High-fidelity Images Research Articles

ROSE: Multi-level super-resolution-oriented semantic embedding for 3D microvasculature segmentation from low-resolution images

Current state-of-the-art segmentation methods often require high-resolution input to attain the high performance, which pushes the limit of data acquisition and brings large computation budgets. Instead, we present an end-to-end deep learning-based method, ROSE, for robust and precise segmentation of high-quality 3D super-resolution (SR) microvasculatures from low-resolution (LR) images as input, which can transform data from the LR imaging domain to the SR semantic domain (cross different modalities and scales). More specifically, a multi-tasking two-stream deep learning framework is proposed to learn the high-fidelity microvasculature SR image and semantic hybrid features simultaneously. During the proposed joint learning process, the high-resolution features of microvasculatures are further enhanced by the learned fine-grained structural/textural features from the microvasculature SR stream with a multi-level embedding scheme through the oriented feature aggregation at different fusion stages. In the constructed joint multi-level hybrid embedding spaces, the instance semantic embedding and the SR imaging embedding can be connected and integrated synergistically. We have conducted extensive experiments using public and real patient micro-cerebrovascular image datasets and compare our framework with traditional 3D vessel segmentation methods and the other state-of-the-art in deep learning. This robust and precise microvascular visualization in different brain regions by our method demonstrates its potential impact in magnetic resonance (MR) angiography and venography for the diagnosis of microvascular disease.

Assessing the efficacy of 3D Dual-CycleGAN model for multi-contrast MRI synthesis

BackgroundThis research presents a novel methodology for synthesizing 3D multi-contrast MRI images utilizing the 3D Dual-CycleGAN architecture. The performance of the model is evaluated on different MRI sequences, including T1-weighted (T1W), T1-weighted contrast-enhanced (T1c), T2-weighted (T2W), and FLAIR sequences.ResultsOur approach demonstrates proficient learning capabilities in transforming T1W images into target modalities. The proposed framework encompasses a combination of different loss functions including voxel-wise, gradient difference, perceptual, and structural similarity losses. These loss components, along with adversarial and dual cycle-consistency losses, contribute significantly to realistic and accurate syntheses. Evaluation metrics including MAE, PMAE, RMSE, PCC, PSNR, and SSIM are employed to assess the fidelity of synthesized images compared to their ground truth counterparts. Empirical results indicate the effectiveness of the 3D Dual-CycleGAN model in generating T1c images from T1W inputs with minimal average discrepancies (MAE of 2.8 ± 2.61) and strong similarity (SSIM of 0.82 ± 0.28). Furthermore, the synthesis of T2W and FLAIR images yields promising outcomes, demonstrating acceptable average discrepancies (MAE of 3.87 ± 3.32 for T2W and 3.82 ± 3.32 for FLAIR) and reasonable similarities (SSIM of 0.82 ± 0.28 for T2W and 0.80 ± 0.29 for FLAIR) relative to the original images.ConclusionsThese findings underscore the efficacy of the 3D Dual-CycleGAN model in generating high-fidelity images, with significant implications for diverse applications in the field of medical imaging.

Information Density Enhancement Using Lossy Compression in DNA Data Storage.

This study develops two deoxyribonucleic acid (DNA)lossy compression models, Models A and B, to encode grayscale images into DNA sequences, enhance information density, and enable high-fidelity image recovery. These models, distinguished by their handling of pixel domains and interpolation methods, offer a novel approach to data storage for DNA. Model A processes pixels in overlapped domains using linear interpolation (LI), whereas Model B uses non-overlapped domains with nearest-neighbor interpolation (NNI). Through a comparative analysis with Joint Photographic Experts Group (JPEG)compression, the DNA lossy compression models demonstrate competitive advantages in terms of information density and image quality restoration. The application of these models to the Modified National Institute of Standards and Technology (MNIST) dataset reveals their efficiency and the recognizability of decompressed images, which is validated by convolutional neural network (CNN) performance. In particular, Model B2, a version of Model B, emerges as an effective method for balancing high information density (surpassing over 20 times the typical densities of two bits per nucleotide) with reasonably good image quality. These findings highlight the potential of DNA-based data storage systems for high-density and efficient compression, indicating a promising future for biological data storage solutions.

