GPU-based deep convolutional neural network for tomographic phase microscopy with ℓ1 fitting and regularization.

Hui Qiao,Jiamin Wu

doi:10.1117/1.jbo.23.6.066003

Abstract

Tomographic phase microscopy (TPM) is a unique imaging modality to measure the three-dimensional refractive index distribution of transparent and semitransparent samples. However, the requirement of the dense sampling in a large range of incident angles restricts its temporal resolution and prevents its application in dynamic scenes. Here, we propose a graphics processing unit-based implementation of a deep convolutional neural network to improve the performance of phase tomography, especially with much fewer incident angles. As a loss function for the regularized TPM, the ℓ1-norm sparsity constraint is introduced for both data-fidelity term and gradient-domain regularizer in the multislice beam propagation model. We compare our method with several state-of-the-art algorithms and obtain at least 14dB improvement in signal-to-noise ratio. Experimental results on HeLa cells are also shown with different levels of data reduction.

Highlights

Most biological samples such as live cells have low contrast in intensity but exhibit strong phase contrast
Phase contrast microscopy is widely applied in various biomedical imaging applications.[1]
The development of quantitative phase imaging[2,3] gives rise to a label-free imaging modality, tomographic phase microscopy (TPM), which deals with the three-dimensional (3-D) refractive index distribution of the sample.[4,5,6]

Summary

Introduction

Most biological samples such as live cells have low contrast in intensity but exhibit strong phase contrast. Phase contrast microscopy is widely applied in various biomedical imaging applications.[1] In the past decades, the development of quantitative phase imaging[2,3] gives rise to a label-free imaging modality, tomographic phase microscopy (TPM), which deals with the three-dimensional (3-D) refractive index distribution of the sample.[4,5,6] The label-free and noninvasive character makes it attractive in biomedical imaging, especially for cultured cells.[7,8]. Most of the current methods require around 50 quantitative phase images acquired at different angles[9,10,11] or different depths[6] for optical tomography. This speed limitation greatly restricts its field of applications. Another challenge for TPM is the missing cone problem, which limits its reconstruction performance, especially for limited axial resolution compared with the subnanometer optical-path-length sensitivity.[12]

Methods

Results

Discussion

Conclusion