[1]袁红杰,杨艳,张东,等.基于多监督注意力机制神经网络的脑胶质瘤循环肿瘤细胞分割算法[J].中国医学物理学杂志,2022,39(7):828-833.[doi:DOI:10.3969/j.issn.1005-202X.2022.07.007]
　YUAN Hongjie,YANG Yan,ZHANG Dong,et al.Neural network-based multi-level supervision and attention mechanism algorithm for brain glioma CTC segmentation[J].Chinese Journal of Medical Physics,2022,39(7):828-833.[doi:DOI:10.3969/j.issn.1005-202X.2022.07.007]
点击复制

基于多监督注意力机制神经网络的脑胶质瘤循环肿瘤细胞分割算法()
分享到：

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

卷:
39卷
期数:
2022年第7期
页码:
828-833
栏目:
医学影像物理
出版日期:
2022-07-15

文章信息/Info

Title:
Neural network-based multi-level supervision and attention mechanism algorithm for brain glioma CTC segmentation
文章编号:
1005-202X（2022）07-0828-06
作者:
袁红杰1; 杨艳1; 张东1; 杨双1; 2
1.武汉大学物理科学与技术学院， 湖北 武汉 430072； 2.桂林航天工业学院电子信息与自动化学院， 广西 桂林 541004
Author(s):
YUAN Hongjie1;  YANG Yan1;  ZHANG Dong1;  YANG Shuang1;  2
1. School of Physics and Technology, Wuhan University, Wuhan 430072, China 2. School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin 541004, China
关键词:
脑胶质瘤; 循环肿瘤细胞; 多监督; 卷积块注意力机制模块; 小目标分割
Keywords:
Keywords: glioma circulating tumor cell multi-level supervision convolutional block attention module small target segmentation
分类号:
R318；TP391
DOI:
DOI:10.3969/j.issn.1005-202X.2022.07.007
文献标志码:
A
摘要:
为了提升脑胶质瘤循环肿瘤细胞的分割准确率，解决人工分割中肉眼分辨边界困难、目标占比小和操作流程繁琐等问题，提出一种端到端的像素级分割算法。针对数据特征，提出一种基于多监督机制的混合损失函数用以提升预测区域与目标区域的交并比，同时训练网络向预测正确目标个数的方向收敛；其次，在网络中逐层加入卷积块注意力机制模块，使得网络能在空间、通道层面重点学习数据特征，进一步提升预测准确率；最后，通过采用混合训练的方式，只需一个网络模型就能直接分割出细胞核、细胞质区域，缩减训练流程。实验结果表明，此分割算法对比U-Net网络在召回率、精确率以及Dice系数方面均有显著提升，在细胞核分割方面，分别达到92.20%、86.56%、88.27%；在细胞质分割方面，分别达到89.33%、85.31%、86.33%。
Abstract:
Abstract: In order to improve the segmentation accuracy of glioma circulating tumor cells (CTC) and solve the problems of difficulties in distinguishing boundaries with the naked eye, small target ratio and cumbersome operation process in manual segmentation, an end-to-end pixel-level segmentation algorithm is proposed. In view of data features, the proposed algorithm utilizes a hybrid loss function based on a multi-level supervision mechanism to improve the intersection-over-union between the prediction area and the ground truth area, and iterate the network converging in the direction of predicting the right numbers of targets. Then, the convolutional block attention module is put in every layer of the proposed network enables the network to focus on learning data features at the spatial and channel dimensions, thereby further improving the prediction accuracy. Finally, the proposed algorithm can segment the nucleus and cytoplasm by one network model through hybrid training, which simples the process of training. The experimental results showed that compared with U-Net network, the proposed segmentation algorithm has improved in terms of recall rate, precision and Dice coefficient. The above-mentioned indexes are 92.20%, 86.56%, 88.27% for cell nucleus segmentation, and 89.33%, 85.31%, 86.33% for cytoplasm segmentation.

