[1]史健婷,崔闫靖,常 亮.基于优化 U-Net 网络的乳腺肿瘤区域分割方法[J].计算机技术与发展,2021,31(08):156-161.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 027]
 SHI Jian-ting,CUI Yan-jing,CHANG Liang.A Segmentation Method of Breast Tumor Region Based onOptimized U-Net[J].,2021,31(08):156-161.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 027]
点击复制

基于优化 U-Net 网络的乳腺肿瘤区域分割方法()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年08期
页码:
156-161
栏目:
应用前沿与综合
出版日期:
2021-08-10

文章信息/Info

Title:
A Segmentation Method of Breast Tumor Region Based onOptimized U-Net
文章编号:
1673-629X(2021)08-0156-06
作者:
史健婷崔闫靖常 亮
黑龙江科技大学 计算机与信息工程学院,黑龙江 哈尔滨 150022
Author(s):
SHI Jian-tingCUI Yan-jingCHANG Liang
School of Computer and Information Engineering,Heilongjiang University ofScience and Technology,Harbin 150022,China
关键词:
乳腺超声图像分割U-Net高斯滤波残差块
Keywords:
breast ultrasoundimage segmentationU-NetGaussian filteringresidual block
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 08. 027
摘要:
乳腺癌是发生在乳腺腺上皮组织的恶性肿瘤,防治的关键在于早发现、早诊断。 乳腺肿瘤在超声图像中一般表现为低回声区,因此乳腺超声图像有斑点噪声多、边缘比较模糊、灰度不均匀等特性,造成了乳腺肿瘤分割难度增大的情况。针对以上情况,为了提高乳腺肿瘤超声图像分割的精度和效率,提出了一种基于优化 U-Net 网络的乳腺肿瘤区域分割新方法。 采用高斯滤波预处理来减小噪声对超声图片的影响。 受残差结构启发设计新的特征提取网络,既能获得更强的特征提取能力使得图边缘信息分割更加精细,还能减少梯度消失等问题。 实验使用 532 幅超声图像和医生标注过的乳腺肿瘤区域掩码图像为原始数据集,验证该分割方法的性能。 实验结果表明,该方法可以使肿瘤区域的分割结果更加精确,优于传统的分割模型,具有较大的临床应用前景。
Abstract:
Breast cancer is a malignant tumor occurring in the epithelial tissue of breast gland. The key to prevention and treatment is early detection and early diagnosis. Breast tumor is usually low echo area in ultrasound image. Therefore,breast ultrasound image has many characteristics such as more speckle noise,blurred edge and uneven gray,which greatly increases the difficulty of breast tumor segmentation. In order to improve the accuracy and efficiency of breast tumor ultrasound image segmentation, a new fast segmentation method of breast ultrasound image based on optimized U - Net is proposed. In this method, the ultrasonic image is preprocessed by Gaussian filter and the depth of the network is deepened by residual to obtain stronger feature extraction ability,which makes the image edge information segmentation more precise.? 532 ultrasound images and the mask image of breast tumor region marked by doctors were used as the original data set to verify the segmentation performance of the proposed method. The experiment shows that the proposed method can accurately and efficiently segment tumor area, which is better than the traditional segmentation model,and has great clinical application prospects.

相似文献/References:

[1]蒋璐璐 王适 王宝成 李慧敏 李鑫慧.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010,(01):36.
 JIANG Lu-lu,WANG Shi,WANG Bao-cheng,et al.Segmentation of Remote Sensing Image Based on an Improved Labeling Watershed Algorithm[J].,2010,(08):36.
[2]张少娴 俞琼.基于时空相关性预测的运动估计的优化[J].计算机技术与发展,2010,(01):100.
 ZHANG Shao-xian,YU Qiong.An Optimization Method for Spatiotemporal Predictive Motion Estimation[J].,2010,(08):100.
[3]王兴 冯子亮.基于自适应初始值的FCM聚类图像分割[J].计算机技术与发展,2010,(03):101.
 WANG Xing,FENG Zi-liang.An Image Segmentation Algorithm Based on Adaptive Initialization FCM Clustering[J].,2010,(08):101.
[4]何小娜 逄焕利.基于二维直方图和改进蚁群聚类的图像分割[J].计算机技术与发展,2010,(03):128.
 HE Xiao-na,PANG Huan-li.Image Segmentation Based on Improved Ant Colony Clustering and Two- Dimensional Histogram[J].,2010,(08):128.
[5]宋淑娜 李金霞 胡学坤 高尚.一种自适应模糊阈值区间的图像分割方法[J].计算机技术与发展,2010,(05):121.
 SONG Shu-na,LI Jin-xia,HU Xue-kun,et al.A Method of Adaptive Fuzzy Threshold Region for Image Segmentation[J].,2010,(08):121.
[6]来磊 卢文科 邓开连.基于二维Tsallis交叉熵直线型图像阈值分割方法[J].计算机技术与发展,2010,(06):105.
 LAI Lei,LU Wen-ke,DENG Kai-lian.New Image Thresholding Segmentation Methods Based on Two-Dimensional Tsallis Cross-Entropy Liner-Type[J].,2010,(08):105.
[7]黄长专 王彪 杨忠.图像分割方法研究[J].计算机技术与发展,2009,(06):76.
 HUANG Chang-zhuan,WANG Biao,YANG Zhong.A Study on Image Segmentation Techniques[J].,2009,(08):76.
[8]李光耀 聂诗良.基于小波分解和模糊聚类的图像分割方法[J].计算机技术与发展,2009,(06):121.
 LI Guang-yao,NIE Shi-liang.Image Segment Algorithm Based on Wavelet Decomposition and Fuzzy Clustering Theory[J].,2009,(08):121.
[9]吴亚 汪继文.水平集图像分割中重新初始化规避的探索[J].计算机技术与发展,2009,(09):69.
 WU Ya,WANG Ji-wen.Avoidance of Re- Initialization in Level Set Image Segmentation[J].,2009,(08):69.
[10]李鑫环 陈立潮 赵红艳 赵勇.基于多小波分析与SOFM的MR图像分割算法研究[J].计算机技术与发展,2009,(09):104.
 LI Xin-huan,CHEN Li-chao,ZHAO Hong-yan,et al.Research on MR Image Segmentation Based on Multi- wavelet Analysis and SOFM[J].,2009,(08):104.

更新日期/Last Update: 2021-08-10