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 4 条

[1] Noise2Void-Learning Denoising from Single Noisy Images
Krull, Alexander
Buchholz, Tim-Oliver
Jug, Florian
[J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 2124 - 2132
[2] Removing independent noise in systems neuroscience data using DeepInterpolation
Lecoq, Jerome
Oliver, Michael
Siegle, Joshua H.
Orlova, Natalia
Ledochowitsch, Peter
Koch, Christof
[J]. NATURE METHODS, 2021, 18 (11) : 1401 - +
[3] Platisa J., 2021, BIORXIV
[4] Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, Kai
Zuo, Wangmeng
Chen, Yunjin
Meng, Deyu
Zhang, Lei
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (07) : 3142 - 3155

← 1 →