A lightweight network based on dual-stream feature fusion and dual-domain attention for white blood cells segmentation

被引:2
|
作者
Luo, Yang [1 ]
Wang, Yingwei [1 ]
Zhao, Yongda [1 ]
Guan, Wei [2 ]
Shi, Hanfeng [3 ]
Fu, Chong [4 ,5 ,6 ]
Jiang, Hongyang [3 ]
机构
[1] Anshan Normal Univ, Sch Math & Informat Sci, Anshan, Liaoning, Peoples R China
[2] Anshan Normal Univ, Sch Appl Technol, Anshan, Liaoning, Peoples R China
[3] Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Guangdong, Peoples R China
[4] Northeastern Univ, Sch Comp Sci & Engn, Shenyang, Peoples R China
[5] Minist Educ, Engn Res Ctr Secur Technol Complex Network Syst, Shenyang, Peoples R China
[6] Northeastern Univ, Key Lab Intelligent Comp Med Image, Minist Educ, Shenyang, Peoples R China
来源
FRONTIERS IN ONCOLOGY | 2023年 / 13卷
关键词
white blood cells segmentation; instance segmentation; YOLACT-CIS; dual-stream feature fusion network (DFFN); dual-domain attention module (DDAM); CLASSIFICATION; ALGORITHM; IMAGES; COLOR;
D O I
10.3389/fonc.2023.1223353
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
IntroductionAccurate white blood cells segmentation from cytopathological images is crucial for evaluating leukemia. However, segmentation is difficult in clinical practice. Given the very large numbers of cytopathological images to be processed, diagnosis becomes cumbersome and time consuming, and diagnostic accuracy is also closely related to experts' experience, fatigue and mood and so on. Besides, fully automatic white blood cells segmentation is challenging for several reasons. There exists cell deformation, blurred cell boundaries, and cell color differences, cells overlapping or adhesion.MethodsThe proposed method improves the feature representation capability of the network while reducing parameters and computational redundancy by utilizing the feature reuse of Ghost module to reconstruct a lightweight backbone network. Additionally, a dual-stream feature fusion network (DFFN) based on the feature pyramid network is designed to enhance detailed information acquisition. Furthermore, a dual-domain attention module (DDAM) is developed to extract global features from both frequency and spatial domains simultaneously, resulting in better cell segmentation performance.ResultsExperimental results on ALL-IDB and BCCD datasets demonstrate that our method outperforms existing instance segmentation networks such as Mask R-CNN, PointRend, MS R-CNN, SOLOv2, and YOLACT with an average precision (AP) of 87.41%, while significantly reducing parameters and computational cost.DiscussionOur method is significantly better than the current state-of-the-art single-stage methods in terms of both the number of parameters and FLOPs, and our method has the best performance among all compared methods. However, the performance of our method is still lower than the two-stage instance segmentation algorithms. in future work, how to design a more lightweight network model while ensuring a good accuracy will become an important problem.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Dual-stream pyramid and attention network for stereo matching
    Shi, Liqing
    Xiong, Taiping
    Cui, Gengshen
    Pan, Minghua
    Zhu, Zhiguo
    Cheng, Wei
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2024, 46 (02) : 4909 - 4922
  • [22] Deep Dual-Stream Network with Scale Context Selection Attention Module for Semantic Segmentation
    Liu, Yifu
    Xu, Chenfeng
    Chen, Zhihong
    Chen, Chao
    Zhao, Han
    Jin, Xinyu
    NEURAL PROCESSING LETTERS, 2020, 51 (03) : 2281 - 2299
  • [23] Dual-stream GNN fusion network for hyperspectral classification
    Li, Weiming
    Liu, Qikang
    Fan, Shuaishuai
    Xu, Con'gan
    Bai, Hongyang
    APPLIED INTELLIGENCE, 2023, 53 (22) : 26542 - 26567
  • [24] Deep Dual-Stream Network with Scale Context Selection Attention Module for Semantic Segmentation
    Yifu Liu
    Chenfeng Xu
    Zhihong Chen
    Chao Chen
    Han Zhao
    Xinyu Jin
    Neural Processing Letters, 2020, 51 : 2281 - 2299
  • [25] DSAGAN: A generative adversarial network based on dual-stream attention mechanism for anatomical and functional image fusion
    Fu, Jun
    Li, Weisheng
    Du, Jiao
    Xu, Liming
    Li, Weisheng (liws@cqupt.edu.cn), 1600, Elsevier Inc. (576): : 484 - 506
  • [26] Graph Dual-stream Convolutional Attention Fusion for precipitation nowcasting
    Vatamany, Lorand
    Mehrkanoon, Siamak
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 141
  • [27] DSAGAN: A generative adversarial network based on dual-stream attention mechanism for anatomical and functional image fusion
    Fu, Jun
    Li, Weisheng
    Du, Jiao
    Xu, Liming
    INFORMATION SCIENCES, 2021, 576 : 484 - 506
  • [28] Dual-Stream Feature Fusion Network for Detection and ReID in Multi-object Tracking
    He, Qingyou
    Li, Liangqun
    PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT I, 2022, 13629 : 247 - 260
  • [29] Dual-stream VO: Visual Odometry Based on LSTM Dual-Stream Convolutional Neural Network
    Luo, Yuan
    Zeng, YongChao
    Lv, RunZhe
    Wang, WenHao
    ENGINEERING LETTERS, 2022, 30 (03) : 926 - 934
  • [30] DDFL: Dual-Domain Feature Learning for nighttime semantic segmentation
    Lin, Xiao
    Tan, Peiwen
    Wang, Zhengkai
    Ma, Lizhuang
    Li, Yan
    DISPLAYS, 2024, 83