Two-photon Voltage Imaging Denoising by Self-supervised Learning

被引：1

作者：

Liu, Chang ^{[1
,2
]}

Platisa, Jelena ^{[3
,4
,5
]}

Ye, Xin ^{[2
,6
]}

Ahrens, Allison M. ^{[7
]}

Chen, Ichun Anderson ^{[6
]}

Davison, Ian G. ^{[6
,7
,8
]}

Pieribone, Vincent A. ^{[3
,4
,5
]}

Chen, Jerry L. ^{[2
,6
,7
,8
]}

Tian, Lei ^{[1
,2
,6
]}

机构：

[1] Boston Univ, Dept Elect & Comp Engn, Boston, MA 02215 USA

[2] Boston Univ, Dept Biomed Engn, Boston, MA 02215 USA

[3] Yale Univ, Dept Cellular & Mol Physiol, New Haven, CT 06520 USA

[4] Yale Univ, Dept Neurosci, New Haven, CT 06520 USA

[5] John B Pierce Lab, New Haven, CT 06520 USA

[6] Boston Univ, Ctr Neurophoton, Boston, MA 02215 USA

[7] Boston Univ, Dept Biol, Boston, MA 02215 USA

[8] Boston Univ, Ctr Syst Neurosci, Boston, MA 02215 USA

来源：

NEURAL IMAGING AND SENSING 2023 | 2023年 / 12365卷

关键词：

denoising; voltage imaging; self-supervised learning; two photon; deep learning; high speed; large field of view; low light;

D O I：

10.1117/12.2648122

中图分类号：

TH742 [显微镜];

学科分类号：

摘要：

High-speed low-light two-photon voltage imaging is an emerging tool to simultaneously monitor neuronal activity from a large number of neurons. However, shot noise dominates pixel-wise measurements and the neuronal signals are difficult to be identified in the single-frame raw measurement. We developed a self-supervised deep learning framework for voltage imaging denoising, DeepVID, without the need for any high-SNR measurements. DeepVID infers the underlying fluorescence signal based on independent temporal and spatial statistics of the measurement that is attributable to shot noise. DeepVID achieved a 15-fold improvement in SNR when comparing denoised and raw image data.

引用

页数：2

共 50 条

[31] Seismic Data Denoising Using a Self-Supervised Deep Learning Network
Detao Wang
Guoxiong Chen
Jianwei Chen
Qiuming Cheng
Mathematical Geosciences, 2024, 56 : 487 - 510
[32] Transfer learning for self-supervised, blind-spot seismic denoising
Birnie, Claire
Alkhalifah, Tariq
FRONTIERS IN EARTH SCIENCE, 2022, 10
[33] Robust seismic data denoising via self-supervised deep learning
Li, Ji
Trad, Daniel
Liu, Dawei
Geophysics, 2024, 89 (05)
[34] Self-supervised learning for modal transfer of brain imaging
Cheng, Dapeng
Chen, Chao
Yanyan, Mao
You, Panlu
Huang, Xingdan
Gai, Jiale
Zhao, Feng
Mao, Ning
FRONTIERS IN NEUROSCIENCE, 2022, 16
[35] Self-Supervised Federated Learning for Fast MR Imaging
Zou, Juan
Pei, Tingrui
Li, Cheng
Wu, Ruoyou
Wang, Shanshan
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 (1-11) : 1 - 11
[36] Leveraging Self-supervised Denoising for Image Segmentation
Prakash, Mangal
Buchholz, Tim-Oliver
Lalit, Manan
Tomancak, Pavel
Jug, Florian
Krull, Alexander
2020 IEEE 17TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2020), 2020, : 428 - 432
[37] Self-Supervised Poisson-Gaussian Denoising
Khademi, Wesley
Rao, Sonia
Minnerath, Clare
Hagen, Guy
Ventura, Jonathan
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 2130 - 2138
[38] Investigating self-supervised image denoising with denaturation
Waida, Hiroki
Yamazaki, Kimihiro
Tokuhisa, Atsushi
Wada, Mutsuyo
Wada, Yuichiro
Neural Networks, 2025, 184
[39] Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image
Quan, Yuhui
Chen, Mingqin
Pang, Tongyao
Ji, Hui
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 1887 - 1895
[40] Two-photon temporal self-imaging
Torres-Company, Victor
Lancis, Jesus
Lajunen, Hanna
Friberg, Ari T.
22ND CONGRESS OF THE INTERNATIONAL COMMISSION FOR OPTICS: LIGHT FOR THE DEVELOPMENT OF THE WORLD, 2011, 8011

← 1 2 3 4 5 →