Generation and study of the synthetic brain electron microscopy dataset for segmentation purpose

被引:0
|
作者
Sokolov, N. A. [1 ]
Vasiliev, E. P. [1 ]
Getmanskaya, A. A. [1 ]
机构
[1] Lobachevsky Univ, Dept Math Software & Supercomp Technol, Gagarina St 23, Nizhnii Novgorod 603950, Russia
关键词
multi-class segmentation; electron microscopy; neural network; image segmentation; machine learning; RADIALLY POLARIZED-LIGHT; OPTICAL-ELEMENTS; VECTOR BEAMS; BASE ANGLE; AXICON; FABRICATION; GRATINGS; SCHEME; STATES; PHASE;
D O I
10.18287/-6179-CO-1273
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Advanced microscopy technologies such as electron microscopy have opened up a new field of vision for biomedical researchers. The use of artificial intelligence methods for processing EM data is largely difficult due to the small amount of annotated data at the training stage. Therefore, we add synthetic images to an annotated real EM dataset or use a fully synthetic training dataset. In this work, we present an algorithm for the synthesis of 6 types of organelles. Based on the EPFL dataset, a training set of 1161 real fragments 256x256 (ORG) and 2000 synthetic ones (SYN), as well as their combination (MIX), were generated. The experiment of training models for 6, 5 classes and binary segmentation showed that, despite the imperfections of synthetics, training on a mixed (MIX) dataset gave a significant increase (about 0.1) in the Dice metric for 6 and 5 and same results at binary. The synthetic data strategy gives annotations for free, but shifts the effort to producing sufficiently realistic images.
引用
收藏
页码:778 / 787
页数:10
相关论文
共 50 条
  • [41] Transmission Electron Microscopy Study of Mitochondria in Aging Brain Synapses
    Rybka, Vladyslava
    Suzuki, Yuichiro J.
    Gavrish, Alexander S.
    Dibrova, Vyacheslav A.
    Gychka, Sergiy G.
    Shults, Nataliia, V
    ANTIOXIDANTS, 2019, 8 (06)
  • [42] Reelin expression in brain endothelial cells: an electron microscopy study
    Emma Perez-Costas
    Erin Y Fenton
    Hector J Caruncho
    BMC Neuroscience, 16
  • [43] Cable Instance Segmentation with Synthetic Data Generation
    Wahd, Assefa Seyoum
    Kim, Donghyung
    Lee, Seung-Ik
    2022 22ND INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2022), 2022, : 1533 - 1538
  • [44] A Drosophila heart optical coherence microscopy dataset for automatic video segmentation
    Matthew Fishman
    Abigail Matt
    Fei Wang
    Elena Gracheva
    Jiantao Zhu
    Xiangping Ouyang
    Andrey Komarov
    Yuxuan Wang
    Hongwu Liang
    Chao Zhou
    Scientific Data, 10
  • [45] A Drosophila heart optical coherence microscopy dataset for automatic video segmentation
    Fishman, Matthew
    Matt, Abigail
    Wang, Fei
    Gracheva, Elena
    Zhu, Jiantao
    Ouyang, Xiangping
    Komarov, Andrey
    Wang, Yuxuan
    Liang, Hongwu
    Zhou, Chao
    SCIENTIFIC DATA, 2023, 10 (01)
  • [46] Copy-Move Detection in Optical Microscopy: A Segmentation Network and a Dataset
    Shao, Hao-Chiang
    Liao, Yuan-Rong
    Tseng, Tse-Yu
    Chuo, Yen-Liang
    Lin, Fong-Yi
    IEEE SIGNAL PROCESSING LETTERS, 2025, 32 : 1106 - 1110
  • [47] Synaptic Cleft Segmentation in Non-isotropic Volume Electron Microscopy of the Complete Drosophila Brain
    Heinrich, Larissa
    Funke, Jan
    Pape, Constantin
    Nunez-Iglesias, Juan
    Saalfeld, Stephan
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT II, 2018, 11071 : 317 - 325
  • [48] Generating Synthetic Image Segmentation Dataset Using Realistic City Backgrounds
    Islek, Irem
    Aksayli, N. Deniz
    Gungor, Onur
    Karaman, Cagla Cig
    2022 30TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU, 2022,
  • [49] Plant disease symptom segmentation in chlorophyll fluorescence imaging with a synthetic dataset
    Sapoukhina, Natalia
    Boureau, Tristan
    Rousseau, David
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [50] Extensible portal frame bridge synthetic dataset for structural semantic segmentation
    Tatiana Fountoukidou
    Iuliia Tkachenko
    Benjamin Poli
    Serge Miguet
    AI in Civil Engineering, 2024, 3 (1):