计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (7): 161-169.doi: 10.11896/jsjkx.240500134

• 计算机图形学&多媒体 • 上一篇    下一篇

SCF U2-Net:结合模糊逻辑的轻量化改进U2-Net乳腺超声病变分割方法

庄建军1,2, 万理1   

  1. 1 南京信息工程大学电子与信息工程学院 南京 210044
    2 南京信息工程大学人工智能学院中大医院智慧医疗研究院 南京 210044
  • 收稿日期:2024-05-30 修回日期:2024-09-20 发布日期:2025-07-17
  • 通讯作者: 庄建军(jjzhuang@nuist.edu.cn)
  • 基金资助:
    国家自然科学基金(62272234);江苏高校“青蓝工程”

SCF U2-Net:Lightweight U2-Net Improved Method for Breast Ultrasound Lesion SegmentationCombined with Fuzzy Logic

ZHUANG Jianjun1,2, WAN Li1   

  1. 1 School of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
    2 Institute for Artificial Intelligence in Medicine, School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China
  • Received:2024-05-30 Revised:2024-09-20 Published:2025-07-17
  • About author:ZHUANG Jianjun,born in 1973,Ph.D,professor.His main research interests include medical image processing and embedded,wearable medical instruments.
  • Supported by:
    National Natural Science Foundation of China(62272234) and Jiangsu University “Blue Project”.

PDF (PC)

25

摘要： 乳腺超声图像中病变的边界具有不确定性且形态不一,原始U2-Net存在参数量大的问题,对此提出一种结合模糊逻辑的轻量化改进U2-Net乳腺超声病变分割方法SCF U2-Net。利用模糊逻辑对特征图像素进行模糊化并计算不确定度值,与输入特征图相乘来降低图像的模糊性,有效解决了边界的不确定性问题。结合深度可分离卷积和扩张卷积,对残差U型模块(ReSidual U-blocks,RSU)进行改进,以减少模型参数量,提高分割效率。针对乳腺病变形态不一的问题,在解码阶段嵌入坐标注意力机制,加强感兴趣区域的信息提取能力,提高分割精度。经BUSI数据集测试,Dice和IoU分别为0.8975和0.8328,参数量降低了90%,推理速度是原来的1.9倍。与3种主流语义分割模型相比,所提算法的分割性能更优;与两种轻量化分割模型相比,在参数规模相当的情况下分割性能优势明显,具有良好的临床应用价值。

关键词: 乳腺病变分割, 模糊逻辑, 轻量化模型, 深度可分离扩张卷积, 注意力机制

Abstract: The boundary of lesions in breast ultrasound images is uncertain and the shape varies.The original U2-Net has a pro-blem with a large number of parameters.In response to this,this paper proposes a lightweight and improved U2-Net breast ultrasound lesion segmentation method called SCF U2-Net,which combines fuzzy logic.It utilizes fuzzy logic to blur the feature map pixels and calculates uncertainty values,then multiply them with the input feature map to reduce image blurriness effectively addressing the uncertainty issue at boundaries.It also improves the Residual U-blocks (RSU) by combining depthwise separable convolution and dilated convolution to reduce model parameter count and enhance segmentation efficiency.To address the varied morphology of breast lesions,embedding coordinate attention mechanisms in the decoding stage to strengthen information extraction capabilities for regions of interest,thereby improving segmentation accuracy.Through testing on BUSI dataset,the proposed method achieves Dice and IoU scores of 0.8975 and 0.8328 respectively,while reducing parameter count by 90% and increasing inference speed by 1.9 times compared to original speeds.Furthermore,when compared with three mainstream semantic segmentation models,the proposed algorithm demonstrates superior performance,has a significantly segmentation performance advantage with a comparable parameters,and has good clinical application value.

