Robust Phase Unwrapping via Deep Image Prior for Quantitative Phase Imaging

09/24/2020
by   Fangshu Yang, et al.
0

Quantitative phase imaging (QPI) is an emerging label-free technique that produces images containing morphological and dynamical information without contrast agents. Unfortunately, the phase is wrapped in most imaging system. Phase unwrapping is the computational process that recovers a more informative image. It is particularly challenging with thick and complex samples such as organoids. Recent works that rely on supervised training show that deep learning is a powerful method to unwrap the phase; however, supervised approaches require large and representative datasets which are difficult to obtain for complex biological samples. Inspired by the concept of deep image priors, we propose a deep-learning-based method that does not need any training set. Our framework relies on an untrained convolutional neural network to accurately unwrap the phase while ensuring the consistency of the measurements. We experimentally demonstrate that the proposed method faithfully recovers the phase of complex samples on both real and simulated data. Our work paves the way to reliable phase imaging of thick and complex samples with QPI.

READ FULL TEXT

page 7

page 19

page 25

page 26

page 28

page 29

page 30

page 31

research
05/10/2017

Phase recovery and holographic image reconstruction using deep learning in neural networks

Phase recovery from intensity-only measurements forms the heart of coher...
research
04/25/2022

Tensorial tomographic differential phase-contrast microscopy

We report Tensorial Tomographic Differential Phase-Contrast microscopy (...
research
09/28/2021

Deep Unrolled Recovery in Sparse Biological Imaging

Deep algorithm unrolling has emerged as a powerful model-based approach ...
research
03/29/2021

Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples

Recovering 3D phase features of complex, multiple-scattering biological ...
research
04/14/2020

On the interplay between physical and content priors in deep learning for computational imaging

Deep learning (DL) has been applied extensively in many computational im...
research
06/15/2022

High-fidelity quantitative differential phase contrast deconvolution using dark-field sparse prior

Differential phase contrast (DPC) imaging plays an important role in the...

Please sign up or login with your details

Forgot password? Click here to reset