Computational interference microscopy enabled by deep learning.

Wenlong Lu,Yuchen R. He,Yuheng Jiao,Xiaojun Liu,Mikhail E. Kandel,Gabriel Popescu

doi:10.1063/5.0041901

Abstract

Quantitative phase imaging (QPI) has been widely applied in characterizing cells and tissues. Spatial light interference microscopy (SLIM) is a highly sensitive QPI method due to its partially coherent illumination and common path interferometry geometry. However, SLIM’s acquisition rate is limited because of the four-frame phase-shifting scheme. On the other hand, off-axis methods such as diffraction phase microscopy (DPM) allow for single-shot QPI. However, the laser-based DPM system is plagued by spatial noise due to speckles and multiple reflections. In a parallel development, deep learning was proven valuable in the field of bioimaging, especially due to its ability to translate one form of contrast into another. Here, we propose using deep learning to produce synthetic, SLIM-quality, and high-sensitivity phase maps from DPM using single-shot images as the input. We used an inverted microscope with its two ports connected to the DPM and SLIM modules such that we have access to the two types of images on the same field of view. We constructed a deep learning model based on U-net and trained on over 1000 pairs of DPM and SLIM images. The model learned to remove the speckles in laser DPM and overcame the background phase noise in both the test set and new data. The average peak signal-to-noise ratio, Pearson correlation coefficient, and structural similarity index measure were 29.97, 0.79, and 0.82 for the test dataset. Furthermore, we implemented the neural network inference into the live acquisition software, which now allows a DPM user to observe in real-time an extremely low-noise phase image. We demonstrated this principle of computational interference microscopy imaging using blood smears, as they contain both erythrocytes and leukocytes, under static and dynamic conditions.

Highlights

Quantitative phase imaging (QPI) has developed into an active field with the goal of providing a label-free alternative to biomedical imaging, complementary to the standard techniques relying on stains and fluorescent tags.1 QPI yields the optical path length map associated with the specimen and, informs about both the thickness and the refractive index of the structure of interest
In order to acquire training data necessary to produce SLIMquality images in a single-shot, we developed a combined SLIMDPM system, which generates both images from the same field of view (Fig. 1)
The diffraction phase microscopy (DPM) and Spatial light interference microscopy (SLIM) modules were placed at the two side ports of a commercial inverted microscope (Axio Observer Z1, Zeiss)

Summary

Introduction

Quantitative phase imaging (QPI) has developed into an active field with the goal of providing a label-free alternative to biomedical imaging, complementary to the standard techniques relying on stains and fluorescent tags. QPI yields the optical path length map associated with the specimen and, informs about both the thickness and the refractive index of the structure of interest. QPI yields the optical path length map associated with the specimen and, informs about both the thickness and the refractive index of the structure of interest. The full holographic information (phase and amplitude) associated with a field scattered by a transparent object allows for tomographic reconstructions without ambiguity, as demonstrated by Wolf in 1969.16 QPI-based tomography has been demonstrated by acquiring phase imaging data as a function of illumination angles, scanning the object through focus, and performing spectroscopic measurements.. The full holographic information (phase and amplitude) associated with a field scattered by a transparent object allows for tomographic reconstructions without ambiguity, as demonstrated by Wolf in 1969.16 QPI-based tomography has been demonstrated by acquiring phase imaging data as a function of illumination angles, scanning the object through focus, and performing spectroscopic measurements.22 This approach has been recently extended to second harmonic fields.. Due to its quantitative and nondestructive nature, QPI has found important biomedical applications ranging from basic science to clinical diagnosis. As the specimen refractive index reports on the dry mass density, QPI has been employed to study cell growth. Analyzing the spatio-temporal fluctuations of dry mass provided a new way of monitoring intracellular transport and differentiating between diffusive and active processes. Due to its sensitivity to nanometer scale optical path length changes, QPI is capable of measuring cell membrane fluctuations and imaging unlabeled single microtubules. The full holographic information (phase and amplitude) associated with a field scattered by a transparent object allows for tomographic reconstructions without ambiguity, as demonstrated by Wolf in 1969.16 QPI-based tomography has been demonstrated by acquiring phase imaging data as a function of illumination angles, scanning the object through focus, and performing spectroscopic measurements. This approach has been recently extended to second harmonic fields. QPI has led to the discovery of new intrinsic markers for cancer diagnosis and prognosis without the variability generally introduced by stains. More recently, QPI has been extended to strongly scattering specimens, such as scitation.org/journal/app embryos, spheroids, and acute brain slices, which significantly expanded QPI’s range of applications

Methods

Results

Conclusion