<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Advanced Optical Technologies | Optical Imaging section | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/advanced-optical-technologies/sections/optical-imaging</link>
        <description>RSS Feed for Optical Imaging section in the Advanced Optical Technologies journal | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-05-13T14:08:46.232+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2025.1730807</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2025.1730807</link>
        <title><![CDATA[PSO-based imaging restoration method for diffraction imaging systems]]></title>
        <pubdate>2026-01-07T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Can Li</author><author>Lianghua Wen</author><author>Guochun Liu</author><author>Zhengcong Du</author><author>Jiaxun Li</author><author>Tong Yang</author><author>Sanxiu Jiao</author>
        <description><![CDATA[Membrane diffraction imaging is one of the most widely used imaging technologies today, which offers the advantages such as lightweight design, large aperture, foldability, and low cost. However, the system imaging quality degrades because of the multiple order diffraction generated by the diffractive elements in practical applications. To eliminate the effects of multiple diffraction orders from the diffractive elements and optimize imaging quality, the system images are post processed. Iterative optimization algorithms are commonly used for image post processing. Particle swarm optimization is a commonly used iterative optimization algorithm, which is often used to search for optimal solutions within the solution space. The particle swarm optimization algorithm has the features of few parameters, simple behavior, and fast iteration speed, which can rapidly and effectively optimize imaging. This paper optimizes the simulated imaging of a diffraction imaging system based on Fresnel zone plates by adopting the particle swarm optimization algorithm. Optimize the system image based on known point spread functions and the system image. System imaging is optimized under the premise of known point spread functions and system imaging. The iteration speed is enhanced, reducing the number of iterations by approximately 99.6% compared to the random parallel gradient descent algorithm. Simultaneously, contrast is improved by about 5.4%, while gradient optimization effectiveness increases by approximately 25.4% after optimization by the particle swarm algorithm. Finally, the derived restoration model was applied to other images, achieving overall improvements in all evaluation metrics.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2025.1583836</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2025.1583836</link>
        <title><![CDATA[Efficient high-resolution microscopic ghost imaging via sequenced speckle illumination and deep learning from a single noisy image]]></title>
        <pubdate>2025-06-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Sukyoon Oh</author><author>Tong Tian</author><author>Zhe Sun</author><author>Christian Spielmann</author>
        <description><![CDATA[This study presents a novel approach for achieving high-quality and large-scale microscopic ghost imaging by integrating deep learning-based denoising with computational ghost imaging techniques. By utilizing sequenced random speckle patterns of optimized sizes, we reconstructed large noisy images with fewer patterns while successfully resolving fine details as small as 2.2 μm on a USAF resolution target. To enhance image quality, we incorporated the Deep Neural Network-based Noise2Void (N2V) model, which effectively denoises ghost images without requiring a reference image or a large dataset. By applying the N2V model to a single noisy ghost image, we achieved significant noise reduction, leading to high-resolution and high-quality reconstructions with low computational resources. This method resulted in an average Structural Similarity Index (SSIM) improvement of over 324% and a resolution enhancement exceeding 33% across various target images. The proposed approach proves highly effective in enhancing the clarity and structural integrity of even very low-quality ghost images, paving the way for more efficient and practical implementations of ghost imaging in microscopic applications.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2025.1546386</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2025.1546386</link>
        <title><![CDATA[Deep learning for ultrafast X-ray scattering and imaging with intense X-ray FEL pulses]]></title>
        <pubdate>2025-03-13T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Menglu Hu</author><author>Jiadong Fan</author><author>Yajun Tong</author><author>Zhibin Sun</author><author>Huaidong Jiang</author>
        <description><![CDATA[The advent of X-ray Free Electron Lasers (XFELs) has opened unprecedented opportunities for advances in the physical, chemical, and biological sciences. With their state-of-the-art methodologies and ultrashort, and intense X-ray pulses, XFELs propel X-ray science into a new era, surpassing the capabilities of traditional light sources. Ultrafast X-ray scattering and imaging techniques leverage the coherence of these intense pulses to capture nanoscale structural dynamics with femtosecond spatial-temporal resolution. However, spatial and temporal resolutions remain limited by factors such as intrinsic fluctuations and jitters in the Self-Amplified Spontaneous Emission (SASE) mode, relatively low coherent scattering cross-sections, the need for high-performance, single-photon-sensitive detectors, effective sample delivery techniques, low parasitic X-ray instrumentation, and reliable data analysis methods. Furthermore, the high-throughput data flow from high-repetition rate XFEL facilities presents significant challenges. Therefore, more investigation is required to determine how Artificial Intelligence (AI) can support data science in this situation. In recent years, deep learning has made significant strides across various scientific disciplines. To illustrate its direct influence on ultrafast X-ray science, this article provides a comprehensive overview of deep learning applications in ultrafast X-ray scattering and imaging, covering both theoretical foundations and practical applications. It also discusses the current status, limitations, and future prospects, with an emphasis on its potential to drive advancements in fourth-generation synchrotron radiation, ultrafast electron diffraction, and attosecond X-ray studies.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2025.1536415</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2025.1536415</link>
        <title><![CDATA[Remote physiological monitoring of neck blood vessels with a high-speed camera]]></title>
        <pubdate>2025-03-07T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Meiyun Cao</author><author>Gennadi Saiko</author><author>Alexandre Douplik</author>
