High-fidelity Images Research Articles

Angle-dependent image-domain least-squares migration through analytical point spread functions

Image-domain least-squares migration (IDLSM) is an established approach to recover high-fidelity seismic images of subsurface reflectors; this is achieved by removing the blurring effects of the Hessian operator in the standard migration approach with the help of so-called point spread functions (PSFs). However, most of the existing IDLSM approaches recover an angle-independent image of the subsurface reflectors, which is not suitable for subsequent amplitude-variation-with-angle (AVA) analysis. To overcome this limitation, we have developed an angle-dependent IDLSM approach, denoted as AD-IDLSM, which can recover a high-fidelity and high-resolution angle-dependent reflectivity image of subsurface reflectors. The problem is formulated here as an angle-dependent image-domain inversion with PSFs computed by means of full-wave Green’s function. More specifically, we derive an analytical expression to compute angle-dependent PSFs by means of a wave-equation-based Kirchhoff migration (WEBKM) engine, where a localization assumption is made in both spatial directions to decrease the computational cost and memory overhead. The amplitude and traveltime of the Green’s functions involved in the WEBKM approach are estimated by the excitation amplitude and excitation time of the full-wave wavefield. The scattering angle is then approximately estimated from the Poynting vector of the excitation-time field. To stabilize the solution of AD-IDLSM, we use a regularization scheme that applies a second derivative along the direction of the reflection angle of angle-domain common-image gathers (ADCIGs) to ensure continuity in the amplitude variations versus angle and suppress migration artifacts. We demonstrate the effectiveness of the AD-IDLSM approach through two synthetic and one field marine data set; the presented results confirm that AD-IDLSM can create ADCIGs with higher spatial resolution, better amplitude fidelity, and fewer migration artifacts compared with those obtained by its migration counterpart. Moreover, AD-IDLSM amplitude variations with angle are shown to closely resemble the theoretical AVA curve of the reflectors.

Analyzing the latent space of GAN through local dimension estimation for disentanglement evaluation

The impressive success of style-based GANs (StyleGANs) in high-fidelity image synthesis has motivated research to understand the semantic properties of their latent spaces. In this paper, we approach this problem through a geometric analysis of latent spaces as a manifold. In particular, we propose a local dimension estimation algorithm for arbitrary intermediate layers in a pre-trained GAN model. The estimated local dimension is interpreted as the number of possible semantic variations from this latent variable. Moreover, this intrinsic dimension estimation enables unsupervised evaluation of disentanglement for a latent space. Our proposed metric, called Distortion, measures an inconsistency of intrinsic tangent space on the learned latent space. Distortion is purely geometric and does not require any additional attribute information. Nevertheless, Distortion shows a high correlation with the global-basis-compatibility and supervised disentanglement score. Our work is the first step towards selecting the most disentangled latent space among various latent spaces in a GAN without attribute labels.

Molecular Engineering of a Doubly Quenched Fluorescent Probe Enables Ultrasensitive Detection of Biothiols in Highly Diluted Plasma and High-Fidelity Imaging of Dihydroartemisinin-Induced Ferroptosis.

The occurrence and development of diseases are accompanied by abnormal activity or concentration of biomarkers in cells, tissues, and blood. However, the insufficient sensitivity and accuracy of the available fluorescence probes hinder the precise monitoring of associated indexes in biological systems, which is generally due to the high probe intrinsic fluorescence and false-negative signal caused by the reactive oxygen species (ROS)-induced probe decomposition. To resolve these problems, we have engineered a ROS-stable, meso-carboxylate boron dipyrromethene (BODIPY)-based fluorescent probe, which displays quite a low background fluorescence due to the doubly quenched intrinsic fluorescence by a combined strategy of the photoinduced electron transfer (PET) effect and "ester-to-carboxylate" conversion. The probe achieved a high S/N ratio with ultrasensitivity and good selectivity toward biothiols, endowing its fast detection capability toward the biothiol level in 200×-diluted plasma samples. Using this probe, we achieved remarkable distinguishing of liver injury plasma from normal plasma even at 80× dilution. Moreover, owing to its good stability toward ROS, the probe was successfully employed for high-fidelity imaging of the negative fluctuation of the biothiol level in nonsmall-cell lung cancer (NSCLC) during dihydroartemisinin-induced ferroptosis. This delicate design of suppressing intrinsic fluorescence reveals insights into enhancing the sensitivity and accuracy of fluorescent probes toward the detection and imaging of biomarkers in the occurrence and development of diseases.

