Learning-based lensless imaging through optically thick scattering media

Lyu, Meng; Wang, Hao; Li, Guowei; Zheng, Shourong; Situ, Guohai

doi:10.1117/1.ap.1.3.036002

Cited by 135 publications

(54 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, several groups have demonstrated multiple scattering models suitable for solving large-scale imaging problems [39,[54][55][56], which will be considered in our future work. Our model-based reconstruction approach is also constrained by unknown experimental variabilities that are difficult to be fully parameterized via an analytical model, which may be overcome using emerging learning-based inversion techniques [57][58][59][60][61][62][63][64].…”

Section: Discussionmentioning

confidence: 99%

High-speed in vitro intensity diffraction tomography

Li¹,

Matlock²,

Li³

et al. 2019

Advanced Optical Imaging Technologies II

View full text Add to dashboard Cite

We demonstrate a label-free, scan-free intensity diffraction tomography technique utilizing annular illumination (aIDT) to rapidly characterize large-volume 3D refractive index distributions in vitro. By optimally matching the illumination geometry to the microscope pupil, our technique reduces the data requirement by 60× to achieve highspeed 10 Hz volume rates. Using 8 intensity images, we recover ∼ 350 × 100 × 20µm 3 volumes with near diffraction-limited lateral resolution of 487 nm and axial resolution of 3.4 µm. Our technique's large volume rate and high resolution enables 3D quantitative phase imaging of complex living biological samples across multiple length scales. We demonstrate aIDT's capabilities on unicellular diatom microalgae, epithelial buccal cell clusters with native bacteria, and live Caenorhabditis elegans specimens. Within these samples, we recover macro-scale cellular structures, subcellular organelles, and dynamic micro-organism tissues with minimal motion artifacts. Quantifying such features has significant utility in oncology, immunology, and cellular pathophysiology, where these morphological features are evaluated for changes in the presence of disease, parasites, and new drug treatments. Finally, we simulate our aIDT system to highlight the accuracy and sensitivity of our technique. aIDT shows promise as a powerful high-speed, label-free computational microscopy technique applications where natural imaging is required to evaluate environmental effects on a sample in real-time. We provide example datasets and an open source implementation of aIDT at https://github.com/bu-cisl/IDT-using-Annular-Illumination.

show abstract

Section: Discussionmentioning

confidence: 99%

High-speed in vitro intensity diffraction tomography

Li¹,

Matlock²,

Li³

et al. 2019

Advanced Optical Imaging Technologies II

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning receives much attention in many research fields including optical design [1,2] and optical imaging [3]. In previous works, deep learning has been extensively applied for many optical imaging problems including phase retrieval [4][5][6][7], microscopic image enhancement [8][9], scattering imaging [10][11], holography [12][13][14][15][16][17][18], single-pixel imaging [19,20], super-resolution [21][22][23][24], Fourier ptychography [25][26][27], optical interferometry [28,29], wavefront sensing [30,31], and optical fiber communications [32].…”

Section: Introductionmentioning

confidence: 99%

Does deep learning always outperform simple linear regression in optical imaging?

et al. 2020

View full text Add to dashboard Cite

Deep learning has been extensively applied in many optical imaging problems in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box optical imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.

show abstract

“…Our model-based reconstruction approach is also constrained by unknown experimental variabilities that are difficult to be fully parameterized via an analytical model, which may be overcome using emerging learning-based inversion techniques. [57][58][59][60][61][62][63][64] We provide example datasets and an open-source implementation of aIDT at GitHub repository available at https://github .com/bu-cisl/IDT-using-Annular-Illumination. See also the Supplementary Material for supporting content.…”

Section: Discussionmentioning

confidence: 99%

High-speed in vitro intensity diffraction tomography

Matlock

et al. 2019

Adv. Photon.

109

View full text Add to dashboard Cite

We demonstrate a label-free, scan-free intensity diffraction tomography technique utilizing annular illumination (aIDT) to rapidly characterize large-volume three-dimensional (3-D) refractive index distributions in vitro. By optimally matching the illumination geometry to the microscope pupil, our technique reduces the data requirement by 60 times to achieve high-speed 10-Hz volume rates. Using eight intensity images, we recover volumes of ∼350 μm × 100 μm × 20 μm, with near diffraction-limited lateral resolution of ∼487 nm and axial resolution of ∼3.4 μm. The attained large volume rate and high-resolution enable 3-D quantitative phase imaging of complex living biological samples across multiple length scales. We demonstrate aIDT's capabilities on unicellular diatom microalgae, epithelial buccal cell clusters with native bacteria, and live Caenorhabditis elegans specimens. Within these samples, we recover macroscale cellular structures, subcellular organelles, and dynamic microorganism tissues with minimal motion artifacts. Quantifying such features has significant utility in oncology, immunology, and cellular pathophysiology, where these morphological features are evaluated for changes in the presence of disease, parasites, and new drug treatments. Finally, we simulate the aIDT system to highlight the accuracy and sensitivity of the proposed technique. aIDT shows promise as a powerful high-speed, label-free computational microscopy approach for applications where natural imaging is required to evaluate environmental effects on a sample in real time.

show abstract

Learning-based lensless imaging through optically thick scattering media

Cited by 135 publications

References 38 publications

High-speed in vitro intensity diffraction tomography

High-speed in vitro intensity diffraction tomography

Does deep learning always outperform simple linear regression in optical imaging?

High-speed in vitro intensity diffraction tomography

Contact Info

Product

Resources

About