ACNet: a twin-image removal network based on CNN with attention mechanism in in-line lensless digital holographic microscopy DOI

Hongda Quan,

Wenqi Shi,

Lingbao Kong

et al.

Published: Nov. 13, 2024

Transparent objects are extensively utilized across various aspects, yet their non-destructive optical measurement remains challenging. In-line lensless digital holography has emerged as an efficient and precise technique for detecting transparent objects, with the advantages of simpler device requirements more effective utilization detector limited spacebandwidth product. However, presence twin-image significantly degrades quality reconstructed images. Conventional approaches to mitigating require intricate hardware configurations or time-consuming algorithms. In this paper, we proposed a new network called Attention mechanism in Convolutional neural Network (ACNet), which provides fast deep learning solution twin image suppression. The approach numerically generated datasets training convolutional (CNN) was employed attention perform removal. Simulation results demonstrate that method effectively eliminates interference phase recovery, thereby enhances reconstruction in-line holography. present work great potentials wider applications

Language: Английский

Roadmap on computational methods in optical imaging and holography [invited] DOI Creative Commons
Joseph Rosen, Simon Alford, Blake M. Allan

et al.

Applied Physics B, Journal Year: 2024, Volume and Issue: 130(9)

Published: Aug. 29, 2024

Computational methods have been established as cornerstones in optical imaging and holography recent years. Every year, the dependence of on computational is increasing significantly to extent that components are being completely efficiently replaced with at low cost. This roadmap reviews current scenario four major areas namely incoherent digital holography, quantitative phase imaging, through scattering layers, super-resolution imaging. In addition registering perspectives modern-day architects above research areas, also reports some latest studies topic. codes pseudocodes presented for a plug-and-play fashion readers not only read understand but practice algorithms their data. We believe this will be valuable tool analyzing trends predict prepare future holography.

Language: Английский

Citations

13
Physics-driven universal twin-image removal network for digital in-line holographic microscopy DOI Creative Commons
Mikołaj Rogalski, Piotr Arcab, Luiza Stanaszek

et al.

Optics Express, Journal Year: 2023, Volume and Issue: 32(1), P. 742 - 742

Published: Nov. 24, 2023

Digital in-line holographic microscopy (DIHM) enables efficient and cost-effective computational quantitative phase imaging with a large field of view, making it valuable for studying cell motility, migration, bio-microfluidics. However, the quality DIHM reconstructions is compromised by twin-image noise, posing significant challenge. Conventional methods mitigating this noise involve complex hardware setups or time-consuming algorithms often limited effectiveness. In work, we propose UTIRnet, deep learning solution fast, robust, universally applicable suppression, trained exclusively on numerically generated datasets. The availability open-source UTIRnet codes facilitates its implementation in various systems without need extensive experimental training data. Notably, our network ensures consistency reconstruction results input holograms, imparting physics-based foundation enhancing reliability compared to conventional approaches. Experimental verification was conducted among others live neural glial culture migration sensing, which crucial neurodegenerative disease research.

Language: Английский

Citations

18
Clinical and Biomedical Applications of Lensless Holographic Microscopy DOI
Colin J. Potter, Zhen Xiong, Euan McLeod

et al.

Laser & Photonics Review, Journal Year: 2024, Volume and Issue: 18(10)

Published: May 16, 2024

Abstract Many clinical procedures and biomedical research workflows rely on microscopy, including diagnosis of cancer, genetic disorders, autoimmune diseases, infections, quantification cell culture. Despite its widespread use, traditional image acquisition review by trained microscopists is often lengthy expensive, limited to large hospitals or laboratories, precluding use in point‐of‐care settings. In contrast, lensless lensfree holographic microscopy (LHM) inexpensive widely deployable because it can achieve performance comparable expensive bulky objective‐based benchtop microscopes while relying components that cost only a few hundred dollars less. Lab‐on‐a‐chip integration practical enables LHM be combined with single‐cell isolation, sample mixing, in‐incubator imaging. Additionally, many manual tasks conventional are instead computational LHM, focusing, stitching, classification. Furthermore, offers field view hundreds times greater than without sacrificing resolution. Here, the basic principles summarized, as well recent advances artificial intelligence enhanced How applied above applications discussed detail. Finally, emerging applications, high‐impact areas for future research, some current challenges facing adoption identified.

Language: Английский

Citations

8
Single-shot inline holography using a physics-aware diffusion model DOI Creative Commons
Yunping Zhang, Xihui Liu, Edmund Y. Lam

et al.

Optics Express, Journal Year: 2024, Volume and Issue: 32(6), P. 10444 - 10444

Published: Feb. 27, 2024

Among holographic imaging configurations, inline holography excels in its compact design and portability, making it the preferred choice for on-site or field applications with unique requirements. However, effectively reconstruction from a single-shot measurement remains challenge. While several approaches have been proposed, our novel unsupervised algorithm, physics-aware diffusion model digital (PadDH), offers distinct advantages. By seamlessly integrating physical information pre-trained model, PadDH overcomes need training dataset significantly reduces number of parameters involved. Through comprehensive experiments using both synthetic experimental data, we validate capabilities reducing twin-image contamination generating high-quality reconstructions. Our work represents significant advancements by harnessing full potential prior.

Language: Английский

Citations

7
Hybrid Iterating-Averaging Low Photon Budget Gabor Holographic Microscopy DOI Creative Commons
Mikołaj Rogalski, Piotr Arcab, Emilia Wdowiak

et al.

