Robust Phase Unwrapping via Deep Image Prior for Quantitative Phase Imaging
This work addresses the challenge of reliable phase imaging for complex biological samples, offering an incremental improvement by removing the data requirement of supervised methods.
The authors tackled the problem of phase unwrapping in quantitative phase imaging for thick and complex samples like organoids, proposing a deep-learning method that eliminates the need for training datasets and achieves accurate phase recovery on real and simulated data.
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.