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

и другие.

Опубликована: Ноя. 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

Язык: Английский

Multi-culture label-free quantitative cell migration sensing with single-cell precision DOI Creative Commons
Piotr Arcab, Mikołaj Rogalski, Marcin Marzejon

и другие.

Biomedical Optics Express, Год журнала: 2024, Номер 16(1), С. 222 - 222

Опубликована: Ноя. 13, 2024

A fair comparison of multiple live cell cultures requires examining them under identical environmental conditions, which can only be done accurately if all cells are prepared simultaneously and studied at the same time place. This contribution introduces a multiplexed lensless digital holographic microscopy system (MLS), enabling synchronous, label-free, quantitative observation with single-cell precision. The innovation this setup lies in its ability to robustly compare behaviour, i.e., migratory pathways, cultured or contained different ways (with varied stimuli applied), making it valuable tool for dynamic biomedical diagnostics on cellular level. system's design allows potential expansion accommodate as many samples needed, thus broadening application scope future global multi-culture behaviours via their localized spatiotemporal optical signatures. We believe that our method has empower reliable comparisons through simultaneous imaging, enhancing label-free investigations into effects biochemical physical over large areas, unlocking novel mechanistic understandings high-throughput time-lapse observations.

Язык: Английский

Процитировано

1

Quantitative study of phase sensitivity in immersion-based lensless digital holographic microscopy DOI
Emilia Wdowiak, Mikołaj Rogalski, Maciej Trusiak

и другие.

Опубликована: Янв. 26, 2024

This study introduces a methodology for quantitative assessment of phase measurement sensitivity in lensless digital holographic microscopy (LDHM) setups, incorporating an immersion medium between the object and detector. Utilizing two setup configurations, we systematically investigated influence conditions on accuracy, numerical reconstruction, twin-image artefacts. Employing Angular Spectrum iterative Gerchberg-Saxton methods, reconstructed maps varying thicknesses. Results demonstrate that has minimal but significantly reduces artifacts when direct contact with object, providing valuable insights developing LDHM biological applications.

Язык: Английский

Процитировано

0

Computational optical sensing and imaging: introduction to the feature issue DOI Creative Commons
Prasanna Rangarajan, Daniele Faccio, Seung Ah Lee

и другие.

Optics Express, Год журнала: 2024, Номер 32(10), С. 17255 - 17255

Опубликована: Фев. 21, 2024

This joint feature issue of Optics Express and Applied showcases technical innovations by participants the 2023 topical meeting on Computational Optical Sensing Imaging computational imaging community. The articles included in highlight advances science that emphasize synergistic activities optics, signal processing machine learning. features 26 contributed cover multiple themes including non line-of-sight imaging, through scattering media, compressed sensing, lensless ptychography, microscopy, spectroscopy optical metrology.

Язык: Английский

Процитировано

0

Computational Optical Sensing and Imaging: introduction to the feature issue DOI
Prasanna Rangarajan

Applied Optics, Год журнала: 2024, Номер 63(8), С. COSI1 - COSI1

Опубликована: Фев. 21, 2024

This joint feature issue of Optics Express and Applied showcases technical innovations by participants the 2023 topical meeting on Computational Optical Sensing Imaging computational imaging community. The articles included in highlight advances science that emphasize synergistic activities optics, signal processing machine learning. features 26 contributed cover multiple themes including non line-of-sight imaging, through scattering media, compressed sensing, lensless ptychography, microscopy, spectroscopy optical metrology.

Язык: Английский

Процитировано

0

Method for In-line Holographic Microscopy Reconstruction of Low Signal-to-noise Ratio Holograms DOI
Mikołaj Rogalski, Piotr Arcab, Maciej Trusiak

и другие.

Опубликована: Янв. 1, 2024

This work presents an in-line holographic reconstruction method for low signal-to-noise ratio data. Algorithm is positively validated in terms of shot noise suppression, twin image minimization and high lateral resolution.

Язык: Английский

Процитировано

0

Averaging fractional Fourier domains for background noise removal applied to digital lensless holographic microscopy DOI
Carlos Trujillo, René Restrepo, Jorge Garcı́a-Sucerquia

и другие.

Optik, Год журнала: 2024, Номер unknown, С. 172035 - 172035

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

0

Quantitative phase imaging verification in large field-of-view lensless holographic microscopy via two-photon 3D printing DOI Creative Commons
Emilia Wdowiak, Mikołaj Rogalski, Piotr Arcab

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 9, 2024

Язык: Английский

Процитировано

0

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

и другие.

Опубликована: Ноя. 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

Язык: Английский

Процитировано

0