Deep Learning-Based Holographic Polarization Microscopy

Abstract

Polarized light microscopy provides high contrast to birefringent specimen and is widely used as a diagnostic tool in pathology. However, polarization microscopy systems typically operate by analyzing images collected from two or more light paths in different states of polarization, which lead to relatively complex optical designs, high system costs, or experienced technicians being required. Here, we present a deep learning-based holographic polarization microscope that is capable of obtaining quantitative birefringence retardance and orientation information of specimen from a phase-recovered hologram, while only requiring the addition of one polarizer/analyzer pair to an inline lensfree holographic imaging system. Using a deep neural network, the reconstructed holographic images from a single state of polarization can be transformed into images equivalent to those captured using a single-shot computational polarized light microscope (SCPLM). Our analysis shows that a trained deep neural network can extract the birefringence information using both the sample specific morphological features as well as the holographic amplitude and phase distribution. To demonstrate the efficacy of this method, we tested it by imaging various birefringent samples including, for example, monosodium urate and triamcinolone acetonide crystals. Our method achieves similar results to SCPLM both qualitatively and quantitatively, and due to its simpler optical design and significantly larger field-of-view this method has the potential to expand the access to polarization microscopy and its use for medical diagnosis in resource limited settings.

Calcium pyrophosphate crystal size and characteristics

“…Advances described here and in other areas, such as dual-energy computed tomography (DECT) detection of CPP deposition [ 24 ], may help improve the understanding of this prevalent condition. Our group has reported on lens-free polarized light microscopy and SCPLM as novel methods for crystal arthropathy diagnosis, with higher contrast and wider FOV than traditional CPLM [ 16 , 17 ]. Given these features, we hope these advanced imaging systems will lead to more accurate, less labor-intensive, and less operator-dependent crystal detection when compared to standard CPLM.…”

“…To address the inherent challenges of CPLM for crystal arthropathy diagnosis, our group developed advanced microscopic imaging methods, including a lens-free polarized imaging system that directly images crystals using a light source and complementary metal-oxide-semiconductor (CMOS) [ 16 ] and a single-shot computational polarized light microscopy (SCPLM) system that uses an industrial polarization CMOS image sensor [ 17 ]. We undertook this project to better define the size and shape of CPP crystals as a reference database for these projects.…”

Computational imaging without a computer: seeing through random diffusers at the speed of light

“…Some of the more recent work on imaging through diffusers has also focused on using deep learning methods to digitally recover the images of unknown objects [11,12,48,49]. Deep learning has been re-defining the state-of-the-art across many areas in optics, including optical microscopy [50][51][52][53][54][55], holography [56][57][58][59][60][61], inverse design of optical devices [62][63][64][65][66][67], optical computation and statistical inference [68][69][70][71][72][73][74][75][76][77], among others [78][79][80].…”

Comprehensive deep learning model for 3D color holography

“…In contrast to these algorithms, deep learning correlates an intensity distribution to a hologram without reconstruction of phase and amplitude information from an intensity distribution thanks to its data-driven approach. Deep learning is a superior tool that presents important achievement especially in holography for imaging [25][26][27][28], microscopy [29][30][31][32], optical trapping [33], and molecular diagnostics [34].…”