相似文献/References:

[1]周 钢,田 野,陆雪官,等.同步加量技术应用于脑胶质瘤术后调强放疗的剂量学研究[J].中国医学物理学杂志,2014,31(02):4727.[doi:10.3969/j.issn.1005-202X.2014.02.002]
[2]颜识涵,姚春艳. 太赫兹光谱技术挑战检测循环肿瘤细胞难题[J].中国医学物理学杂志,2016,33(12):1225.[doi:10.3969/j.issn.1005-202X.2016.12.009]
　[J].Chinese Journal of Medical Physics,2016,33(7):1225.[doi:10.3969/j.issn.1005-202X.2016.12.009]
[3]戴红娅,黄江华,陈露,等. RapidArc和IMRT在脑胶质瘤术后放疗中保护海马的剂量学比较[J].中国医学物理学杂志,2018,35(12):1404.[doi:DOI:10.3969/j.issn.1005-202X.2018.12.007]
　DAI Hongya,HUANG Jianghua,CHEN Lu,et al. Dosimetric comparison of RapidArc and IMRT in hippocampus sparing during postoperative radiotherapy for glioma[J].Chinese Journal of Medical Physics,2018,35(7):1404.[doi:DOI:10.3969/j.issn.1005-202X.2018.12.007]
[4]王正源,徐秀林,王燕. 基于微流体技术分选循环肿瘤细胞的方法研究[J].中国医学物理学杂志,2019,36(2):229.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.020]
　WANG Zhengyuan,XU Xiulin,WANG Yan. Microfluidic technology-based method for sorting circulating tumor cells[J].Chinese Journal of Medical Physics,2019,36(7):229.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.020]
[5]郭飞宝.高分级脑胶质瘤4种同步加量调强放射治疗的剂量学分析[J].中国医学物理学杂志,2019,36(12):1396.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.006]
　GUO Feibao.Dosimetric analysis of 4 types of simultaneous integrated boost radiotherapy for high-grade glioma[J].Chinese Journal of Medical Physics,2019,36(7):1396.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.006]
[6]段欢欢,李书舟,曹瑛,等.基于深度学习方法预测IMRT计划射野的γ通过率[J].中国医学物理学杂志,2021,38(6):677.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.004]
　. School of Nuclear Science and Technology,University of South China,Hengyang 00,et al.Predicting gamma passing rates for intensity-modulated radiotherapy fields based on deep learning method[J].Chinese Journal of Medical Physics,2021,38(7):677.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.004]
[7]黄唯,徐中标,邓官华,等.MRI拉莫尔频率范围内人体脑胶质瘤组织的介电特性[J].中国医学物理学杂志,2021,38(12):1538.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.015]
　HUANG Wei,XU Zhongbiao,DENG Guanhua,et al.Dielectric properties of human glioma tissue at Larmor frequencies in MRI[J].Chinese Journal of Medical Physics,2021,38(7):1538.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.015]
[8]张珂,张陶冶,黄慧明.基于明胶膜基底捕获和原位培养循环肿瘤细胞[J].中国医学物理学杂志,2021,38(12):1549.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.017]
　ZHANG Ke,ZHANG Taoye,HUANG Huiming.Capture and culture in situ of circulating tumor cells based on gelatin film substrate[J].Chinese Journal of Medical Physics,2021,38(7):1549.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.017]
[9]郭冰冰,胡秀枋,宋子玥,等.循环肿瘤细胞检测仪的结构设计与功能分析[J].中国医学物理学杂志,2022,39(5):604.[doi:DOI:10.3969/j.issn.1005-202X.2022.05.014]
　GUO Bingbing,HU Xiufang,SONG Ziyue,et al.Structural design and functional analysis of an apparatus for detection of circulating tumor cells[J].Chinese Journal of Medical Physics,2022,39(7):604.[doi:DOI:10.3969/j.issn.1005-202X.2022.05.014]
[10]王瑞,刘志强,齐崇,等.基于3D深度残差网络和多模态MRI的脑胶质瘤自动分级[J].中国医学物理学杂志,2022,39(10):1236.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.010]
　WANG Rui,LIU Zhiqiang,QI Chong,et al.Automated glioma grading based on 3D deep residual network and multimodal MRI[J].Chinese Journal of Medical Physics,2022,39(7):1236.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.010]

备注/Memo

备注/Memo:
【收稿日期】2022-02-26 【基金项目】国家重点研发计划973项目（2011CB707900） 【作者简介】袁红杰，硕士，研究方向：医学图像处理，E-mail: hongj_yuan@163.com
更新日期/Last Update: 2022-07-15