High space-bandwidth in quantitative phase imaging using partially spatially coherent digital holographic microscopy and a deep neural network

A novel approach in cancer diagnosis: integrating holography microscopic medical imaging and deep learning techniques-challenges and future trends

Medical imaging is pivotal in early disease diagnosis, providing essential insights that enable timely and accurate detection of health anomalies. Traditional imaging techniques, such as Magnetic Resonance Imaging (MRI), Computer Tomography (CT), ultrasound, and Positron Emission Tomography (PET), offer vital insights into three-dimensional structures but frequently fall short of delivering a comprehensive and detailed anatomical analysis, capturing only amplitude details. Three-dimensional holography microscopic medical imaging provides a promising solution by capturing the amplitude (brightness) and phase (structural information) details of biological structures. In this study, we investigate the novel collaborative potential of Deep Learning (DL) and holography microscopic phase imaging for cancer diagnosis. The study comprehensively examines existing literature, analyzes advancements, identifies research gaps, and proposes future research directions in cancer diagnosis through the integrated Quantitative Phase Imaging (QPI) and DL methodology. This novel approach addresses a critical limitation of traditional imaging by capturing detailed structural information, paving the way for more accurate diagnostics. The proposed approach comprises tissue sample collection, holographic image scanning, preprocessing in case of imbalanced datasets, and training on annotated datasets using DL architectures like U-Net and Vision Transformer(ViT's). Furthermore, sophisticated concepts in DL, like the incorporation of Explainable AI (XAI) techniques, are suggested for comprehensive disease diagnosis and identification. The study thoroughly investigates the advantages of integrating holography imaging and DL for precise cancer diagnosis. Additionally, meticulous insights are presented by identifying the challenges associated with this integration methodology.

Resolution-enhanced quantitative phase imaging of blood platelets using a generative adversarial network

We developed a new method to enhance the resolution of blood platelet aggregates imaged via quantitative phase imaging (QPI) using a Pix2Pix generative adversarial network (GAN). First, 1 µm polystyrene beads were imaged with low- and high-resolution QPI, to train the GAN model and validate its applicability. Testing on the polystyrene beads demonstrated a mean error of 4.14% in the generated high-resolution optical-path-delay values compared to the optically acquired ones. Next, blood platelets were collected with low- and high-resolution QPI, and a deep neural network was trained to predict the high-resolution platelet optical-path-delay profiles using the low-resolution profiles, achieving a mean error of 7.01% in the generated high-resolution optical-path-delay values compared to the optically acquired ones. These results highlight the potential of the method in enhancing QPI resolution of cell aggregates without the need for sophisticated optical equipment and optical system modifications for high-resolution microscopy, allowing for better understanding of platelet-related disorders and conditions such as thrombocytopenia and thrombocytosis.

Characterizing the consistency of motion of spermatozoa through nanoscale motion tracing

OBJECTIVE

To demonstrate nanoscale motion tracing of spermatozoa and present analysis of the motion traces to characterize the consistency of motion of spermatozoa as a complement to progressive motility analysis.

DESIGN

Anonymized sperm samples were videographed under a quantitative phase microscope, followed by generating and analyzing superresolution motion traces of individual spermatozoa.

SETTING

Not applicable.

PATIENT(S)

Centrifuged human sperm samples.

INTERVENTION(S)

Not applicable.

MAIN OUTCOME MEASURE(S)

Precision of motion trace of individual sperms, presence of a helical pattern in the motion trace, mean and standard deviations of helical periods and radii of sperm motion traces, speed of progression.

RESULT(S)

Spatially sensitive quantitative phase imaging with a superresolution computational technique MUltiple SIgnal Classification ALgorithm allowed achieving motion precision of 340 nm using ×10, 0.25 numerical aperture lens whereas the diffraction-limited resolution at this setting was 1,320 nm. The motion traces thus derived facilitated new kinematic features of sperm, namely the statistics of helix period and radii per sperm. Through the analysis, 47 sperms with a speed >25 μm/s were randomly selected from the same healthy donor semen sample, it is seen that the kinematic features did not correlate with the speed of the sperms. In addition, it is noted that spermatozoa may experience changes in the periodicity and radius of the helical path over time. Further, some very fast sperms (e.g., >70 μm/s) may demonstrate irregular motion and need further investigation. Presented computational analysis can be used directly for sperm samples from both fertility patients with normal and abnormal sperm cell conditions. We note that MUltiple SIgnal Classification ALgorithm is an image analysis technique that may vaguely fall under the machine learning category, but the conventional metrics for reporting found in Enhancing the QUAlity and Transparency Of health Research network do not apply. Alternative suitable metrics are reported, and bias is avoided through random selection of regions for analysis. Detailed methods are included for reproducibility.

CONCLUSION(S)

Kinematic features derived from nanoscale motion traces of spermatozoa contain information complementary to the speed of the sperms, allowing further distinction among the progressively motile sperms. Some highly progressive spermatozoa may have irregular motion patterns, and whether irregularity of motion indicates poor quality regarding artificial insemination needs further investigation. The presented technique can be generalized for sperm analysis for a variety of fertility conditions.

On the use of deep learning for phase recovery

Phase recovery (PR) refers to calculating the phase of the light field from its intensity measurements. As exemplified from quantitative phase imaging and coherent diffraction imaging to adaptive optics, PR is essential for reconstructing the refractive index distribution or topography of an object and correcting the aberration of an imaging system. In recent years, deep learning (DL), often implemented through deep neural networks, has provided unprecedented support for computational imaging, leading to more efficient solutions for various PR problems. In this review, we first briefly introduce conventional methods for PR. Then, we review how DL provides support for PR from the following three stages, namely, pre-processing, in-processing, and post-processing. We also review how DL is used in phase image processing. Finally, we summarize the work in DL for PR and provide an outlook on how to better use DL to improve the reliability and efficiency of PR. Furthermore, we present a live-updating resource ( https://github.com/kqwang/phase-recovery ) for readers to learn more about PR.