Discrete Illumination-Based Compressed Ultrafast Photography for High-Fidelity Dynamic Imaging.

Compressed ultrafast photography (CUP) can capture irreversible or difficult-to-repeat dynamic scenes at the imaging speed of more than one billion frames per second, which is obtained by compressive sensing-based image reconstruction from a compressed 2D image through the discretization of detector pixels. However, an excessively high data compression ratio in CUP severely degrades the image reconstruction quality, thereby restricting its ability to observe ultrafast dynamic scenes with complex spatial structures. To address this issue, a discrete illumination-based CUP (DI-CUP) with high fidelity is reported. In DI-CUP, the dynamic scenes are loaded into an ultrashort laser pulse train with controllable sub-pulse number and time interval, thus the data compression ratio, as well as the overlap between adjacent frames, is greatly decreased and flexibly controlled through the discretization of dynamic scenes based on laser pulse train illumination, and high-fidelity image reconstruction can be realized within the same observation time window. Furthermore, the superior performance of DI-CUP is verified by observing femtosecond laser-induced ablation dynamics and plasma channel evolution, which are hardly resolved in the spatial structures using conventional CUP. It is anticipated that DI-CUP will be widely and dependably used in the real-time observations of various ultrafast dynamics.

A Nano-Aggregatable Acedan Derivative for Clathrin-Mediated Cellular Uptake and Two-Photon Imaging of Diabetes-Associated Lipid Droplets.

Lipid droplets (LDs), the essential cytosolic fat storage organelles, have emerged as pivotal regulators of cellular metabolism and are implicated in various diseases. The noninvasive monitoring of LDs necessitates fluorescent probes with precise organelle selectivity and biocompatibility. Addressing this need, we have engineered a probe by strategically modifying the structure of a conventional two-photon-absorbing dipolar dye, acedan. This innovative approach induces nanoaggregate formation in aqueous environments, leading to aggregation-induced fluorescence quenching. Upon cellular uptake via clathrin-mediated endocytosis, the probe selectively illuminates within LDs through a disassembly process, effectively distinguishing LDs from the cytosol with exceptional specificity. This breakthrough enables the high-fidelity imaging of LDs in both cellular and tissue environments. In a pioneering investigation, we probed LDs in a diabetes model induced by streptozotocin, unveiling significantly heightened LD accumulation in cardiac tissues compared to other organs, as evidenced by TP imaging. Furthermore, our exploration of a lipopolysaccharide-mediated cardiomyopathy model revealed an LD accumulation during heart injury. Thus, our developed probe holds immense potential for elucidating LD-associated diseases and advancing related research endeavors.

Abstract Mo024: Integrated analysis of ex vivo biomechanical ventricular remodeling and imaging-based in vivo strain changes in a pre-clinical murine model of radiation-induced cardiotoxicity

