TY - JOUR
T1 - M-Denoiser: Unsupervised image denoising for real-world optical and electron microscopy data
AU - Chong, Xiaoya
AU - Cheng, Min
AU - Fan, Wenqi
AU - Li, Qing
AU - Leung, Howard
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/9
Y1 - 2023/9
N2 - Real-world microscopy data have a large amount of noise due to the limited light/electron that can be used to capture images. The noise of microscopy data is composed of signal-dependent shot noise and signal-independent read noise, and the Poisson–Gaussian noise model is usually used to describe the noise distribution. Meanwhile, the noise is spatially correlated because of the data acquisition process. Due to the lack of clean ground truth, unsupervised and self-supervised denoising algorithms in computer vision shed new light on tackling such tasks by utilizing paired noisy images or one single noisy image. However, they usually make the assumption that the noise is signal-independent or pixel-wise independent, which contradicts with the actual case. Hence, we propose M-Denoiser for denoising real-world microscopy data in an unsupervised manner. Firstly, the shatter module is used to break the dependency and correlation before denoising. Secondly, a novelly designed unsupervised training loss based on a pair of noisy images is proposed for real-world microscopy data. For evaluation, we train our model on optical and electron microscopy datasets. The experimental results show that M-Denoiser achieves the best performance both quantitatively and qualitatively compared with all the baselines.
AB - Real-world microscopy data have a large amount of noise due to the limited light/electron that can be used to capture images. The noise of microscopy data is composed of signal-dependent shot noise and signal-independent read noise, and the Poisson–Gaussian noise model is usually used to describe the noise distribution. Meanwhile, the noise is spatially correlated because of the data acquisition process. Due to the lack of clean ground truth, unsupervised and self-supervised denoising algorithms in computer vision shed new light on tackling such tasks by utilizing paired noisy images or one single noisy image. However, they usually make the assumption that the noise is signal-independent or pixel-wise independent, which contradicts with the actual case. Hence, we propose M-Denoiser for denoising real-world microscopy data in an unsupervised manner. Firstly, the shatter module is used to break the dependency and correlation before denoising. Secondly, a novelly designed unsupervised training loss based on a pair of noisy images is proposed for real-world microscopy data. For evaluation, we train our model on optical and electron microscopy datasets. The experimental results show that M-Denoiser achieves the best performance both quantitatively and qualitatively compared with all the baselines.
KW - Deep learning
KW - Poisson–Gaussian noise
KW - Real-world microscopy
KW - Unsupervised denoising
UR - http://www.scopus.com/inward/record.url?scp=85167460674&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2023.107308
DO - 10.1016/j.compbiomed.2023.107308
M3 - Journal article
C2 - 37562326
AN - SCOPUS:85167460674
SN - 0010-4825
VL - 164
SP - 1
EP - 13
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 107308
ER -