A Novel Image Processing Method for Obtaining an Accurate Three-Dimensional Profile of Red Blood Cells in Digital Holographic Microscopy

Recently, research on disease diagnosis using red blood cells (RBCs) has been active due to the advantage that it is possible to diagnose many diseases with a drop of blood in a short time. Representatively, there are disease diagnosis technologies that utilize deep learning techniques and digital holographic microscope (DHM) techniques. However, three-dimensional (3D) profile obtained by DHM has a problem of random noise caused by the overlapping DC spectrum and sideband in the Fourier domain, which has the probability of misjudging diseases in deep learning technology. To reduce random noise and obtain a more accurate 3D profile, in this paper, we propose a novel image processing method which randomly selects the center of the high-frequency sideband (RaCoHS) in the Fourier domain. This proposed algorithm has the advantage of filtering while using only recorded hologram information to maintain high-frequency information. We compared and analyzed the conventional filtering method and the general image processing method to verify the effectiveness of the proposed method. In addition, the proposed image processing algorithm can be applied to all digital holography technologies including DHM, and in particular, it is expected to have a great effect on the accuracy of disease diagnosis technologies using DHM.

Photolithographic patterning on multi-wavelength quantum dot film of the improved conversion efficiency for digital holography

A triple-wavelength patterned quantum dot film was fabricated for the light source of digital holography to improve both the axial measurement range and noise reduction. The patterned quantum dot film was fabricated after optimizing the photolithography process condition based on the UV-curable quantum dot solution, which was capable of multiple patterning processes. In addition, an optimized pattern structure was developed by adding TiO2 nanoparticles to both the quantum dot and bank layers to increase the scattering effect for the improved photoluminescence intensity. Finally, the newly developed light source with the balanced spectral distribution was applied to the digital holography, rendering it applicable as an improved light source.

Preprocessing methods for quantitative phase image stitching

Quantitative phase imaging of cell cultures and histopathological slides often requires measurements in large fields of view which is realized through the stitching of multiple high resolution phase maps. Due to the characteristic properties of phase images, careful preprocessing is crucial for maintaining the metrological value of the stitched phase image. In this work, we present various methods that address those properties. Our efforts are focused on increasing robustness to minimize error propagation in consecutive preprocessing steps.

Enhancement of image sharpness and height measurement using a low-speckle light source based on a patterned quantum dot film in dual-wavelength digital holography

A dual-wavelength single light source based on a patterned quantum dot (QD) film was developed with a 405nm LED and bandpass filters to increase color conversion efficiency as well as to decouple the two peaks of dual-wavelength emitted from the QD film. A QD film was patterned laterally with two different sizes of QDs and was combined with bandpass filters to produce a high efficiency and low-speckle dual-wavelength light source. The experimental results showed that the developed dual-wavelength light source can decrease speckle noise to improve the reconstructed image sharpness and the accuracy on height measurement in dual-wavelength digital holography.

Single-shot fringe pattern phase retrieval using improved period-guided bidimensional empirical mode decomposition and Hilbert transform

Fringe pattern analysis is the central aspect of numerous optical measurement methods, e.g., interferometry, fringe projection, digital holography, quantitative phase microscopy. Experimental fringe patterns always contain significant features originating from fluctuating environment, optical system and illumination quality, and the sample itself that severely affect analysis outcome. Before the stage of phase retrieval (information decoding) interferogram needs proper filtering, which minimizes the impact of mentioned issues. In this paper we propose fully automatic and adaptive fringe pattern pre-processing technique - improved period guided bidimensional empirical mode decomposition algorithm (iPGBEMD). It is based on our previous work about PGBEMD which eliminated the mode-mixing phenomenon and made the empirical mode decomposition fully adaptive. In present work we overcame key problems of original PGBEMD - we have considerably increased algorithm's application range and shortened computation time several-fold. We proposed three solutions to the problem of erroneous decomposition for very low fringe amplitude images, which limited original PGBEMD significantly and we have chosen the best one among them after comprehensive analysis. Several acceleration methods were also proposed and merged to ensure the best results. We combined our improved pre-processing algorithm with the Hilbert Spiral Transform to receive complete, consistent, and versatile fringe pattern analysis path. Quality and effectiveness evaluation, in comparison with selected reference methods, is provided using numerical simulations and experimental fringe data.

High-resolution single-shot phase-shifting interference microscopy using deep neural network for quantitative phase imaging of biological samples

White light phase-shifting interference microscopy (WL-PSIM) is a prominent technique for high-resolution quantitative phase imaging (QPI) of industrial and biological specimens. However, multiple interferograms with accurate phase-shifts are essentially required in WL-PSIM for measuring the accurate phase of the object. Here, we present single-shot phase-shifting interferometric techniques for accurate phase measurement using filtered white light (520±36 nm) phase-shifting interference microscopy (F-WL-PSIM) and deep neural network (DNN). The methods are incorporated by training the DNN to generate (a) four phase-shifted frames and (b) direct phase from a single interferogram. The training of network is performed on two different samples i.e., optical waveguide and MG63 osteosarcoma cells. Further, performance of F-WL-PSIM+DNN framework is validated by comparing the phase map extracted from network generated and experimentally recorded interferograms. The current approach can further strengthen QPI techniques for high-resolution phase recovery using a single frame for different biomedical applications.