Introduction: Thoracic radiation therapy (RT) is commonly used for the treatment of many common malignancies, such as lung and breast cancer, but carries a high risk of radiation-induced cardiotoxicity (RIC). Existing diagnosis of RIC is challenged by subclinical ventricular dysfunction, not captured by global indices of cardiac function. Understanding RIC-driven biomechanical remodeling of the myocardium will provide novel insights into developing high-fidelity imaging approaches for early detection of RIC. Methods: A pre-clinical model of RIC was developed by administering whole heart irradiation under image guidance in mice (8 Gy x 5) over five consecutive days. A longitudinal study was carried out to investigate the biomechanical response of the left ventricle (LV). Cardiac magnetic resonance imaging was performed to estimate end-systolic strains. Mechanical testing was performed on the harvested LV free wall (LVFW) specimens to measure passive stiffness, calculated as the tangent to the ensemble stress-strain curve at 30% strain. Results: A significant increase in passive LVFW stiffness was observed at 3M post-RT (Figs. 1A and B). Significant declines in both global circumferential strain (GCS) and global radial strain (GRS) at 3M post-RT, compared to respective measurements at pre-RT, were observed (Figs. 1C and D). Suppressed contractile strains suggested biomechanical remodeling of the LV, including impaired contractility and passive stiffening of the LVFW, consistent with ex-vivo measurements. Conclusion: We have established a direct correlation between ex-vivo mechanical testing (elevated stiffness) and reduced contractile strains in in-vivo analysis in a mouse model of RIC. Such integrated analysis will pave the way towards developing highly sensitive imaging approaches that non-invasively recapitulate the ventricular remodeling events associated with RIC, thereby enabling early detection of RIC in patients receiving thoracic RT.

PO and PN in the Envelope of VY Canis Majoris: Elucidating the Chemistry and Origin of Phosphorus

The J = 5.5 → 4.5 and J = 5 → 4 transitions of PO and PN, respectively, have been imaged in the envelope of hypergiant star VY Canis Majoris (VY CMa) using the Atacama Large Millimeter/submillimeter Array with angular resolutions of 0.″2 and 1.″5 and data from the Submillimeter Telescope of the Arizona Radio Observatory. These maps are the first high-fidelity images of PO and PN in a circumstellar envelope. Both molecules are primarily present in a spherical, star-centered region with a radius ∼60 R * (0.″5), indicating formation by LTE chemistry and then condensation into grains. PN, however, shows additional, fan-shaped emission 2″ southwest of the star, coincident with dust features resolved by Hubble Space Telescope (HST), as well as four newly identified distinct structures 1″–2″ toward the north, east, and west (Cloudlets I–IV), not visible in HST images. The “SW Fan” and the cloudlets are also prominent in the J = 5.5 → 4.5 transition of NS. The correlation of PN with NS, SiO, and dust knots in the SW Fan suggests a formation in shocked gas enhanced with nitrogen. Excess nitrogen is predicted to favor PN synthesis over PO. Abundances for PN and PO in the spherical source are f ∼ 4.4 × 10−8 and 1.4 × 10−7, respectively, relative to H2. Given a cosmic abundance of phosphorus, an unusually high fraction (∼35%) is contained in PO and PN. Alternatively, the stellar winds may be enriched in P (and N) by dredge-up from the interior of VY CMa.

Application of acid-activated near-infrared viscosity fluorescent probe targeting lysosomes in cancer visualization

The higher viscosity and lower pH in lysosomes of cancer cells highlight their potential as biomarkers for cancer. Therefore, the development of acid-activated viscosity fluorescent probes is significant for the early diagnosis and treatment of cancer. Based on this, we have designed and synthesized a near-infrared fluorescent probe based on the 2-(2-hydroxyphenyl)benzothiazole (HBT) group, namely HBTH, to monitor the viscosity changes within lysosomes. It has been demonstrated that HBTH was extremely sensitive to viscosity, with a strong linear relationship between fluorescence intensity and log(viscosity) within the range of (logη) = 0–3.06 (a correlation coefficient of 0.98), proving its capability for quantitative viscosity measurement. In particular, the most obvious fluorescence enhancement of HBTH was only efficiently triggered by the combined effect of low pH and high viscosity. Furthermore, HBTH can rapidly localize to lysosomes by wash-free procedure at a low concentration (100 nM) and achieve high-fidelity imaging within 20 s. It can also monitor the dynamic processes of lysosomes in cells, viscosity changes under drug stimuli, and lysosomal behavior during mitophagy. Importantly, HBTH is capable of identifying tumors in tumor-bearing nude mice through in vivo imaging. These features make HBTH a powerful tool for the early diagnosis and treatment of cancer.