High-fidelity and fast 3D imaging of subcellular dynamics in native states.

High-fidelity and fast 3D imaging of subcellular dynamics in native states.

Ultrahigh-fidelity full-color holographic display via color-aware optimization

Holographic display offers the capability to generate high-quality images with a wide color gamut since it is laser-driven. However, many existing holographic display techniques fail to fully exploit this potential, primarily due to the system’s imperfections. Such flaws often result in inaccurate color representation, and there is a lack of an efficient way to address this color accuracy issue. In this study, we develop a color-aware hologram optimization approach for color-accurate holographic displays. Our approach integrates both laser and camera into the hologram optimization loop, enabling dynamic optimization of the laser’s output color and the acquisition of physically captured feedback. Moreover, we improve the efficiency of the color-aware optimization process for holographic video displays. We introduce a cascade optimization strategy, which leverages the redundant neighbor hologram information to accelerate the iterative process. We evaluate our method through both simulation and optical experiments, demonstrating the superiority in terms of image quality, color accuracy, and hologram optimization speed compared to previous algorithms. Our approach verifies a promising way to realize a high-fidelity image in the holographic display, which provides a new direction toward the practical holographic display.

Single-shot enhanced imaging through multimode fiber based on self-learning networks

High-fidelity imaging through a multimode fiber (MMF) plays a crucial role in various fields such as medicine, communication, and detection. However, the optical transmission matrix of the MMF suffers from dimensionality reduction. This case results in poor reconstruction quality such as low resolution and noise. In this paper, an unsupervised self-learning circulate learning network is employed to enhance a single degraded image without ground truth images. Moreover, an edge-preserving smoothing filter is applied to address the heavy noise problem of the reconstructed images. Experimental results demonstrate that the proposed method can improve the dimensionality and fidelity of the reconstructed target. Compared to traditional transmission matrix-based reconstruction methods, we have a competitive advantage in terms of evaluation metrics. The proposed method further advances the development of imaging through a multimode fiber.

A Methylation-Gated DNAzyme Circuit for Spatially Controlled Imaging of MicroRNA in Cells and Animals.

Epigenetic modification plays an indispensable role in regulating routine molecular signaling pathways, yet it is rarely used to modulate molecular self-assembly networks. Herein, we constructed a bioorthogonal demethylase-stimulated DNA circuitry (DSC) system for high-fidelity imaging of microRNA (miRNA) in live cells and mice by eliminating undesired off-site signal leakage. The simple and robust DSC system is composed of a primary cell-specific circuitry regulation (CR) module and an ultimate signal-transducing amplifier (SA) module. After the modularly designed DSC system was delivered into target live cells, the DNAzyme of the CR module was site-specifically activated by endogenous demethylase to produce fuel strands for the subsequent miRNA-targeting SA module. Through the on-site and multiply guaranteed molecular recognitions, the lucid yet efficient DSC system realized the reliably amplified in vivo miRNA sensing and enabled the in-depth exploration of the demethylase-involved signal pathway with miRNA in live cells. Our bioorthogonally on-site-activated DSC system represents a universal and versatile biomolecular sensing platform via various demethylase regulations and shows more prospects for more different personalized theragnostics.

Light&fast generative adversarial network for high-fidelity CT image synthesis of liver tumor