Key words: Breast lesion segmentation, Fuzzy logic, Lightweight model, Sep-dilated convolution, Attention mechanism

中图分类号: 

  • TP391
[1]SIEGEL R L,KRATZER T B,GIAQUINTO A N,et al.Cancer statistics[J].CA:A Cancer Journal of Clinicians,2025,75(1):10.
[2]MAHAJAN V,VENUGOPAL V.Audit of artificial intelligence algorithms and its impact in relieving shortage of specialist doctors[M]//Artificial Intelligence:Applications in Healthcare Delivery.2020:207-221.
[3]LYU W Q.Medical artificial intelligence based on fuzzy logic:Opening the dimension of morality[J].Chinese Journal of Medical Ethics,2024,37(1):32-38.
[4]KERAMIDAS E G,IAKOVIDIS D K,MAROULIS D,et al.Efficient and effective ultrasound image analysis scheme for thyroid nodule detection[C]//ICIAR 2007.Berlin:Springer,2007:1052-1060.
[5]HUANG Y L,CHEN D R.Watershed segmentation for breast tumor in 2-D sonography[J].Ultrasound in Medicine and Biology,2004,30(5):625-632.
[6]JIANG P,PENG J,ZHANG G,et al.Learning-based automatic breast tumor detection and segmentation in ultrasound images[C]//2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).IEEE,2012:1587-1590.
[7]HUANG Q H,LEE S Y,LIU L Z,et al.A robust graph-basedsegmentation method for breast tumors in ultrasound images[J].Ultrasonics,2012,52(2):266-275.
[8]SHAN J,CHENG H D,WANG Y.A novel segmentation me-thod for breast ultrasound images based on neutrosophic l-means clustering[J].Medical Physics,2012,39(9):5669-5682.
[9]ABDEL M,MELENDEZ J,MORENO A,et al.Breast tumorclassification in ultrasound images using texture analysis and super-resolution methods[J].Engineering Applications of Artificial Intelligence,2017,59:84-92.
[10]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.
[11]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2016:770-778.
[12]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.
[13]ZHOU T,DONG Y L,HUO B Q,et al.U-Net and its applications in medical image segmentation:a review[J].Journal of Image and Graphics,2021,26(9):2058-2077.
[14]BYRA M,JAROSIK P,SZUBERT A,et al.Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network[J].Biomedical Signal Processing and Control,2020,61:102027.
[15]HUANG R,LIN M,DOU H,et al.Boundary-rendering network for breast lesion segmentation in ultrasound images[J].Medical Image Analysis,2022,80:102478.
[16]ZHANG X F,ZHANG S,ZHANG D H,et al.Group Attention-based Medical Image Segmentation Model[J].Journal of Image and Graphics,2023,28(10):3231-3242.
[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]BAI X F,MA Y N,WANG W J.Segmentation Method of Edge-guided Breast Ultrasound Images Based on Feature Fusion[J].Computer Science,2023,50(3):199-207.
[19]PENG Y T,LIANG F M.Tumor segmentation method forbreast ultrasound images incorporating CNN and VIT[J].CAAI Transactions on Intelligent Systems,2024,19(3):556-564.
[20]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[21]VALANARASUJ M J,PATEL V M.Unext:Mlp-based rapid medical image segmentation network[C]//International Confe-rence on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer,2022:23-33.
[22]WANG A,CHEN H,LIN Z,et al.Repvit:Revisiting mobile cnn from vit perspective[J].arXiv:2307.09283,2023.
[23]QIN X,ZHANG Z,HUANG C,et al.U2-Net:Going deeperwith nested U-structure for salient object detection[J].Pattern Recognition,2020,106(1):1-12.
[24]DENG Y,REN Z,KONG Y,et al.A hierarchical fused fuzzy deep neural network for data classification[J].IEEE Transactions on Fuzzy Systems,2016,25(4):1006-1012.
[25]HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].arXiv:1704.04861,2017.
[26]YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].arXiv:1511.07122,2015.
[27]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141.
[28]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:3-19.
[29]HOU Q,ZHOU D,FENG J.Coordinate attention for efficientmobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13713-13722.
[30]AL-DHABYANI W,GOMAA M,KHALED H,et al.Dataset of breast ultrasound images[J].Data in Brief,2020,28:104863.
[31]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2881-2890.
[32]CHEN J,LU Y,YU Q,et al.Transunet:Transformers makestrong encoders for medical image segmentation[J].arXiv:2102.04306,2021.
[33]WANG A,CHEN H,LIN Z,et al.Repvit:Revisiting mobile cnn from vit perspective[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2024:15909-15920.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发