Enhancing capabilities of generative models through VAE-GAN integration: A review

Our review explores the integration of Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), which are pivotal in the realm of generative models. VAEs are renowned for their robust probabilistic foundations and capacity for complex data representation learning, while GANs are celebrated for generating high-fidelity images. Despite their strengths, both models have limitations: VAEs often produce less sharp outputs, and GANs face challenges with training stability. The hybrid VAE-GAN models harness the strengths of both architectures to overcome these limitations, enhancing output quality and diversity. We provide a comprehensive overview of VAEs and GANs technology developments, their integration strategies, and resultant performance improvements. Applications across various fields, such as artistic creation, medical imaging, e-commerce, and video gaming, highlight the transformative potential of these models. However, challenges in model robustness, ethical concerns, and computational demands persist, posing significant hurdles. Future research directions are poised to transform the VAE-GAN landscape significantly. Enhancing training stability remains a priority, with new approaches such as incorporating self-correcting mechanisms into GANs training being tested. Addressing ethical issues is also critical, as policymakers and technologists work together to develop standards that prevent misuse. Moreover, reducing computational costs is fundamental to democratizing access to these technologies. Projects such as the development of MobileNetV2 have made strides in creating more efficient neural network architectures that maintain performance while being less resource-intensive. Further, the exploration of VAE-GAN applications in fields like augmented reality and personalized medicine offers exciting opportunities for growth, as evidenced by recent pilot studies.

High-fidelity imaging of fatty liver in vivo with a fluorescent and photoacoustic dual-mode probe by taking advantage of the liver “first pass effect”

Intravenous injection is the most commonly used method for probe delivery in bio-imaging. While, the oral administration method might be more efficient than intravenous injection for fatty liver imaging due to the existence of liver “first pass effect”. However, this fundamental question has not yet been clarified. Meanwhile, in consideration of the deep tissue imaging and signal fidelity, fluorescent-photoacoustic (PA) dual-mode probes are much more desirable. Herein, an orally administrable dual-mode probe WSP-3 is revealed as a tool for imaging of the fatty liver disease and providing an insight into the above scientific question. A D-π-A system is linked with a rotatable CC single bond in WSP-3, which facilitates the formation of a TICT state in low viscosity environments and an ICT state in high viscosity environments. Base on the positive correlation between fatty liver disease and cell viscosity, dual-mode imaging of non-alcoholic fatty liver disease (NAFLD) and drug-induced fatty liver disease (DIFLD) in vivo was accomplished. Moreover, control experiments indicated that the oral administration method demonstrated higher efficiency in fatty liver disease imaging, providing a fundamental reference for further probe-based fatty liver imaging.

GAN-based quantitative oblique back-illumination microscopy enables computationally efficient epi-mode refractive index tomography.

Quantitative oblique back-illumination microscopy (qOBM) is a novel imaging technology that enables epi-mode 3D quantitative phase imaging and refractive index (RI) tomography of thick scattering samples. The technology uses four oblique back illumination images captured at the same focal plane and a fast 2D deconvolution reconstruction algorithm to reconstruct 2D phase cross-sections of thick samples. Alternatively, a through-focus z-stack of oblique back illumination images can be used to recover 3D RI tomograms with improved RI quantitative fidelity at the cost of a more computationally expensive reconstruction algorithm. Here, we report on a generative adversarial network (GAN) assisted approach to reconstruct 3D RI tomograms with qOBM that achieves high fidelity and greatly reduces processing time. The proposed approach achieves high-fidelity 3D RI tomography using differential phase contrast images from three adjacent z-planes. A ∼9-fold improvement in volumetric reconstruction time is achieved. We further show that this technique provides high SNR RI tomograms with high quantitative fidelity, reduces motion artifacts, and generalizes to different tissue types. This work can lead to real-time, high-fidelity RI tomographic imaging for in-vivo pre-clinical and clinical applications.