Background and objective:Hepatocellular carcinoma is a common disease with high mortality. Through deep learning methods to analyze HCC CT, the screening classification and prognosis model of HCC can be established, which further promotes the development of computer-aided diagnosis and treatment in the treatment of HCC. However, there are significant challenges in the actual establishment of HCC auxiliary diagnosis model due to data imbalance, especially for rare subtypes of HCC and underrepresented demographic groups. This study proposes a GAN model aimed at overcoming these obstacles and improving the accuracy of HCC auxiliary diagnosis. Methods:In order to generate liver and tumor images close to the real distribution. Firstly, we construct a new gradient transfer sampling module to improve the lack of texture details and excessive gradient transfer parameters of the deep model; Secondly, we construct an attention module with spatial and cross-channel feature extraction ability to improve the discriminator’s ability to distinguish images; Finally, we design a new loss function for liver tumor imaging features to constrain the model to approach the real tumor features in iterations. Results:In qualitative analysis, the images synthetic by our method closely resemble the real images in liver parenchyma, blood vessels, tumors, and other parts. In quantitative analysis, the optimal results of FID, PSNR, and SSIM are 75.73, 22.77, and 0.74, respectively. Furthermore, our experiments establish classification models for imbalanced data and enhanced data, resulting in an increase in accuracy rate by 21%–34%, an increase in AUC by 0.29 - 0.33, and an increase in specificity to 0.89. Conclusion:Our solution provides a variety of training data sources with low cost and high efficiency for the establishment of classification or prognostic models for imbalanced data.

A Geant4-based Monte Carlo X-ray imaging simulation platform

X-ray digital radiography plays a pivotal role in accessing the internal structure of objects. Nevertheless, key imaging parameters, such as source-to-target distance or number of projected images needed for three-dimensional construction, mostly rely on real-life trials thus increasing radiation exposure risks. This paper introduces a recently developed software platform known as GMAX (Geant4-based Monte Carlo Advanced X-ray) that helps addressing above issues from a simulation perspective. GMAX employs Geant4, a Monte Carlo simulation code at its core and facilitates high-fidelity X-ray imaging, requiring no prior user experience. Compared to CAD models that only reflect object's geometrical information, GMAX simulates how objects interact with photon and can accurately evaluate important imaging parameters, such as target object to detector distance. It also provides three-dimensional construction functionality for images and therefore could be used as an effective tool for X-ray non-destructive testing and inspection.

Implementation of Text to Image using Diffusion Model

Text-to-image generation is a transformative field in artificial intelligence, aiming to bridge the semantic gap between textual descriptions and visual representations. This presents a comprehensive approach to tackle this challenging task. Leveraging the advancements in deep learning, natural language processing (NLP), and computer vision, this proposes a cutting-edge model for generating high-fidelity images from textual prompts. Trained on a vast and varied dataset of written descriptions and related images, this model combines an image decoder and a text encoder within a hierarchical framework. To enhance realism, this incorporates attention mechanisms and fine-grained semantic parsing. The model's performance is rigorously evaluated through both quantitative metrics and qualitative human assessments. Results demonstrate its ability to produce visually compelling and contextually accurate images across various domains, from natural scenes to specific object synthesis. This further explores applications in creative content generation, design automation, and virtual environments, showcasing the potential impact of our approach. Additionally, this releases a user-friendly API, empowering developers and designers to integrate our model into their projects, and fostering innovation and creativity. Key Words: image generation model, Deep learning, Natural language processing.

Logo recognition of vehicles based on deep convolutional generative adversarial networks

Vehicle logo recognition plays a critical role in enhancing the efficiency of intelligent transportation systems by enabling accurate vehicle identification and tracking. Despite advancements in image recognition technologies, accurately detecting and classifying vehicle logos in diverse and dynamically changing environments remains a significant challenge. This research introduces an innovative approach utilizing a Deep Convolutional Generative Adversarial Network (DCGAN) framework, tailored specifically for the complex task of vehicle logo recognition. Unlike traditional methods, which heavily rely on manual feature extraction and pre-defined image processing techniques, our method employs a novel DCGAN architecture. This architecture automatically learns the distinctive features of vehicle logos directly from data, enabling more robust and accurate recognition across various conditions. Furthermore, we propose a refined training strategy for both the generator and discriminator components of our DCGAN, optimized through extensive experimentation, to enhance the model’s ability to generate high-fidelity vehicle logo images for improved training efficacy. The technical core of our approach lies in the strategic integration of transfer learning techniques. These techniques significantly boost classification accuracy by leveraging pre-learned features from vast image datasets, thereby addressing the challenge of limited labeled data in the vehicle logo domain. Our experimental results demonstrate a substantial improvement in logo detection and classification accuracy, achieving an Intersection over Union (IoU) ratio of 42.67 % and a classification accuracy of 99.78 %, which markedly surpasses the performance of existing methods. This research not only advances the field of vehicle logo recognition but also contributes to the broader domain of measurement science and technology, offering a technically sound and logically coherent solution to a complex problem.

