Boundary-Preserved Deep Denoising of Stochastic Resonance Enhanced Multiphoton Images
Journal
IEEE journal of translational engineering in health and medicine
Journal Volume
10
Pages
1800812
Date Issued
2022
Author(s)
Niu, Sheng-Yong
Guo, Lun-Zhang
Li, Yue
Zhang, Zhiming
Liu, Kai-Chun
Li, You-Jin
Tsao, Yu
Liu, Tzu-Ming
Abstract
With the rapid growth of high-speed deep-tissue imaging in biomedical research, there is an urgent need to develop a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional denoising filters and models can easily suppress the perturbative noise in high-contrast images; however, for low photon budget multiphoton images, a high detector gain will not only boost the signals but also bring significant background noise. In such a stochastic resonance imaging regime, subthreshold signals may be detectable with the help of noise, meaning that a denoising filter capable of removing noise without sacrificing important cellular features, such as cell boundaries, is desirable.
Subjects
Third harmonic generation; deep denoising autoencoder; three-photon fluorescence
SDGs
Type
journal article