Structure-aware diffusion for low-dose CT imaging

Reducing the radiation dose leads to the x-ray computed tomography (CT) images suffering from heavy noise and artifacts, which inevitably interferes with the subsequent clinic diagnostic and analysis. Leading works have explored diffusion models for low-dose CT imaging to avoid the structure degeneration and blurring effects of previous deep denoising models. However, most of them always begin their generative processes with Gaussian noise, which has little or no structure priors of the clean data distribution, thereby leading to long-time inference and unpleasant reconstruction quality. To alleviate these problems, this paper presents a Structure-Aware Diffusion model (SAD), an end-to-end self-guided learning framework for high-fidelity CT image reconstruction. First, SAD builds a nonlinear diffusion bridge between clean and degraded data distributions, which could directly learn the implicit physical degradation prior from observed measurements. Second, SAD integrates the prompt learning mechanism and implicit neural representation into the diffusion process, where rich and diverse structure representations extracted by degraded inputs are exploited as prompts, which provides global and local structure priors, to guide CT image reconstruction. Finally, we devise an efficient self-guided diffusion architecture using an iterative updated strategy, which further refines structural prompts during each generative step to drive finer image reconstruction. Extensive experiments on AAPM-Mayo and LoDoPaB-CT datasets demonstrate that our SAD could achieve superior performance in terms of noise removal, structure preservation, and blind-dose generalization, with few generative steps, even one step only.

FUSION3D: Multimodal data fusion for 3D shape reconstruction: A soft-sensing approach

Traditional high-fidelity imaging techniques, such as X-ray computer tomography (CT), excel in capturing intricate shape details through high-resolution two-dimensional (2D) images. However, the extensive cost or impracticality of obtaining X-ray images poses a significant challenge in various applications (e.g., dense metal components in manufacturing). To overcome this limitation, we propose a soft sensing approach, named FUSION3D, aimed at reconstructing three-dimensional (3D) shapes from 2D sliced images and heterogenous process inputs using a novel model based on multi-modal process knowledge. The developed FUSION3D method is built upon a deep learning framework that utilizes continuous normalizing flow to model the complex shape distribution of 3D objects. We propose a principled probabilistic framework to regularize 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes, and the second level is the distribution of points given a shape. Our generative regularization model learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Our methodology is validated through a case study in additive manufacturing, demonstrating its effectiveness as a soft sensing approach for accurate 3D shape reconstruction without relying on high-fidelity imaging techniques like CT during model deployment.

LD-CSNet: A latent diffusion-based architecture for perceptual Compressed Sensing

Compressed Sensing (CS) is a groundbreaking paradigm in image acquisition, challenging the constraints of the Nyquist–Shannon sampling theorem. This enables high-quality image reconstruction using a minimal number of measurements. Neural Networks’ potent feature induction capabilities enable advanced data-driven CS methods to achieve high-fidelity image reconstruction. However, achieving satisfactory reconstruction performance, particularly in terms of perceptual quality, remains challenging at extremely low sampling rates. To tackle this challenge, we introduce a novel two-stage image CS framework based on latent diffusion, named LD-CSNet. In the first stage, we utilize an autoencoder pre-trained on a large dataset to represent natural images as low-dimensional latent vectors, establishing prior knowledge distinct from sparsity and effectively reducing the dimensionality of the solution space. In the second stage, we employ a conditional diffusion model for maximum likelihood estimates in the latent space. This is supported by a measurement embedding module designed to encode measurements, making them suitable for a denoising network. This guides the generation process in reconstructing low-dimensional latent vectors. Finally, the image is reconstructed using a pre-trained decoder. Experimental results across multiple public datasets demonstrate LD-CSNet’s superior perceptual quality and robustness to noise. It maintains fidelity and visual quality at lower sampling rates. Research findings suggest the promising application of diffusion models in image CS. Future research can focus on developing more appropriate models for the first stage.