        <description><![CDATA[IntroductionSeveral population-based clinical studies suggest that increased Pulse Wave Velocity (PWV) is highly associated with increased cardiovascular disease (CVD) mortality, which is one of the leading causes of death worldwide. Current methods for CVD detection are invasive, expensive, and contact methods, which are not friendly for skin-sensitive patients.MethodsIn this study, we investigated the use of remote photoplethysmography (rPPG) on the neck region using a high-speed camera (2000 frames per second (fps)) to resolve the drawbacks of CVD detection and overcome the limitations of current PWV measurement techniques. Pearson correlation and cross-correlation were used for signal processing and generating the projection map of potential major vessels. A reference signal is selected for the region of interest based on peak value and modulation depth variation. The signal distance and pulse transit time (PPT) between the local and reference signals were calculated using the cross-correlation method and then fitted into a linear regression model for PWV calculation.ResultsThe results revealed areas on the neck that positively and negatively correlated with the selected reference signals, potentially representing the distribution of the main neck vessels - carotid artery and jugular vein- and, consequently, the upstream and downstream blood circulation directions.DiscussionThis research implies the feasibility of touchless estimation of local PWV using a high-speed camera, expanding the potential applications of remote photoplethysmography in aiding the diagnosis of CVD.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2024.1505036</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2024.1505036</link>
        <title><![CDATA[Exoplanet detection in rotational shearing interferometry through experimental setup and digital filtering techniques]]></title>
        <pubdate>2025-01-07T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Manuel Montes-Flores</author><author>Guillermo Garcia-Torales</author><author>Marija Strojnik</author>
        <description><![CDATA[The significant brightness contrast between stars and orbiting planets often hinders the detection of exoplanets. This paper presents the development and validation of an experimental setup and digital filtering techniques for a rotational shearing interferometer (RSI) aimed at enhancing exoplanet detection. The method leverages controlled phase shifts and spatial frequency modulation through Risley and Dove prisms to isolate faint planetary signals from dominant starlight. Laboratory experiments use HeNe lasers to simulate a star-planet system, and spatial filters ensure precise wavefront alignment. The interferometer’s rotational shearing capabilities enhance the accuracy of phase alignment, allowing for significant suppression of starlight and improved detection of planetary signals. Additionally, applying Fourier-based digital filtering techniques further enhances detection sensitivity by reducing background noise. Experimental results demonstrate an 80% reduction in noise and up to a 20% increase in detection sensitivity compared to traditional interferometric methods. The RSI’s performance represents a significant advancement in interferometric techniques, suggesting its potential for real-world astronomical applications. However, further optimization is required to address challenges associated with space-based observations. This work sets the foundation for future research aimed at refining optical configurations and digital filtering techniques for exoplanet detection.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2024.1474654</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2024.1474654</link>
        <title><![CDATA[W1-Net: a highly scalable ptychography convolutional neural network]]></title>
        <pubdate>2024-10-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Chengye Xing</author><author>Lei Wang</author><author>Yangyang Mu</author><author>Yu Li</author><author>Guangcai Chang</author>
        <description><![CDATA[X-ray ptychography is a coherent diffraction imaging technique that allows for the quantitative retrieval of both the amplitude and phase information of a sample in diffraction-limited resolution. However, traditional reconstruction algorithms require a large number of iterations to obtain phase and amplitude images exactly, and the expensive computation precludes real-time imaging. To solve the inverse problem of ptychography data, PtychoNN uses deep convolutional neural networks for real-time imaging. However, its model is relatively simple, and its accuracy is limited by the size of the training dataset, resulting in lower robustness. To address this problem, a series of W-Net neural network models have been proposed which can robustly reconstruct the object phase information from the raw data. Numerical experiments demonstrate that our neural network exhibits better robustness, superior reconstruction capabilities and shorter training time with high-precision ptychography imaging.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/aot.2024.1306142</guid>
        <link>https://www.frontiersin.org/articles/10.3389/aot.2024.1306142</link>
        <title><![CDATA[Intelligent visually lossless compression of dental images]]></title>
        <pubdate>2024-02-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Liudmyla Kryvenko</author><author>Olha Krylova</author><author>Vladimir Lukin</author><author>Sergii Kryvenko</author>
        <description><![CDATA[Background: Tendencies to increase the mean size of dental images and the number of images acquired daily makes necessary their compression for efficient storage and transferring via communication lines in telemedicine and other applications. To be a proper solution, lossy compression techniques have to provide a visually lossless option (mode) where a desired quality (invisibility of introduced distortions for preserving diagnostically valuable information) is ensured quickly and reliably simultaneously with a rather large compression ratio.Objective: Within such an approach, our goal is to give answers to several practical questions such as what encoder to use, how to set its parameter that controls compression, how to verify that we have reached our ultimate goal, what are additional advantages and drawbacks of a given coder, and so on.Methods: We analyze the performance characteristics of several encoders mainly based on discrete cosine transform for a set of 512 × 512 pixel fragments of larger size dental images produced by Morita and Dentsply Sirona imaging systems. To control the visual quality of compressed images and the invisibility of introduced distortions, we have used modern visual quality metrics and distortion invisibility thresholds established for them in previous experiments. Besides, we have also studied the so-called just noticeable distortions (JND) concept, namely, the approach based on the first JND point when the difference between an image subject to compression and its compressed version starts to appear.Results: The rate-distortion dependences and coder setting parameters obtained for the considered approaches are compared. The values of the parameters that control compression (PCC) have been determined. The ranges of the provided values of compression ratio have been estimated and compared. It is shown that the provided CR values vary from about 20 to almost 70 for modern coders and almost noise-free images that is significantly better than for JPEG. For images with visible noise, the minimal and maximal values of produced CR are smaller than for the almost noise-free images. We also present the results of the verification of compressed image quality by specialists (professional dentists).Conclusion: It is shown that it is possible and easy to carry out visually lossless compression of dental images using the proposed approaches with providing quite high compression ratios without loss of data diagnostic value.]]></description>
      </item>
      </channel>
    </rss>