[1]陈杰,陈金令,陆浩,等.自适应特征融合和条件随机场的乳腺病理图像诊断算法[J].中国医学物理学杂志,2024,41(4):433-438.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.006]
 CHEN Jie,CHEN Jinling,LU Hao,et al.Breast pathological image diagnosis algorithm incorporating adaptive feature fusion and conditional random field[J].Chinese Journal of Medical Physics,2024,41(4):433-438.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.006]
点击复制

自适应特征融合和条件随机场的乳腺病理图像诊断算法()
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4期
页码:
433-438
栏目:
医学影像物理
出版日期:
2024-04-25

文章信息/Info

Title:
Breast pathological image diagnosis algorithm incorporating adaptive feature fusion and conditional random field
文章编号:
1005-202X(2024)04-0433-06
作者:
陈杰1陈金令1陆浩1陈百合1唐卓葳2
1.西南石油大学电气信息学院, 四川 成都 610500; 2.绵阳中心医院/电子科技大学医学院附属绵阳医院, 四川 绵阳 621000
Author(s):
CHEN Jie1 CHEN Jinling1 LU Hao1 CHEN Baihe1 TANG Zhuowei2
1. School of Electrical Engineering and Information, Southwest Petroleum University, Chengdu 610500, China 2. Mianyang Central Hospital/Affiliated Mianyang Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang 621000, China
关键词:
乳腺图像处理自适应特征融合条件随机场病理切片
Keywords:
Keywords: breast image processing adaptive feature fusion conditional random field pathological slice
分类号:
R318;TP391.4
DOI:
DOI:10.3969/j.issn.1005-202X.2024.04.006
文献标志码:
A
摘要:
肿瘤病理学分析是常见的癌症诊断方法之一。基于深度学习的病理检测方法取得了良好性能,然而针对组织切片的处理方法往往会忽略病理组织空间相关性,为了更加准确地获取乳腺癌分类结果和恶性肿瘤位置信息,提出嵌入自适应特征融合模块和均值条件随机场的Transformer框架,利用反向传播算法端到端地训练整个框架。自适应特征融合模块采用可学习参数将改进的自注意力和多感受野卷积模块自适应结合,获取多尺度语义特征,从全局和局部的角度增强模型特征提取能力;提出均值条件随机场与主干网络结合,整合组织切片间的空间相关性,获取病理组织间的形态学信息。实验结果表明:所提方法在切片级图像上准确率高达95.51%,在全切片扫描图像的AUC、FROC分别为0.974 5、0.810 2,有较好的可行性,提高了病理图像分类临床诊断准确率。
Abstract:
Abstract: Pathological analysis is one of the common methods for cancer diagnosis. Although pathological examination based on deep learning exhibits good performance, the processing method for tissue slices tends to ignore the spatial correlation of pathological tissues. In order to obtain breast cancer classification results and malignant tumor location more accurately, a Transformer framework embedded with adaptive feature fusion module and mean value conditional random field is proposed, and the whole framework is trained end-to-end using back propagation algorithm. The adaptive feature fusion module uses learnable parameters to combine the improved self-attention and multi receptive field convolution module adaptively for obtaining multi-scale semantic features and enhancing the model feature extraction capability from both global and local perspectives. The proposed mean value conditional random field is combined with the backbone network to integrate the spatial correlation between tissue slices and obtain morphological information between pathological tissues. Experimental results show that the proposed method yields 95.51% accuracy on slice images, and achieves 0.974 5 AUC and 0.810 2 FROC on whole-slice images, demonstrating its feasibility and higher diagnostic accuracy for pathological image classification.

相似文献/References:

[1]乔庆玲,卢 玫.基于红外乳腺检测的体表温度分布[J].中国医学物理学杂志,2015,32(03):332.[doi:10.3969/j.issn.1005-202X.2015.03.007]
[2]田 龙,李明辉,胡逸民,等.利用EPID图像金球位置自动跟踪算法研究[J].中国医学物理学杂志,2014,31(04):5038.[doi:10.3969/j.issn.1005-202X.2014.04.014]
[3]刘玉红,王志芳,杨佳仪,等.彩色图像二值化算法及应用[J].中国医学物理学杂志,2013,30(01):3873.[doi:10.3969/j.issn.1005-202X.2013.01.009]
[4]蔡冬鹭,蔡思清,颜丽笙,等.数字乳腺三维断层摄影剂量控制[J].中国医学物理学杂志,2015,32(05):702.[doi:doi:10.3969/j.issn.1005-202X.2015.05.020]
[5]车琳琳,翟代庆,鲁雯,等.乳腺良恶性病变的影像学特征[J].中国医学物理学杂志,2016,33(10):973.[doi:10.3969/j.issn.1005-202X.2016.10.001]
 [J].Chinese Journal of Medical Physics,2016,33(4):973.[doi:10.3969/j.issn.1005-202X.2016.10.001]
[6]杜永兴,桑路路,秦岭,等.一种基于图像匹配的微波热疗方法[J].中国医学物理学杂志,2016,33(10):1026.[doi:10.3969/j.issn.1005-202X.2016.10.011]
 [J].Chinese Journal of Medical Physics,2016,33(4):1026.[doi:10.3969/j.issn.1005-202X.2016.10.011]
[7]朱翔宇,葛中芹,张冰清,等.基于图像处理的医学影像处理平台系统设计[J].中国医学物理学杂志,2017,34(4):388.[doi:DOI:10.3969/j.issn.1005-202X.2017.04.014]
[8]孟爽,王辉,谢蓄芬,等.超像素有偏观测模糊聚类的乳腺超声图像分割[J].中国医学物理学杂志,2017,34(7):693.[doi:10.3969/j.issn.1005-202X.2017.07.009]
 [J].Chinese Journal of Medical Physics,2017,34(4):693.[doi:10.3969/j.issn.1005-202X.2017.07.009]
[9]金京,孟雅丹,徐琦,等.二维分形维数在皮肤癌光学相干断层成像技术诊断中的应用[J].中国医学物理学杂志,2017,34(7):698.[doi:10.3969/j.issn.1005-202X.2017.07.010]
 [J].Chinese Journal of Medical Physics,2017,34(4):698.[doi:10.3969/j.issn.1005-202X.2017.07.010]
[10]王耿媛,赖官铨,段铮昱,等. 基于裂隙灯的眼微血管形态学参数分析在眼科疾病诊断的应用[J].中国医学物理学杂志,2018,35(3):323.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.014]
 WANG Gengyuan,LAI Guanquan,DUAN Zhengyu,et al. Application of morphological parameters analysis of ophthalmic microvasculature based on slit lamp in the diagnosis of ophthalmic diseases[J].Chinese Journal of Medical Physics,2018,35(4):323.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.014]

备注/Memo

备注/Memo:
【收稿日期】2023-10-21 【基金项目】四川省重点研发计划(重大科技专项)项目(2022YFS0020);四川省卫生健康委员会临床研究项目(23LCYJ020);南充市市校科技战略合作专项(22SXQT0292) 【作者简介】陈杰,硕士,研究方向:医学图像处理、模式识别、目标检测,E-mail: 202121000155@stu.swpu.edu.cn 【通信作者】陈金令,博士,教授,研究方向:深度学习和医学图像处理,E-mail: 201899010004@swpu.edu.cn
更新日期/Last Update: 2024-04-25