Advancing Image Generation with Denoising Diffusion Probabilistic Model and ConvNeXt-V2: A novel approach for enhanced diversity and quality

In the rapidly evolving domain of image generation, the availability of sufficient data is crucial for effective model training. However, obtaining a large dataset is often challenging. Medical imaging, industrial monitoring, and self-driving cars are among the applications that require high-fidelity image generation from limited or single data points. The paper proposes a novel approach for increasing the diversity of images generated from a single input image by combining a Denoising Diffusion Probabilistic Model (DDPM) with the ConvNeXt-V2 architecture. This technique addresses the issue of limited data availability by utilizing single images using the BSD and Places365 datasets, significantly increasing the ability of the model through different conditions. The research greatly enhances the image quality by including Global Response Normalization (GRN) and Sigmoid-Weighted Linear Units (SiLU) in the DDPM. In-depth analyses and comparisons with the existing State-of-the-art (SOTA) models highlight the model’s effectiveness, which shows higher experimental results. Achievements include a Pixel Diversity score of 0.87±0.1, an LPIPS Diversity score of 0.42±0.03, and a SIFID for Patch Distribution of 0.046±0.02, along with notable NIQE and RECO scores. These findings indicate the exceptional ability of the model to generate a wide range of high-quality images, exhibiting significant advancement over existing State-of-the-art models in the field of image generation.

A Novel Adversarial Deep Learning Method for Substation Defect Image Generation.

The presence of defects in substation equipment is a major factor affecting the safety of power transmission. Therefore, timely and accurate detection of these defects is crucial. As intelligent inspection robots advance, using mainstream object detection models to diagnose surface defects in substation equipment has become a focal point of current research. However, the lack of defect image data is one of the main factors affecting the accuracy of supervised deep learning-based defect detection models. To address the issue of insufficient training data for defect images with complex backgrounds, such as rust and surface oil leakage in substation equipment, which leads to the poor performance of detection models, this paper proposes a novel adversarial deep learning model for substation defect image generation: the Abnormal Defect Detection Generative Adversarial Network (ADD-GAN). Unlike existing generative adversarial networks, this model generates defect images based on effectively segmented local areas of substation equipment images, avoiding image distortion caused by global style changes. Additionally, the model uses a joint discriminator for both overall images and defect images to address the issue of low attention to local defect areas, thereby reducing the loss of image features. This approach enhances the overall quality of generated images as well as locally generated defect images, ultimately improving image realism. Experimental results demonstrate that the YOLOV7 object detection model trained on the dataset generated using the ADD-GAN method achieves a mean average precision (mAP) of 81.5% on the test dataset, and outperforms other image data augmentation and generation methods. This confirms that the ADD-GAN method can generate a high-fidelity image dataset of substation equipment defects.

Unwrapping non-locality in the image transmission through turbid media

Achieving high-fidelity image transmission through turbid media is a significant challenge facing both the AI and photonic/optical communities. While this capability holds promise for a variety of applications, including data transfer, neural endoscopy, and multi-mode optical fiber-based imaging, conventional deep learning methods struggle to capture the nuances of light propagation, leading to weak generalization and limited reconstruction performance. To address this limitation, we investigated the non-locality present in the reconstructed images and discovered that conventional deep learning methods rely on specific features extracted from the training dataset rather than meticulously reconstructing each pixel. This suggests that they fail to effectively capture long-range dependencies between pixels, which are crucial for accurate image reconstruction. Inspired by the physics of light propagation in turbid media, we developed a global attention mechanism to approach this problem from a broader perspective. Our network harnesses information redundancy generated by peculiar non-local features across the input and output fiber facets. This mechanism enables a two-order-of-magnitude performance boost and high fidelity to the data context, ensuring an accurate representation of intricate details in a pixel-to-pixel reconstruction rather than mere loss minimization.