ACS Photonics, Journal Year: 2025, Volume and Issue: 12(4), P. 1771 - 1782

Published: Jan. 10, 2025

Achieving high-contrast, label-free imaging with minimal impact on live cell culture behavior remains a primary challenge in quantitative phase (QPI). By enabling under low illumination intensities (low photon budget, LPB), it is possible to minimize photostimulation, phototoxicity, and photodamage while supporting long-term high-speed observations. However, LPB introduces significant difficulties QPI due high levels of camera shot noise quantification noise. Digital in-line holographic microscopy (DIHM) technique known for its robustness against data. simultaneous minimization inherent DIHM twin image perturbation critical challenge. In this study, we present the iterative Gabor averaging (IGA) algorithm, novel approach that integrates retrieval frame effectively suppress both disturbance multiframe DIHM. The IGA algorithm achieves by leveraging an process reconstructs high-fidelity images selectively across frames. Our simulations demonstrate consistently outperforms conventional methods, achieving superior reconstruction accuracy, particularly high-noise conditions. Experimental validations involving dynamic sperm cells static test target measurement further confirmed IGA's efficacy. also proved successful optically thin samples, which often yield signal-to-noise holograms even at budgets. These advancements make powerful tool photostimulation-free, biological samples enhance ability extremely optical thickness, potentially transforming biomedical environmental applications low-light settings.

Language: Английский

Citations

0
Phase-Driven Classification for Improved Detection of Malaria-Infected Red Blood Cells in Digital Holographic Microscopy DOI

Charlotte Kyeremah,

Aditya S. Paul, Daniel Haehn

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Abstract Digital holographic microscopy (DHM) has emerged as a powerful, label-free technique for visualizing and analyzing biological samples. By extracting the intrinsic optical properties of red blood cells (RBCs), DHM enables detection infection-induced morphological biophysical changes. Traditional classification methods often rely on feature-specific analysis, which can lead to misclassification when single parameter fails differentiate between uninfected infected cells. In this study, we present novel features-based approach that integrates multiple characteristics classify Plasmodium falciparum-infected RBCs obtained using lensless inline DHM. Our analysis shows phase-based features provide more reliable indicator compared features. Additionally, our approach, considers collectively, outperforms individual attributes. The parasitemia rate improved from 48% (feature-specific method) 61% (phase-based same sample set, demonstrating enhanced accuracy. Furthermore, proposed method achieved high specificity (98–100%), ensuring identification Although slightly underestimates Giemsa staining (90%), it offers significant advantage real-time, imaging tool, presenting promising avenue rapid automated malaria diagnosis.

Language: Английский

Citations

0
Phase retrieval via conjugate gradient minimization in double-plane lensless holographic microscopy DOI Creative Commons
Julianna Winnik, Damian Suski, Piotr Arcab

et al.

Optics Express, Journal Year: 2024, Volume and Issue: 32(16), P. 28666 - 28666

Published: June 14, 2024

Optimization-based phase retrieval method for digital lensless holographic microscopy in the double-plane recording configuration is proposed. In our framed as an optimization problem that can be efficiently and rigorously tackled with gradient decent tools. This done conjugate possesses excellent theoretical features such global fast convergence (compared to steepest descent) relatively low computational cost second order optimizers). The proposed extensively tested simulations experimental measurements show superiority of over Gerchberg-Saxton algorithm, especially terms reconstruction problematic frequency components viable information.

Language: Английский

Citations

2
Single-beam digital holographic reconstruction: a phase-support enhanced complex wavefront on phase-only function for twin-image elimination DOI Creative Commons

Charlotte Kyeremah,

Matthew Weiss,

D. D. Kandel

et al.

Journal of Biomedical Optics, Journal Year: 2024, Volume and Issue: 29(07)

Published: July 13, 2024

SignificanceIn in-line digital holographic microscopy (DHM), twin-image artifacts pose a significant challenge, and reduction or complete elimination is essential for object reconstruction.AimTo facilitate reconstruction using single hologram, significantly reduce inaccuracies, avoid iterative processing, algorithm called phase-support constraint on phase-only function (PCOF) presented.ApproachIn-line DHM simulations tabletop experiments employing the sliding-window approach are used to compute arithmetic mean variance of phase values in reconstructed image. A support mask, through thresholding, effectively enabled artifacts.ResultsQuantitative evaluations metrics such as squared error, peak signal-to-noise ratio, structural similarity index show PCOF's superior capability eliminating achieving high-fidelity reconstructions compared with conventional methods angular spectrum retrieval methods.ConclusionsPCOF stands promising reconstruction, offering robust solution mitigate enhance fidelity objects.

Language: Английский

Citations

2
Phase from defocus: transport of intensity or in-line holography? DOI
Mikołaj Rogalski, Piotr Arcab, Emilia Wdowiak

et al.

Published: Jan. 26, 2024

Quantitative phase imaging techniques (QPI) enable to observe transparent samples with high contrast and quantitative information about their optical thickness. Among the vast family of QPI methods, two them: (1) transport intensity equation (TIE) (2) digital in-line holographic microscopy (DIHM), rely on retrieving from several images collected different defocus. In this work, we preliminarily investigate, mainly numerically under simulated conditions, differences between those showing that TIE is more suitable for lower-frequency objects small defocus distance difference (around micrometers). On other hand, DIHM performs better higher frequency larger (hundreds Moreover, our results show achieves results, when all are relatively far focal plane (in millimeter range rather than in micrometer range), while parameter does not have a significant influence onto retrieved phase.

Language: Английский

Citations

1
基于物理模型驱动无监督学习的无透镜成像质量增强方法 DOI

左嘉乐 Zuo Jiale,

张蒙蒙 Zhang Mengmeng,

Ju Tang

et al.

Acta Optica Sinica, Journal Year: 2024, Volume and Issue: 44(16), P. 1611001 - 1611001

Published: Jan. 1, 2024

Citations

1