Deep learning and random light structuring ensure robust free-space communications

Having shown early promise, free-space optical (FSO) communications face formidable challenges in the age of information explosion. The ever-growing demand for greater channel communication capacity is one of the challenges. The inter-channel crosstalk, which severely degrades the quality of transmitted information, creates another roadblock in the way of efficient implementation of FSO communication systems. Here, we advance theoretically and realize experimentally a potentially high-capacity FSO protocol that enables high-fidelity transfer of an image or set of images through a complex environment. In our protocol, we complement random light structuring at the transmitter with a deep learning image classification platform at the receiver. Multiplexing unique, independent, mutually orthogonal degrees of freedom available to structured random light can potentially significantly boost the channel communication capacity of our protocol without introducing any deleterious crosstalk. Specifically, we show how one can multiplex the degrees of freedom associated with the source coherence radius and a spatial position of a beamlet within an array of structured random beams to greatly enhance the capacity of our communication link. The superb resilience of structured random light to environmental noise, as well as extreme efficiency of deep learning networks at classifying images, guarantees high-fidelity image transfer within the framework of our protocol.

From raw seismic data to quantitative interpretation via cloud-based FWI

Full-waveform inversion (FWI) has evolved in recent years from a technique for recovering long- to intermediate-wavelength updates of acoustic overburden velocities as part of a broader model building workflow to a standalone tool for high-fidelity seismic imaging using raw seismic data – with ever greater resolution and ever more sophisticated physics being sought. In doing so, it has moved notably closer to fulfilling the vision of its original inventors in the late 70s and early 80s. In this work, two novel approaches to FWI along with enabling technologies for their effective deployment are considered. The first of these allows for robust long-wavelength updates to be generated from raw seismic data in the absence of diving wave energy, providing reliable estimates of acoustic velocity at depths equivalent to or greater than the longest offsets available in the data – thereby enabling more effective imaging with data of limited quality. The second allows for the estimation of elastic amplitude-versus-angle behaviour while still using an acoustic wave equation, thereby mitigating the significant computational burden typically associated with elastic FWI. Finally, it is demonstrated that these approaches can be deployed in a reliable and cost-effective manner via the considered use of public cloud resources, with learnings relevant for analogous massively parallel scientific applications. Case studies from two marine environments are provided for discussion, one being from deep-water US Gulf of Mexico and the other from intermediate water depths offshore Western Australia.

Exploring the micro-to-macro response of granular soils with real particle shapes by way of μCT-aided DEM analyses

This contribution provides high-fidelity images of real granular materials with the aid of X-ray micro-computed tomography (μCT), and employs a multi-sphere representation to reconstruct non-spherical particles. Through discrete-element method (DEM) simulations of granular samples composed of these non-spherical clumps, the effect of particle shape on the macroscopic mechanical response and microscopic soil fabric evolution is examined for soil assemblies under triaxial compression. Simulation results indicate that materials with more irregular particles tend to show higher shear resistance in both peak and critical states, while exhibiting higher void ratio under isotropic loading conditions and in the critical state. The proposed critical state parameters for describing the sensitivity of the mean coordination number to confining pressures are larger as particles become more irregular. At a microscopic level of observation, directional and scalar parameters of particle contacts are sensitive to predefined particle shapes. More irregular materials appear to exhibit higher fabric anisotropy with respect to particle orientation in the critical state, while the branch vector is affected by both contact modes and particle shape. The critical stress ratio from the simulation results is validated by comparing with experimental results, and further found to be linearly linked to the shape-weighted fabric anisotropy indices.