O-251 Generative artificial intelligence substantially enhances the accuracy of embryo selection models

Abstract Study question Can generative artificial intelligence (AI) produce high-fidelity human embryo images to improve AI-based embryo selection models? Summary answer Generative AI models exhibit the capability to generate high-fidelity human embryo images and can substantially improve the performance of AI models through extensive training data. What is known already The integration of AI into in vitro fertilization (IVF) procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative Adversarial Networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images. However, the advantage of applying GAN in IVF embryo images is yet to be determined. Study design, size, duration Embryo images were retrieved as training data from time-lapse microscopy (TLM) videos (n = 328). Embryo key morphokinetic variables including blastomere division from 1-cell stage to 9 (and more) cells-stage, compaction of morula, and blastocyst formation were manually annotated by six embryologists. A style-based GAN was fine-tuned as the generative model and a residual network as the morphokinetic classification model. Participants/materials, setting, methods We configured generative models with data augmentation (AUG) and pretrained weights (Pretrained-T/R) to test their refinement to synthetic image quality. We analyzed quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance through a visual Turing test. Then, we compared the performance of a classifier by training real images alone and by integrating real images with generated data. Main results and the role of chance During the training process, we observed consistent improvement in image quality that was measured by FID and KID scores. The AUG+Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004 following 5,000 training iterations. Subsequently, we carried out a visual Turing test, such that a total of 60 individuals including IVF embryologists (Group I, n = 25), IVF laboratory technicians (Group II, n = 15), and non-experts (Group III, n = 20) evaluated the synthetic blastocyst-stage embryo images. Group I displayed accuracy of 55.7% (±6.2), sensitivity of 65.9% (±14.1), and specificity of 45.1% (±17.8). Group II showed accuracy of 54.2% (±4.7), sensitivity of 65.9% (±17.6), and specificity of 42.0% (±19.6). Group III had the accuracy of 50.1% (±3.8), sensitivity of 49.3% (±6.3), and specificity was 50.9% (±10.4). Statistical analysis indicated significant differences in accuracy (Kruskal-Wallis test, P=1.2x10-3) and sensitivity (Kruskal-Wallis test, P=1.6x10-4) among the three groups. In the embryonic stage classification model, integrated with generated data outperformed the model using real data solely, with an increase of validation accuracy from 72.6% to 90.6%. The classifier was tested on external TLM video data (n = 100) where the area under the curve was 0.92. Limitations, reasons for caution Further research is needed to involve a more extensive and diverse dataset, e.g. video generation, and more detailed annotations including polar body appearance, pronuclei appearance and disappearance, and blastocyst expansion and hatching. Wider implications of the findings Generative AI offers potential in generating high-fidelity human embryo images. This approach ensures sufficient training datasets while addressing class imbalances for robust AI-based methods, ultimately transforming embryo selection and enhancing IVF outcomes. A set of 5,000 generated images (1024x1024-pixel) at each embryonic developmental stage was open-source for future AI studies. Trial registration number not applicable

