[1]张彩娣,李岳阳,崔方正,等.基于深度学习的候选结节检测算法[J].中国医学物理学杂志,2024,41(9):1177-1184.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.017]
 ZHANG Caidi,LI Yueyang,CUI Fangzheng,et al.Nodule candidate detection algorithm based on deep learning[J].Chinese Journal of Medical Physics,2024,41(9):1177-1184.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.017]
点击复制

基于深度学习的候选结节检测算法()
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9期
页码:
1177-1184
栏目:
医学人工智能
出版日期:
2024-10-25

文章信息/Info

Title:
Nodule candidate detection algorithm based on deep learning
文章编号:
1005-202X(2024)09-1177-08
作者:
张彩娣1李岳阳2崔方正2罗海驰3顾中轩2
1.江南大学附属医院呼吸内科, 江苏 无锡 214122; 2.江南大学人工智能与计算机学院, 江苏 无锡 214122; 3.江南大学物理网工程学院, 江苏 无锡 214122
Author(s):
ZHANG Caidi1 LI Yueyang2 CUI Fangzheng2 LUO Haichi3 GU Zhongxuan2
1. Department of Respiration, Affiliated Hospital of Jiangnan University, Wuxi 214122, China 2. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China 3. School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China
关键词:
候选结节检测计算机辅助检测增强坐标注意力机制模块球体损失函数
Keywords:
Keywords: nodule candidate detection computer-aided detection strengthen coordinate attention module sphere based loss function
分类号:
R318;TP391.4
DOI:
DOI:10.3969/j.issn.1005-202X.2024.09.017
文献标志码:
A
摘要:
为提高候选结节检测性能,应用深度学习技术提出基于3DSCANet的候选结节检测算法。该算法提出增强坐标注意力机制模块(SCA),在坐标注意力机制的基础上做出改进,使之能提取三维(3D)特征,并引入自适应卷积提取跨通道特征,增加SCA注意力机制的特征提取能力;提出一种将3D长方体锚框转换为3D球体的方法,并进一步引入新的球体交并比损失函数[SIoUX],以充分利用肺结节的球体形态特征。在实验阶段,该方法在LUNA16数据集上采用十折交叉验证的方法进行测试,平均召回率CPM达到0.94。
Abstract:
Abstract: A nodule candidate detection algorithm based on 3DSCANet utilizing deep learning techniques is proposed to improve nodule candidate detection performance. The algorithm employs a strengthen coordinate attention (SCA) module which improves upon the basic coordinate attention mechanism to enable it to extract three-dimensional (3D) features, and incorporates adaptive convolution to extract cross-channel features, thereby enhancing the feature extraction capability of the SCA mechanism. Additionally, a method to convert 3D rectangular anchor boxes into 3D spheres is proposed, along with the introduction of a sphere based intersection over union loss function (SIoUX) to fully leverage the morphological characteristics of lung nodules which are spherical in shape. During the experimental phase, the method is tested on the LUNA16 dataset using ten-fold cross-validation, and it achieves an average recall rate of 0.94.

相似文献/References:

[1]褚晶辉,刘静媛,吕卫,等.一种基于小波变换的乳腺X线图肿块分割方法[J].中国医学物理学杂志,2013,30(06):4519.[doi:10.3969/j.issn.1005-202X.2013.06.013]

备注/Memo

备注/Memo:
【收稿日期】2024-02-23 【基金项目】国家自然科学基金联合基金(U1836218) 【作者简介】张彩娣,硕士,主任医师,研究方向:医学图像处理、人工智能,E-mail: 15301516381@163.com 【通信作者】李岳阳,博士,副教授,研究方向:医学图像处理、人工智能,E-mail: lyueyang@jiangnan.edu.cn
更新日期/Last Update: 2024-09-26