[1]谢绍鹏,王明泉,耿宇杰,等.基于全尺度通道特征聚合编解码网络的肺结节分割算法[J].中国医学物理学杂志,2024,41(12):1501-1508.[doi:DOI:10.3969/j.issn.1005-202X.2024.12.007]
　XIE Shaopeng,WANG Mingquan,GENG Yujie,et al.Lung nodule segmentation algorithm based on full-scale channel feature aggregation coding and decoding network[J].Chinese Journal of Medical Physics,2024,41(12):1501-1508.[doi:DOI:10.3969/j.issn.1005-202X.2024.12.007]
点击复制

基于全尺度通道特征聚合编解码网络的肺结节分割算法()
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12期
页码:
1501-1508
栏目:
医学影像物理
出版日期:
2024-12-17

文章信息/Info

Title:
Lung nodule segmentation algorithm based on full-scale channel feature aggregation coding and decoding network
文章编号:
1005-202X（2024）12-1501-08
作者:
谢绍鹏; 王明泉; 耿宇杰; 黄心玥; 商然
中北大学信息与通信工程学院， 山西 太原 030051
Author(s):
XIE Shaopeng;  WANG Mingquan;  GENG Yujie;  HUANG Xinyue;  SHANG Ran
School of Information and Communication Engineering, North University of China, Taiyuan 030051, China
关键词:
肺结节分割; 全尺度跳跃连接; 双项限制损失函数; 空洞卷积
Keywords:
Keywords: lung nodule segmentation full-scale skip connection binomial constraint loss function dilated convolution
分类号:
R318；TP391.41
DOI:
DOI:10.3969/j.issn.1005-202X.2024.12.007
文献标志码:
A
摘要:
针对不同性质下肺结节难以精准检测的难题，提出全尺度通道特征聚合编解码网络（FCFA-Net）去辅助经验丰富的医师进行诊断。本网络由SMC、全尺度特征聚合器、自相关特征增强器、通道特征层级提取解码器以及双项限制损失函数构成，用于充分提取CT图像中的浅层与深层特征，以达到分割大小各异、形状各异的肺结节病灶。本文方法FCFA-Net网络相较于UNet、UNet++和TransUnet方法精准率分别提升9.66%、7.84%、3.75%，召回率提升5.50%、2.96%、1.37%，均交并比提升11.35%、7.16%、4.18%，F1分数提升8.07%、5.87%、3.10%，且消融实验表明各个结构均发挥作用，在参数接受范围内达到最佳效果。
Abstract:
Abstract: To address the difficulty in accurately detecting pulmonary nodules of different properties, a full-scale channel feature aggregation encoding and decoding network (FCFA-Net) is employed to assist experienced physicians in diagnosis. The network which consists of SMC, full-scale feature aggregator, autocorrelation feature enhancer, channel feature hierarchy extraction decoder and binomial constraint loss function can fully extract shallow and deep features from CT images for realizing the segmentation of pulmonary nodules of different sizes and shapes. Compared with UNet, UNet++ and TransUnet, FCFA-Net increases the accuracy by 9.96%, 7.84% and 3.75%, recall rate by 5.50%, 2.96% and 1.37%, mean intersection over union by 11.35%, 7.16% and 4.18%, F1 score by 8.07%, 5.87% and 3.10%, respectively. Additionally, ablation experiment results demonstrate that each structure is effective and can achieve the best result within the acceptable parameter range.

相似文献/References:

[1]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(12):705.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.009]
[2]刘方,孙鹏,陈真诚.基于3DV-Net的肺结节检测分割算法[J].中国医学物理学杂志,2023,40(1):77.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.013]
　LIU Fang,SUN Peng,CHEN Zhencheng.Detection and segmentation of pulmonary nodules using improved 3DV-Net[J].Chinese Journal of Medical Physics,2023,40(12):77.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.013]

备注/Memo

备注/Memo:
【收稿日期】2024-07-27 【基金项目】国家自然科学基金（61171177）；国家重大科学仪器设备开发项目（2013YQ240803）；山西省重点研发计划（201803D121069）；山西省高等学校科技创新项目（2020L0624）；山西省信息探测与处理重点实验室基金（ISPT-2020-5） 【作者简介】谢绍鹏，硕士研究生，研究方向：图像处理与人工智能，E-mail: 2090117685@qq.com 【通信作者】王明泉，教授，博士，研究方向：智能信息处理、图像处理与信息反演等，E-mail: 3087378457@qq.com
更新日期/Last Update: 2024-12-20