P-182 High-resolution synthetic embryo images generated by AI

Abstract Study question How effectively can a latent diffusion model generate high-fidelity embryo images tailored to the specific contextual needs of researchers, based on the user’s text input? Summary answer The latent diffusion model successfully generated high-resolution embryo images, providing a novel approach to address data scarcity in embryo imaging. What is known already The use of AI in generating synthetic data has been increasingly explored to address the scarcity of real-world datasets in various fields. Particularly in medical imaging, AI-generated synthetic data offers a potential solution to overcome the limitations imposed by data privacy concerns and ethical considerations. Previous studies have shown that AI can replicate complex patterns in data, but its application in generating embryo images remains less explored. Study design, size, duration Single static images of 5,133 Day 5 blastocysts and 2,093 Day 3 cleavages were retrospectively collected from seven in vitro fertilization clinics between June 2011 and May 2022. The images were analyzed along with relevant metadata including clinical information and embryo grades. Day 3 embryo grading was based on the number of blastomeres, evenness, and fragmentation percentage. Day 5 grading criteria included the inner cell mass, trophectoderm, and blastocyst stage evaluations. Participants/materials, setting, methods An AI model using latent diffusion was developed to generate 10,051 Day 5 and 10,088 Day 3 synthetic embryo images. The authenticity was assessed through visual Turing tests, where embryologists discerned real from synthetic images. For the evaluation, 200 real (100 Day 5, 100 Day 3) and 200 synthetic (100 Day 5, 100 Day 3) images were randomly chosen from each dataset, ensuring a comprehensive test of the generated images’ realism. Main results and the role of chance The AI model’s efficacy in generating synthetic embryo images was assessed through visual Turing tests on Day 5 and Day 3 embryos, yielding accuracies of 0.59 and 0.57, respectively. These accuracies fall within the 99% confidence interval of near-random performance (0.41 to 0.59), highlighting the challenge in distinguishing synthetic from real images. For Day 5 embryos, the sensitivity and specificity were recorded at 0.52 and 0.66, indicating a moderate challenge in identifying synthetic images and a relatively higher ease in recognizing real ones. Day 3 embryos presented a lower sensitivity of 0.41, suggesting greater difficulty in detecting synthetic images, while the specificity increased to 0.73, indicating a stronger ability to identify real images. Collectively, with an overall accuracy of 0.58, sensitivity of 0.47, and specificity of 0.70, these findings confirm the synthetic images’ remarkable realism, closely emulating actual embryo features to the extent that differentiation by experts proved challenging. This level of realism underscores the synthetic images’ potential to significantly enrich embryological research datasets, promising advancements in the field. Limitations, reasons for caution The study’s limitation lies in the generated synthetic embryos being based on three embryo grade categories, limiting feature diversity. Additionally, there was no quantitative assessment method for these images, relying instead on expert evaluation, which required deploying a large number of embryologists. Wider implications of the findings The model’s generation of highly realistic embryo images counters data scarcity in embryological research, potentially elevating AI’s utility, enriching educational content, advancing reproductive medicine, and ensuring ethical data usage. Trial registration number not applicable

High-Fidelity Detection of Large-Scale Atom Arrays in an Optical Lattice.

Recent advances in quantum simulation based on neutral atoms have largely benefited from high-resolution, single-atom sensitive imaging techniques. A variety of approaches have been developed to achieve such local detection of atoms in optical lattices or optical tweezers. For alkaline-earth and alkaline-earth-like atoms, the presence of narrow optical transitions opens up the possibility of performing novel types of Sisyphus cooling, where the cooling mechanism originates from the capability to spatially resolve the differential optical level shifts in the trap potential. Up to now, it has been an open question whether high-fidelity imaging could be achieved in a "repulsive Sisyphus" configuration, where the trap depth of the ground state exceeds that of the excited state involved in cooling. Here, we demonstrate high-fidelity (99.971(1)%) and high-survival (99.80(5)%) imaging of strontium atoms using repulsive Sisyphus cooling. We use an optical lattice as a pinning potential for atoms in a large-scale tweezer array with up to 399 tweezers and show repeated, high-fidelity lattice-tweezer-lattice transfers. We furthermore demonstrate loading the lattice with approximately 10 000 atoms directly from the MOT and scalable imaging over >10 000 lattice sites with a combined survival probability and classification fidelity better than 99.2%. Our lattice thus serves as a locally addressable and sortable reservoir for continuous refilling of optical tweezer arrays in the future.