Few-shot SAR vehicle target augmentation based on generative adversarial networks

Abstract. The study of few-shot SAR image generation is an effective way to expand the SAR dataset, which not only provides diversified data support for SAR target classification, but also provides a high-fidelity false image template for SAR deceptive jamming. In this paper, we have constructed a multi-frequency and multi-target type SAR vehicle imagery dataset that encompasses frequencies such as X, Ka, P, and S bands. The vehicle types are coaster, suv and cabin. Subsequently, we utilized various Generative Adversarial Networks for image generation from the SAR vehicle dataset. The experimental result indicates that the images generated by the DCGAN and the LSGAN models are of superior quality. Furthermore, we employed different recognition networks to evaluate the classification accuracy of the generated images. Of all the frequency bands, the Ka band generated images achieved the highest recognition rate, with an accuracy of up to 99%. Under conditions of a limited number of samples, the LSGAN model performed the best, reaching a classification recognition rate of 71.48% with a dataset of only 20 samples. Finally, we use a conditional network generation model to generate conditions based on target categories and frequency bands, providing high fidelity samples for SAR deception jamming.

Enhancing medical image classification with generative AI using latent denoising diffusion probabilistic model and wiener filtering approach

In the evolving landscape of medical diagnostics, a paradigm shift is being catalysed by the advent of generative artificial intelligence. Medical X-ray, CT and MRI images are essential diagnostic tools used by healthcare professionals to assess various musculoskeletal conditions. However, obtaining a sufficient number of medical images for training deep learning models can be challenging due to limited access to labelled data. Hence, the authors propose a novel Latent diffusion process for synthesizing medical images that closely resemble real patient images, aiming to address the challenge of limited access to labelled data in medical diagnostics. Leveraging deep learning and generative modelling techniques, this method synthesizes high-fidelity images that closely mimic real patient scans. By introducing noise and subsequently training the model to denoise, the approach captures intricate patterns inherent in authentic medical images. Among the four datasets utilized, the Diabetes Retinopathy dataset demonstrates superior performance, achieving the highest Mean Structural Similarity Index (MSSIM) score of 0.57 (compared to the dataset baseline of 0.62) and an accuracy of 93.75% when passed through the proposed pipeline. The Cataract dataset, registered a MSSIM score of 0.51 (versus the dataset baseline of 0.53) and an accuracy score of 97.52%, while the Knee OA dataset follows closely with MSSIM and accuracy scores of 0.65 (in contrast to the dataset baseline of 0.63) and 68.66% respectively. The results obtained are then compared with the results generated by the other state of the art models.

3D-DGGAN: A Data-Guided Generative Adversarial Network for High Fidelity in Medical Image Generation.

Three-dimensional images are frequently used in medical imaging research for classification, segmentation, and detection. However, the limited availability of 3D images hinders research progress due to network training difficulties. Generative methods have been proposed to create medical images using AI techniques. Nevertheless, 2D approaches have difficulty dealing with 3D anatomical structures, which can result in discontinuities between slices. To mitigate these discontinuities, several 3D generative networks have been proposed. However, the scarcity of available 3D images makes training these networks with limited samples inadequate for producing high-fidelity 3D images. We propose a data-guided generative adversarial network to provide high fidelity in 3D image generation. The generator creates fake images with noise using reference code obtained by extracting features from real images. The generator also creates decoded images using reference code without noise. These decoded images are compared to the real images to evaluate fidelity in the reference code. This generation process can create high-fidelity 3D images from only a small amount of real training data. Additionally, our method employs three types of discriminator: volume (evaluates all the slices), slab (evaluates a set of consecutive slices), and slice (evaluates randomly selected slices). The proposed discriminator enhances fidelity by differentiating between real and fake images based on detailed characteristics. Results from our method are compared with existing methods by using quantitative analysis such as Fréchet inception distance and maximum mean discrepancy. The results demonstrate that our method produces more realistic 3D images than existing methods.

