the VOE and RVD of EANet were decreased by 0.88 percentage points and 0.31 percentage points respectively, and the DICE accuracy was increased by 1.48 percentage points. Experimental results indicate that the proposed EANet has good segmentation effect of liver image.

Key words: medical liver image, semantic segmentation, feature extraction, residual network, Volumetric Overlap Error (VOE), Relative Volume Difference (RVD)

摘要: 肝脏是人体代谢功能的主要器官,目前机器学习在肝脏影像语义分割研究中的难点有:1)肝脏中间部位有下腔静脉、软组织和血管,甚至有坏死或肝裂等情况;2)肝脏与一些邻近器官之间的边界模糊,难以分辨。针对这些问题,提出了边缘关注模型(EAM)及边缘关注网络(EANet)。该网络采用了Encoder-Decoder(编码-解码)的模型框架:在编码器中运用了在ImageNet上预训练好的残差网络ResNet34和EAM,由此来充分获取肝脏边缘的细节特征信息;在解码器中则运用了反卷积操作和EAM对有效信息进行特征提取,进而得到肝脏影像的语义分割图。最后,对分割后噪声较大的图片实施了平滑处理。在三个数据集上与AHCNet进行对比,结果显示:在3Dircadb数据集上,EANet的体积重叠误差(VOE)和相对体积差异(RVD)分别降低了1.95个百分点和0.11个百分点,且DICE精度提高了1.58个百分点;在Sliver07数据集上,EANet的VOE、最大表面距离(MSD)和均方差对称表面距离(RMSD)分别降低了大约1个百分点、3.3 mm和0.2 mm;在某医院临床MRI肝脏影像数据集上,EANet的VOE和RVD分别降低了0.88个百分点和0.31个百分点,且DICE精度提高了1.48个百分点。实验结果表明,所提出的EANet具有较好的肝脏图像分割效果。

关键词: 医学肝脏影像, 语义分割, 特征提取, 残差网络, 体积重叠误差, 相对体积差异

CLC Number: