Implicit neural representations in light microscopy

被引:0
|
作者
Hauser, Sophie Louise [1 ]
Brosig, Johanna [2 ]
Murthy, Bhargavi [3 ]
Attardo, Alessio [3 ]
Kist, Andreas M. [1 ]
机构
[1] Friedrich Alexander Univ Erlangen Nurnberg FAU, Dept Artificial Intelligence Biomed Engn, Erlangen, Germany
[2] Charite Univ Med Berlin, Berlin, Germany
[3] Leibniz Inst Neurobiol, Leibniz, Germany
来源
BIOMEDICAL OPTICS EXPRESS | 2024年 / 15卷 / 04期
关键词
DENDRITIC SPINES;
D O I
10.1364/BOE.515517
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Three-dimensional stacks acquired with confocal or two-photon microscopy are crucial for studying neuroanatomy. However, high-resolution image stacks acquired at multiple depths are time-consuming and susceptible to photobleaching. In vivo microscopy is further prone to motion artifacts. In this work, we suggest that deep neural networks with sine activation functions encoding implicit neural representations (SIRENs) are suitable for predicting intermediate planes and correcting motion artifacts, addressing the aforementioned shortcomings. We show that we can accurately estimate intermediate planes across multiple micrometers and fully automatically and unsupervised estimate a motion-corrected denoised picture. We show that noise statistics can be affected by SIRENs, however, rescued by a downstream denoising neural network, shown exemplarily with the recovery of dendritic spines. We believe that the application of these technologies will facilitate more efficient acquisition and superior post-processing in the future.
引用
收藏
页码:2175 / 2186
页数:12
相关论文
共 50 条
  • [41] Hyperspectral Image Compression Using Sampling and Implicit Neural Representations
    Rezasoltani, Shima
    Qureshi, Faisal Z.
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [42] Implicit Neural Representations for Variable Length Human Motion Generation
    Cervantes, Pablo
    Sekikawa, Yusuke
    Sato, Ikuro
    Shinoda, Koichi
    COMPUTER VISION - ECCV 2022, PT XVII, 2022, 13677 : 356 - 372
  • [43] Neural Networks for Implicit Representations of 3D Scenes
    Schirmer, Luiz
    Schardong, Guilherme
    da Silva, Vinicius
    Lopes, Helio
    Novello, Tiago
    Yukimura, Daniel
    Magalhaes, Thales
    Paz, Hallison
    Velho, Luiz
    2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021), 2021, : 17 - 24
  • [44] Implicit Neural Spatial Representations for Time-dependent PDEs
    Chen, Honglin
    Wu, Rundi
    Grinspun, Eitan
    Zheng, Changxi
    Chen, Peter Yichen
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202
  • [45] Exploring the performance of implicit neural representations for brain image registration
    Byra, Michal
    Poon, Charissa
    Rachmadi, Muhammad Febrian
    Schlachter, Matthias
    Skibbe, Henrik
    SCIENTIFIC REPORTS, 2023, 13 (01)
  • [46] Hyperspectral Image Compression Using Sampling and Implicit Neural Representations
    Rezasoltani, Shima
    Qureshi, Faisal Z.
    arXiv, 2023,
  • [47] Point Cloud Compression with Implicit Neural Representations: A Unified Framework
    Ruan, Hongning
    Shao, Yulin
    Yang, Qianqian
    Zhao, Liang
    Niyato, Dusit
    2024 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA, ICCC, 2024,
  • [48] Neural Feature Matching in Implicit 3D Representations
    Chen, Yunlu
    Fernando, Basura
    Bilen, Hakan
    Mensink, Thomas
    Gavves, Efstratios
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [49] Automatic Adjustment of Fourier Embedding Parametrizations for Implicit Neural Representations
    Hoefer, Timon
    Zell, Andreas
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 2307 - 2313
  • [50] Implicit Neural Representations for Generative Modeling of Living Cell Shapes
    Wiesner, David
    Suk, Julian
    Dummer, Sven
    Svoboda, David
    Wolterink, Jelmer M.
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT IV, 2022, 13434 : 58 - 67