Iterative reconstruction for limited-angle CT using implicit neural representation

Objective. Limited-angle computed tomography (CT) presents a challenge due to its ill-posed nature. In such scenarios, analytical reconstruction methods often exhibit severe artifacts. To tackle this inverse problem, several supervised deep learning-based approaches have been proposed. However, they are constrained by limitations such as generalization issue and the difficulty of acquiring a large amount of paired CT images. Approach. In this work, we propose an iterative neural reconstruction framework designed for limited-angle CT. By leveraging a coordinate-based neural representation, we formulate tomographic reconstruction as a convex optimization problem involving a deep neural network. We then employ differentiable projection layer to optimize this network by minimizing the discrepancy between the predicted and measured projection data. In addition, we introduce a prior-based weight initialization method to ensure the network starts optimization with an informed initial guess. This strategic initialization significantly improves the quality of iterative reconstruction by stabilizing the divergent behavior in ill-posed neural fields. Our method operates in a self-supervised manner, thereby eliminating the need for extensive data. Main results. The proposed method outperforms other iterative and learning-based methods. Experimental results on XCAT and Mayo Clinic datasets demonstrate the effectiveness of our approach in restoring anatomical features as well as structures. This finding was substantiated by visual inspections and quantitative evaluations using NRMSE, PSNR, and SSIM. Moreover, we conduct a comprehensive investigation into the divergent behavior of iterative neural reconstruction, thus revealing its suboptimal convergence when starting from scratch. In contrast, our method consistently produced accurate images by incorporating an initial estimate as informed initialization. Significance. This work showcases the feasibility to reconstruct high-fidelity CT images from limited-angle x-ray projections. The proposed methodology introduces a novel data-free approach to enhance medical imaging, holding promise across various clinical applications.

Robust residual-guided iterative reconstruction for sparse-view CT in small animal imaging

Objective. We introduce a robust image reconstruction algorithm named residual-guided Golub–Kahan iterative reconstruction technique (RGIRT) designed for sparse-view computed tomography (CT), which aims at high-fidelity image reconstruction from a limited number of projection views. Approach. RGIRT utilizes an inner-outer dual iteration framework, with a flexible least square QR (FLSQR) algorithm implemented in the inner iteration and a restarted iterative scheme applied in the outer iteration. The inner FLSQR employs a flexible Golub–Kahan bidiagonalization method to reduce the size of the inverse problem, and a weighted generalized cross-validation method to adaptively estimate the regularization hyper-parameter. The inner iteration efficiently yields the intermediate reconstruction result, while the outer iteration minimizes the residual and refines the solution by using the result obtained from the inner iteration. Main results. The reconstruction performance of RGIRT is evaluated and compared to other reference methods (FBPConvNet, SART-TV, and FLSQR) using projection data from both numerical phantoms and real experimental Micro-CT data. The experimental findings, from testing various numbers of projection views and different noise levels, underscore the robustness of RGIRT. Meanwhile, theoretical analysis confirms the convergence of residual for our approach. Significance. We propose a robust iterative reconstruction algorithm for x-ray CT scans with sparse views, thereby shortening scanning time and mitigating excessive ionizing radiation exposure to small animals.

Conditioning diffusion models via attributes and semantic masks for face generation

Deep generative models have shown impressive results in generating realistic images of faces. GANs managed to generate high-quality, high-fidelity images when conditioned on semantic masks, but they still lack the ability to diversify their output. Diffusion models partially solve this problem and are able to generate diverse samples given the same condition. This paper introduces a novel strategy for enhancing diffusion models through multi-conditioning, harnessing cross-attention mechanisms to utilize multiple feature sets, ultimately enabling the generation of high-quality and controllable images. The proposed method extends previous approaches by introducing conditioning on both attributes and semantic masks, ensuring finer control over the generated face images. In order to improve the training time and the generation quality, the impact of applying perceptual-focused loss weighting into the latent space instead of the pixel space is also investigated. The proposed solution has been evaluated on the CelebA-HQ dataset, and it can generate realistic and diverse samples while allowing for fine-grained control over multiple attributes and semantic regions. Experiments on the DeepFashion dataset have also been performed in order to analyze the capability of the proposed model to generalize to different domains. In addition, an ablation study has been conducted to evaluate the impact of different conditioning strategies on the quality and diversity of the generated images.