计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230500004-6.doi: 10.11896/jsjkx.230500004
郭洪洋1, 程前2, 康晓东1, 杨靖怡1, 杨舒琪1, 李芳1,3, 张蕊1
GUO Hongyang1, CHENG Qian2, KANG Xiaodong1, YANG Jingyi1, YANG Shuqi1, LI Fang1,3, ZHANG Rui1
摘要： 传统基于U-Net超声乳腺图像分割任务中存在预测尺度单一和信息丢失等问题。针对存在的问题,提出一种由多重注意力引导机制的U-Net超声乳腺肿瘤图像分割。首先,在U-Net的编码结构中,引入多个SE通道注意力,对输入的乳腺肿瘤图像进行多层级的语义信息提取,引导编码器聚焦乳腺肿瘤特征,减少冗余背景信息带来的干扰;其次,通过设计特征融合处理模块,对编码器传来的特征图进行复杂语义特征的融合处理;最后,在解码器部分,加入金字塔结构捕获全局空间信息,提高模型对肿瘤图像的多尺度特征提取能力,以提高整体网络的表达能力和分割性能。在乳腺肿瘤图像数据集上对该方法进行了仿真实验,结果表明,与其他U-Net改进策略相比,该方法具有更强的准确率和鲁棒性。
中图分类号:
| [1]REBECCAR L,MILLER K D,JEMAL A.Cancer statistics,2019[J].CA:A Cancer Journal for Clinicians,20222,6(1):7-34. [2]XIAO D,LI W B,ZHANG H M.Tumor Segmentation in Breast Ultrasound Images by Fusing Efficient-Net and U-Net[J].Chinese Medical Equipment Journal,2022,43(11):8-13. [3]KANG X D.Medical Image Processing.[M].Beijing:People’s Health Publishing House,2009. [4]XU M L,LI F,ZENG S,et al.Correlation Between the Characteristics of Ultrasound Gray Histogram and HER-2 Expression in Invasive Ductal Carcinoma of Breast[J].Chinese Journal of Medical Imaging,2022,30(12):1224-1229. [5]GOMEZ W,LEJIA L A.Computerized lesion segmentation of breast ultrasound based on marker-controlled watershed transformation[J].Medical Physics,2010,37(1):82-95. [6]HUANG Y L,CHEN D R.Watershed segmentation for breast tumor in 2-D sonography[J].Ultrasound in Medicine & Biology,2004,30(5):625-632. [7]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651. [8]ZHAO H S,SHI J P,QI X J,et al.Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.2017:6230-6239. [9]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Seg-Net:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495. [10]RONNEBERGER O,FISCHER P,BROX T.U-Net:convolu-tional networks for biomedical image segmentation[C]//18th International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer,2015:234-241. [11]CHEN L C,PAPANDREOU G,KKINOS I,et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[J].Computer Science,2014(4):357-361. [12]CHEN L C,PAPANDREOU G,KKINOS I,et al.Deep-Lab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848. [13]CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation[J].arXiv:1706.05587,2017. [14]ZHOU Y W,LIU Z Q,WANG Q F,et al.Breast Mass Image Segmentation Algorithm Based on Improved Residual U-Net[J].Journal of Southwest University,2021,36(2):68-74. [15]ZHAO J Y,QUE D S,TAN J Q,et al.Automated breast lesion segmentation from ultrasound images based on PPU-Net[C]//Proceedings of the 2019 International Conference on Medical Imaging Physics and Engineering.Piscataway:IEEE,2019:19725937. [16]ALEKSANDAR V,MIN X,PHOEBE E F.Attention-enriched deep learning model for breast tumor segmentation in ultrasound images[J].Ultrasound in Medicine and Biology,2020,46(10):2819-2833. [17]CHEN X,LIU Q,DENG X B,et al.Enhanced Network for Ultrasound Breast Tumor Segmentation Based on U-Net[J].Computer Engineering and Applications,2022,58(22):219-228. [18]CHEN X,CAI Y J,RAN W B,et al.SECU-Net:A skin disease images segmentation network combining SE with CRF[J].Intelligent Computer And Applications,2022,12(11):71-77,86. [19]CHANG H.Continuous blood pressure prediction based on deep learning[D].Lanzhou:Lanzhou University of Technology,2020. [20]WANG X,YU M,REN H E.Remote sensing image semantic segmentation combining UNET and FPN[J].Chinese Journal of Liquid Crystals and Displays,2021,36(3):475-483. [21]ZHANG F C,ZHONG G Q,MAO Y X.Neural Architecture Search for Light-weight Medical Image Segmentation Network[J].Computer Science,2022,49(10):183-190. |
|
||
首页