[1]冉梅子,胡小军,姜晓燕,等.基于多尺度特征融合与注意力的肝脏分割方法[J].中国医学物理学杂志,2024,41(6):739-746.[doi:DOI:10.3969/j.issn.1005-202X.2024.06.012]
　RAN Meizi,HU Xiaojun,JIANG Xiaoyan,et al.Liver segmentation method based on multi-scale feature fusion and attention[J].Chinese Journal of Medical Physics,2024,41(6):739-746.[doi:DOI:10.3969/j.issn.1005-202X.2024.06.012]
点击复制

基于多尺度特征融合与注意力的肝脏分割方法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第6期
页码:
739-746
栏目:
医学影像物理
出版日期:
2024-06-25

文章信息/Info

Title:
Liver segmentation method based on multi-scale feature fusion and attention
文章编号:
1005-202X（2024）06-0739-08
作者:
冉梅子1; 胡小军2; 姜晓燕1; 范应方2; 王航1; 王海玲1; 高永彬1
1.上海工程技术大学电子电气工程学院， 上海 201620； 2.南方医科大学第五附属医院肝胆外科， 广东 广州 510000
Author(s):
RAN Meizi1;  HU Xiaojun2;  JIANG Xiaoyan1;  FAN Yingfang2;  WANG Hang1;  WANG Hailing1;  GAO Yongbin1
1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China 2. Department of Hepatobiliary Surgery, the Fifth Affiliated Hospital of Southern Medical University, Guangzhou 510000, China
关键词:
肝脏分割; 注意力机制; 多尺度特征融合; 深度监督; MFFA UNet
Keywords:
Keywords: liver segmentation attention mechanism multi-scale feature fusion deep supervision MFFA UNet
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2024.06.012
文献标志码:
A
摘要:
由于CT影像对比度低、肝脏形状不规则、相邻器官边界模糊，目前基于卷积神经网络的方法在肝脏分割任务上的表现不佳，尤其是在边界识别和小目标检测方面。基于此，提出一种基于多尺度特征融合与注意力的肝脏分割方法（MFFA UNet）。首先，利用多尺度特征融合获取丰富的分割信息，同时使用空间和通道注意力机制捕获全局空间和通道间的关系。其次，通过深度监督模块充分利用中间隐藏层的输出，增强网络的学习能力，加快网络收敛速度。此外，采用一种混合损失函数，以解决类别不平衡的问题，进一步提升模型的分割效能。实验结果表明，所提出的MFFA UNet方法在公共数据集LITS上的表现超越当前主流分割网络，分割结果更接近真实值。
Abstract:
Abstract: Due to the low contrast of CT images, irregular shape of the liver, and blurred boundaries with adjacent organs, the existing methods based on convolutional neural network underperform in liver segmentation tasks, especially for boundary recognition and small object detection. A novel liver segmentation method is proposed based on multi-scale feature fusion and attention, namely MFFA UNet. Multi-scale feature fusion is firstly employed to acquire abundant segmentation details, while spatial and channel attention mechanisms are utilized to capture global spatial and inter-channel relationships. Additionally, a deep supervision module fully leverages the output of intermediate hidden layers, enhancing the learning capability of the network, which in turn accelerates the networks convergence speed. Moreover, a hybrid loss function is adopted to address the issue of class imbalance, further boosting the models segmentation efficacy. Experimental results demonstrate that the proposed MFFA UNet outperforms the prevailing segmentation networks on the public LITS dataset, producing results that are closer to the ground truth.

相似文献/References:

[1]陈津津,赵于前,邹润民.基于超限学习机的腹部CT序列图像肝脏自动分割[J].中国医学物理学杂志,2015,32(05):611.[doi:doi:10.3969/j.issn.1005-202X.2015.05.001]
[2]何兰,吴倩. 基于3D卷积神经网络的肝脏自动分割方法[J].中国医学物理学杂志,2018,35(6):680.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.012]
　HE Lan,WU Qian. Automatic liver segmentation based on three-dimensional convolutional neural network[J].Chinese Journal of Medical Physics,2018,35(6):680.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.012]
[3]蒋家良,罗勇,何奕松,等.特征区域再聚焦提升全卷积神经网络勾画较小靶区准确度[J].中国医学物理学杂志,2020,37(1):75.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.015]
　JIANG Jialiang,LUO Yong,HE Yisong,et al.Feature area refocusing for improving the accuracy of small target area segmentations by fully convolutional networks[J].Chinese Journal of Medical Physics,2020,37(6):75.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.015]
[4]莫春梅,周金治,李雪,等.基于改进U-Net的肝脏分割方法[J].中国医学物理学杂志,2021,38(5):571.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.009]
　MO Chunmei,ZHOU Jinzhi,et al.Liver segmentation method based on improved U-Net[J].Chinese Journal of Medical Physics,2021,38(6):571.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.009]
[5]周意龙,卫子然,蔡清萍,等.基于卷积神经网络胃癌分割与T分期算法[J].中国医学物理学杂志,2022,39(2):215.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.015]
　ZHOU Yilong,WEI Ziran,CAI Qingping,et al.Gastric cancer segmentation and T staging algorithm based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(6):215.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.015]
[6]李启行,廖薇.基于注意力机制的生物医学文本分类模型[J].中国医学物理学杂志,2022,39(4):518.[doi:DOI:10.3969/j.issn.1005-202X.2022.04.023]
　LI Qihang,LIAO Wei.Biomedical text classification model based on attention mechanism[J].Chinese Journal of Medical Physics,2022,39(6):518.[doi:DOI:10.3969/j.issn.1005-202X.2022.04.023]
[7]江悦莹,施一萍,翁晓俊,等.融合Vnet和边缘特征的肺结节分割算法[J].中国医学物理学杂志,2022,39(6):705.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.009]
　JIANG Yueying,SHI Yiping,WENG Xiaojun,et al.Lung nodule segmentation algorithm integrating Vnet and boundary features[J].Chinese Journal of Medical Physics,2022,39(6):705.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.009]
[8]刘雲,王一达,张成秀,等.基于深度学习结合解剖学注意力机制的肺结节良恶性分类[J].中国医学物理学杂志,2022,39(11):1441.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.019]
　LIU Yun,WANG Yida,ZHANG Chengxiu,et al.Classification of benign and malignant pulmonary nodules by deep learning with anatomy-based attention mechanism[J].Chinese Journal of Medical Physics,2022,39(6):1441.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.019]
[9]陈菁菁,李小霞,吕念祖.结合通道权重更新与密集残差金字塔空间注意力的皮肤病变分割方法[J].中国医学物理学杂志,2023,40(1):39.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.007]
　CHEN Jingjing,LI Xiaoxia,L?Nianzu,et al.Skin lesion segmentation method combining channel weight update and dense residual pyramid spatial attention[J].Chinese Journal of Medical Physics,2023,40(6):39.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.007]
[10]王振华,刘阳星,赵晓雨,等.结合上下文和注意力机制改进的视盘分割模型[J].中国医学物理学杂志,2023,40(1):47.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.008]
　WANG Zhenhua,LIU Yangxing,ZHAO Xiaoyu,et al.Optic disc segmentation model improved by contextual information and attention mechanism[J].Chinese Journal of Medical Physics,2023,40(6):47.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.008]
[11]邸敬,马帅,王国栋,等.基于改进Unet与动态阈值可变FCMSPCNN的医学图像分割[J].中国医学物理学杂志,2023,40(3):328.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.011]
　DI Jing,MA Shuai,WANG Guodong,et al.Medical image segmentation using improved Unet combined with dynamic threshold changed FCMSPCNN[J].Chinese Journal of Medical Physics,2023,40(6):328.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.011]

备注/Memo

备注/Memo:
【收稿日期】2023-10-26 【基金项目】广州市科技计划项目（202206010093）；上海市科委社会发展项目“科技创新行动计划”（21DZ1204900） 【作者简介】冉梅子，硕士研究生，研究方向：目标检测、图像分割，E-mail: ranmeizi0106@163.com 【通信作者】姜晓燕，博士，副教授，研究方向：计算机视觉、图像分割，E-mail: xiaoyan.jiang@sues.edu.cn
更新日期/Last Update: 2024-06-25