Optical imaging through diffuse media is a challenging issue and has attracted applications in many fields such as biomedical imaging, non-destructive testing, and computer-assisted surgery. However, light interaction with diffuse media leads to multiple scattering of the photons in the angular and spatial domain, severely degrading the image reconstruction process. In this article, a novel method to image through diffuse media using multiple modes of vortex beams and a new deep learning network named “LGDiffNet” is derived. A proof-of-concept numerical simulation is conducted using this method, and the results are experimentally verified. In this technique, the multiple modes of Gaussian and Laguerre-Gaussian beams illuminate the displayed digits dataset number, and the beams are then propagated through the diffuser before being captured on the beam profiler. Furthermore, we investigated whether imaging through diffuse media using multiple modes of vortex beams instead of Gaussian beams improves the imaging system's imaging capability and enhances the network's reconstruction ability. Our results show that illuminating the diffuser using vortex beams and employing the “LGDiffNet” network provides enhanced image reconstruction compared to existing modalities. When employing vortex beams for image reconstruction, the best NPCC is − 0.9850. However, when using Gaussian beams for imaging acquisition, the best NPCC is − 0.9837. An enhancement of 0.62 dB, in terms of PSNR, is achieved using this method when a highly scattering diffuser of grit 220 and width 2 mm (7.11 times the mean free path) is used. No additional optimizations or reference beams were used in the imaging system, revealing the robustness of the “LGDiffNet” network and the adaptability of the imaging system for practical applications in medical imaging.

Interest in optical wireless communications (OWC) as a possible complement to RF technology has increased recently. However, the propagation of optical beams through the atmosphere distorts the beam's amplitude and phase, resulting in information loss and significant noise. Arising due to a combination of multiple absorption and scattering events, the distortion of the beam makes optical communication difficult. In some cases, the orbital angular momentum of light (OAM), along with various deep learning algorithms (DL), could be helpful to mitigate the problem and provide high-capacity optical communication links. In this work, we propagate Laguerre-Gaussian (LG) beams with different topological charges ( l ) under diffuse and turbulent conditions and develop a deep-learning classification network to characterize the ‘ l ’ of the LG beam. The proposed method is later implemented using a laboratory setup demonstrating communication on the optical table. The results show that the proposed algorithm can identify the modes of the LG beam with high accuracy even when the optical beam propagates through highly turbulent and scattering media. To demonstrate the robustness of the proposed OWC system, small grayscale images are transmitted over the communication channel. A bit error rate (BER) of only $2.3 \times {10}^{ - 4}$ and $9.7 \times {10}^{ - 4}$ for the tabletop experiment and the simulations, respectively. The demonstrated low BER in the proposed OWC system suggests promising applications for secure and reliable data transmission in adverse atmospheric conditions, highlighting the potential of this method in advancing optical wireless communication technologies.

Diffuse optical tomography using deep learning is an emerging technology that has found impressive medical diagnostic applications. However, creating an optical imaging system that uses visible and near-infrared (NIR) light is not straightforward due to photon absorption and multi-scattering by tissues. The high distortion levels caused due to these effects make the image reconstruction incredibly challenging. To overcome these challenges, various techniques have been proposed in the past, with varying success. One of the most successful techniques is the application of deep learning algorithms in diffuse optical tomography. This article discusses the current state-of-the-art diffuse optical tomography systems and comprehensively reviews the deep learning algorithms used in image reconstruction. This article attempts to provide researchers with the necessary background and tools to implement deep learning methods to solve diffuse optical tomography.

Diffuse optical tomography (DOT) is a non-invasive imaging technique utilizing multi-scattered light at visible and infrared wavelengths to detect anomalies in tissues. However, the DOT image reconstruction is based on solving the inverse problem, which requires massive calculations and time. In this article, for the first time, to the best of our knowledge, a simple, regression-based cascaded feed-forward deep learning neural network is derived to solve the inverse problem of DOT in compressed breast geometry. The predicted data is subsequently utilized to visualize the breast tissues and their anomalies. The dataset in this study is created using a Monte-Carlo algorithm, which simulates the light propagation in the compressed breast placed inside a parallel plate source-detector geometry (forward process). The simulated DL-DOT system's performance is evaluated using the Pearson correlation coefficient (R) and the Mean squared error (MSE) metrics. Although a comparatively smaller dataset (50 nos.) is used, our simulation results show that the developed feed-forward network algorithm to solve the inverse problem delivers an increment of ∼30% over the analytical solution approach, in terms of R. Furthermore, the proposed network's MSE outperforms that of the analytical solution's MSE by a large margin revealing the robustness of the network and the adaptability of the system for potential applications in medical settings.

Optical wireless communication (OWC) is in high demand due to its potential for high-speed data transmission and spectrum relief in congested radio frequencies. However, real-world implementations face significant challenges, particularly due to atmospheric turbulence, which distorts the optical signal, making reliable OWC difficult to achieve. In this study, we propose a novel methodology to mitigate the effects of turbulence by investigating the application of orbital angular momentum (OAM) and deep learning for robust OWC. In this study, we propagate information in the form of optical Laguerre-Gaussian (LG) beams through turbulent atmosphere and use the conjugate light field (CLF) method to retrieve the information. This process is further integrated into a deep learning framework to enhance the OWC systems performance. This integration reduces the computational load by minimizing the network classes to two CLF outcomes instead of using all LG beam modes as classes. The proposed method achieves faster processing time by reducing computational load, essential for real-time applications. An optical tabletop experiment also verifies the proposed technique, where we achieve a bit error rate (BER) of 2.44 × 10⁻⁴, demonstrating a performance that surpasses baseline algorithms by over ∼99% for a given set of parameters. To the best of the author's knowledge, this is the first time this concept has been presented for the use of OWC in turbulent atmospheric conditions.

Recent research has increasingly focused on Laguerre-Gaussian (LG) beams carrying a topological charge (l) due to their demonstrated ability to enhance signal transmission through turbid media. This promising phenomenon has spurred considerable interest in understanding the complex propagation dynamics of such beams, with the goal of optimizing optical systems for highly scattering environments. In this study, we experimentally investigate the transmission characteristics of LG beams with various topological charges as they propagate through a turbid multiple-scattering medium at different depths. By analyzing the resulting transmission data, we calculate the scattering mean free path (\(\:{{\Lambda\:}}^{*}\)) for each LG mode and show that \(\:{{\Lambda\:}}^{*}\) increases with increasing values of l. Moreover, we show that beams with higher topological charges traverse greater distances within diffuse media while retaining their characteristic donut shape using Monte Carlo simulations. Our findings provide an empirical characterization of the relationship between topological charge and scattering mean free path and also explain the improved transmission with increasing l, at least until optical depths of ~ 40 \(\:{{\Lambda\:}}^{*}\), highlighting potential trends that warrant further investigation regarding the potential of applying Laguerre-Gaussian beams for enhanced optical imaging and spectroscopy through highly scattering media.