[1]梁楠,赵政辉,周依,等.基于滑动块的深度卷积神经网络乳腺X线摄影图像肿块分割算法[J].中国医学物理学杂志,2020,37(12):1513-1519.[doi:DOI:10.3969/j.issn.1005-202X.2020.12.008]
　LIANG Nan,ZHAO Zhenghui,et al.An algorithm of mass segmentation in mammogram by using deep convolutional neural network based on sliding patch[J].Chinese Journal of Medical Physics,2020,37(12):1513-1519.[doi:DOI:10.3969/j.issn.1005-202X.2020.12.008]
点击复制

基于滑动块的深度卷积神经网络乳腺X线摄影图像肿块分割算法()
分享到：

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

卷:
37
期数:
2020年第12期
页码:
1513-1519
栏目:
医学影像物理
出版日期:
2020-12-30

文章信息/Info

Title:
An algorithm of mass segmentation in mammogram by using deep convolutional neural network based on sliding patch
文章编号:
1005-202X（2020）12-1513-07
作者:
梁楠1; 2; 赵政辉3; 4; 周依5; 武博1; 2; 李长波5; 于鑫3; 马思伟3; 张楠1; 2
1.首都医科大学生物医学工程学院， 北京 100069； 2.首都医科大学临床生物力学应用基础研究北京市重点实验室， 北京 100069； 3.北京大学数字媒体所， 北京 100871； 4.北京大学数学与应用数学实验室， 北京 100871； 5.河南大学影像研究所淮河医院放射科， 河南 开封 475000
Author(s):
LIANG Nan1;  2;  ZHAO Zhenghui3;  4;  ZHOU Yi5;  WU Bo1;  2;  LI Changbo5;  YU Xin3;  MA Siwei3;  ZHANG Nan1;  2
1. School of Biomedical Engineering, Capital Medical University, Beijing 100069, China 2. Beijings Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing 100069, China 3. Institute of Digital Media, Peking University, Beijing 100871, China 4. Laboratory of Mathematics and Applied Mathematics, Peking University, Beijing 100871, China 5. Department of Radiology, Huaihe Hospital, Institute of Medical Imaging of Henan University, Kaifeng 475000, China
关键词:
乳腺X线摄影图像; 乳腺肿块; 滑动块; 深度卷积神经网络; 图像分割
Keywords:
Keywords: mammogram images breast mass sliding patch deep convolutional neural network image segmentation
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2020.12.008
文献标志码:
A
摘要:
目的：提出一种基于滑动块的深度卷积神经网络局部分类、整图乳腺肿块分割的算法，为临床诊断提供有效的肿块形态特征。方法：首先通过区域生长算法和膨胀算法提取患者乳腺区域，并进行数据归一化操作。为了得到每一个像素位置上的诊断信息，在图像的对应位置中滑动提取肿块类及非肿块类图像块，根据卷积神经网络提取其中的纹理信息并对图像块进行分类。通过整合图像块的预测分类结果，进行由粗到细的肿块分割，获得乳腺整图中像素级别的肿块分割。结果：通过比较先进的深度卷积神经网络模型，本文算法滑动块分类结果DenseNet模型下准确率达到96.71%，乳腺X线摄影图像全图肿块分割结果F1-score最优为83.49%。结论：本算法可以分割出乳腺X线摄影图像中的肿块，为后续的乳腺病灶诊断提供可靠的基础。
Abstract:
Abstract: Objective An algorithm which includes local patch classification and breast mass segmentation in whole images was proposed based on sliding patch by using deep convolutional neural networks (CNNs) to provide effective morphological features for clinical diagnosis. Methods Firstly, breast region was extracted by regional growing algorithm and dilation algorithm, and the data were normalized. In order to obtain the diagnostic information of each pixel, the images blocks of mass patches and non-mass patches were slid and extracted in corresponding location of the original image. Based on the texture features extracted by deep CNNs, image blocks were classified. At last, based on the prospective classification results of the image blocks, the mass segmentation was made based on coarse-to-fine, and the pixel-level segmentation in whole image was obtained. Results Compared with the advanced deep CNNs, the experimental results demonstrated the algorithm achieved the best accuracy of 96.71% for patches classification under the model of DenseNet and the best F1-score of 83.49% for image segmentation in whole mammogram image. Conclusion According to the results achieved by CNNs, the proposed algorithm can segment mass in mammogram images with good generalization and robustness performance. And it provides a reliable basis for subsequent computer-aided diagnosis of breast lesions.

相似文献/References:

[1]王美文,王艳春,肖沪生,等.S-Detect技术在乳腺超声检查中的诊断性能[J].中国医学物理学杂志,2020,37(4):450.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.010]
　WANG Meiwen,WANG Yanchun,XIAO Husheng,et al.Diagnostic performances of S-Detect technique in breast ultrasound examination[J].Chinese Journal of Medical Physics,2020,37(12):450.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.010]
[2]王孝义,邢素霞,王瑜,等.基于自适应能量偏移场无边缘主动轮廓模型的乳腺肿块分割与分类方法研究[J].中国医学物理学杂志,2020,37(8):1010.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.014]
　WANG Xiaoyi,XING Suxia,WANG Yu,et al.Breast mass image segmentation and classification based on adaptive energy offset field-CV[J].Chinese Journal of Medical Physics,2020,37(12):1010.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.014]

备注/Memo

备注/Memo:
【收稿日期】2020-06-15 【基金项目】国家自然科学基金（61672362）；北京市自然科学基金（4172012）；北京市教育委员会科技发展计划一般项目 （KM201710025011） 【作者简介】梁楠，硕士研究生，研究方向：医学图像处理，E-mail: liangnan@ccmu.edu.cn 【通信作者】张楠，教授，博士生导师，研究方向：图像处理技术，E-mail: zhangnan@ccmu.edu.cn
更新日期/Last Update: 2020-12-30