An improved you only look once algorithm for pronuclei and blastomeres localization

被引:0
作者
Dong, Xinghao [1 ]
Li, Chang [1 ,2 ]
Zhang, Xu [3 ]
Huang, Guoning [3 ]
Zhang, Xiaodong [3 ]
机构
[1] Hefei Univ Technol, Dept Biomed Engn, Hefei 230009, Peoples R China
[2] Hefei Univ Technol, Anhui Prov Key Lab Measuring Theory & Precis Instr, Hefei 230009, Peoples R China
[3] Chongqing Med Univ, Women & Childrens Hosp, Chongqing Clin Res Ctr Reprod Med, 64 Jintang Rd, Chongqing 400013, Peoples R China
基金
中国国家自然科学基金;
关键词
Embryo images; Target localization; Deep learning; Attention module; Partial convolution; OBJECT DETECTION; EMBRYO; STAGE;
D O I
10.1016/j.engappai.2024.108929
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Pronuclei and blastomeres are key structures in early embryonic development, and by localizing these structures simultaneously, the developmental state of the embryo can be assessed more comprehensively. However, there are several unavoidable problems in localization tasks due to the biological characteristics of embryos, including blastomeres overlap, pronuclei overlap, and similarity between pronuclei and background. In this study, we propose a novel localization network for pronuclei and blastomeres, which can solve these localization problems. Firstly, to address the issues related to the overlap of pronuclei and blastomeres, as well as the pronuclei and background similarity problem, we put the vision transformer with bi-level routing attention module (BiFormer) in the backbone. The BiFormer finds attention regions in the embryo image scene to obtain more edge and texture information of both pronuclei and blastomeres, which allows for a better feature realization of the neck region fusion interaction. Subsequently, to enhance model performance and mitigate redundant computation. The localization network uses partial convolution (PConv) in the backbone. The backbone network allows more efficient extraction of features by simultaneously reducing redundancy in computation with the effect of PConv. In addition, to mitigate the impact of low-quality samples in embryo images on localization, as well as to pay more attention to ordinary quality samples, we use wise intersection over union version 3 (WIoUv3) loss function with a dynamic non-monotonic focusing mechanism in the localization network, thus improving the overall performance of the algorithm. The experimental results show our model mAP@0.5 is 92.4% in localizing pronuclei and blastomeres. In practical terms, the ability to accurately localize pronuclei and blastomeres allows for better assessment of embryo quality and selects the best embryos.
引用
收藏
页数:12
相关论文
共 49 条
  • [1] Ali A.A., 2017, 2017 INT C EL COMP T, P1
  • [2] Chen F, 2019, arXiv
  • [3] Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
    Chen, Jierun
    Kao, Shiu-Hong
    He, Hao
    Zhuo, Weipeng
    Wen, Song
    Lee, Chul-Ho
    Chan, S. -H. Gary
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 12021 - 12031
  • [4] DPT: Deformable Patch-based Transformer for Visual Recognition
    Chen, Zhiyang
    Zhu, Yousong
    Zhao, Chaoyang
    Hu, Guosheng
    Zeng, Wei
    Wang, Jinqiao
    Tang, Ming
    [J]. PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 2899 - 2907
  • [5] Cicconet M, 2014, IEEE IMAGE PROC, P3626, DOI 10.1109/ICIP.2014.7025736
  • [6] DECHERNEY AH, 1986, YALE J BIOL MED, V59, P409
  • [7] Filho E Santos, 2010, Open Biomed Eng J, V4, P170, DOI 10.2174/1874120701004010170
  • [8] Gevorgyan Z, 2022, Arxiv, DOI arXiv:2205.12740
  • [9] Fast R-CNN
    Girshick, Ross
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 1440 - 1448
  • [10] Rich feature hierarchies for accurate object detection and semantic segmentation
    Girshick, Ross
    Donahue, Jeff
    Darrell, Trevor
    Malik, Jitendra
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 580 - 587