Complementary Images Research Articles

Hybrid-Layer Data Storage with High-Orthogonality Random Meta-Channels

Optical data storage (ODS) is a low-cost and high-durability counterpart of traditional electronic or magnetic storage. As a means of enhancing ODS capacity, the multiple recording layer (MRL) method is more promising than other approaches such as reducing the recording volume and multiplexing technology. However, the architecture of current MRLs is identical to that of recording data into physical layers with rigid space, which leads to either severe interlayer crosstalk or finite recording layers constrained by the short working distances of the objectives. Here, we propose the concept of hybrid-layer ODS, which can record optical information into a physical layer and multiple virtual layers by using high-orthogonality random meta-channels. In the virtual layer, 32 images are experimentally reconstructed through holography, where their holographic phases are encoded into 16 printed images and complementary images in the physical layer, yielding a capacity of 2.5 Tbit·cm−3. A higher capacity is achievable with more virtual layers, suggesting hybrid-layer ODS as a possible candidate for next-generation ODS.

LACOSTE: Exploiting stereo and temporal contexts for surgical instrument segmentation

Surgical instrument segmentation is instrumental to minimally invasive surgeries and related applications. Most previous methods formulate this task as single-frame-based instance segmentation while ignoring the natural temporal and stereo attributes of a surgical video. As a result, these methods are less robust against the appearance variation through temporal motion and view change. In this work, we propose a novel LACOSTE model that exploits Location-Agnostic COntexts in Stereo and TEmporal images for improved surgical instrument segmentation. Leveraging a query-based segmentation model as core, we design three performance-enhancing modules. Firstly, we design a disparity-guided feature propagation module to enhance depth-aware features explicitly. To generalize well for even only a monocular video, we apply a pseudo stereo scheme to generate complementary right images. Secondly, we propose a stereo-temporal set classifier, which aggregates stereo-temporal contexts in a universal way for making a consolidated prediction and mitigates transient failures. Finally, we propose a location-agnostic classifier to decouple the location bias from mask prediction and enhance the feature semantics. We extensively validate our approach on three public surgical video datasets, including two benchmarks from EndoVis Challenges and one real radical prostatectomy surgery dataset GraSP. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches.

C0-C1 joint injection: Anatomical, clinical and technical review

BackgroundCervicogenic headaches (CGH) are proven clinical entities. The prevalence of CGH arising from the atlanto-occipital (AO) joint is unknown. The best evidence for treatment of CGH is for third occipital nerve radiofrequency neurotomy. Treatment of CGH includes intra-articular injections into upper cervical spine joints. ObjectiveTo perform a review of the anatomy and clinical presentation of AO joint (AOJ) pain referral as well as a technical description to safely access the AOJ. MethodsA literature review was performed to explore the intricacies of the cranio-cervical junction (CCJ) with a focus on the relation between the AOJ and vascular anatomy. Our technical approach is described with complementary images. ResultsThe AOJ lies anterior to a venous sinus and slightly superior to the horizontally oriented vertebral artery crossing the joint line. ConclusionThe authors propose a modified superior needle trajectory that seeks to avoid these vascular structures and to access the AOJ safely.

Multimodal Image Confidence: A Novel Method for Tumor and Organ Boundary Representation

BackgroundThe ambiguous boundaries of tumors and organs at risk (OARs) seen in medical images pose challenges in treatment planning and other tasks in radiotherapy. MethodsThis study introduces an innovative analytical algorithm, Multi-Modal Image Confidence (MMC), which exploits the collective strengths of complementary multi-modal medical images to determine a confidence measure for each voxel belonging to the region of interest (ROI). MMC facilitates the creation of modality-specific ROI-enhanced images, enabling a detailed representation of the ROI's boundaries and internal features. By employing an interpretable mathematical model that propagates voxel confidence based on inter-voxel correlations, MMC avoids the need for model training, distinguishing it from deep learning (DL)-based methods. ResultsThe performance of the proposed algorithm was qualitatively and quantitatively evaluated using 156 nasopharyngeal carcinoma cases and 1251 glioma cases. Qualitative assessments underscored the accuracy of MMC and ROI-enhanced images in estimating lesion boundaries and capturing internal tumor characteristics. Quantitative analyses revealed strong agreement between MMC and manual delineations. ConclusionThis paper introduces a novel analytical algorithm to identify and depict ROI boundaries based on complementary multi-modal 3D medical images. The applicability of the proposed method can extend to both targets and OARs at diverse anatomical sites across multiple image modalities, amplifying its potential for augmenting radiotherapy-related tasks.

The impact of co-branding on consumer purchase intentions in the automotive industry

This study aims to delve into the influence of co-branding on consumer purchase intentions in the automotive industry and the impact of brand image. It seeks to analyze how co-branding is carried out, its characteristics, and how it affects consumers' brand perceptions and purchase decisions, especially exploring consumers' acceptance and willingness to buy co-branded products. A quantitative research methodology is adopted, involving questionnaire design and data collection through an online survey. Multiple analyses, such as frequency, reliability, validity, factor, correlation, and regression analyses, are conducted to examine the data. Co-branding has a positive effect on consumer purchase intention. Brand fit, innovativeness, and product complementarity are crucial factors contributing to the success of co-branding. Brand image has a positive moderating impact, and complementary brand images enhance consumers' purchase intention. The study also reveals that these factors can explain a significant portion of the variance in purchase intention. Automobile brands can enhance their attractiveness and market competitiveness by engaging in co-branding with suitable brands, focusing on brand fit, innovation, and product complementarity. Maintaining and enhancing a positive brand image is of great importance. Additionally, demographic information can help brands target consumers more effectively and design co-branding campaigns that better meet consumers' needs and preferences. These findings offer practical guidance for marketers to utilize co-branding strategies more efficiently and boost brand value.

Deep-learning-assisted inverse design of polarization-multiplexed structural color filters with ultrahigh saturation based on all-dielectric metasurface

Although great progress has been made for metasurface-based structural color filters, there are still significant challenges in encoding metasurfaces with complex color images, especially in high saturation or multi-channel cases, where traditional iterative optimization calculations demand substantial computational resources. Here, we proposed a dual-channel multilayered all-dielectric metasurface that can generate structural colors accounting for 224% Standard RGB space, 168% Adobe RGB space and 78% of the 1931 CIE chromaticity space under vertically-polarized incidence. A deep learning-based designing approach is introduced to significantly reduce the computing consumption while maintaining high accuracy. Numerical simulations further demonstrated that the proposed design method is effective for encoding both complementary and independent images with high saturation and wide color gamut. Therefore, the proposed color filters may find potential applications in image display, information encryption and optical anti-counterfeiting.

Imaging the shallow velocity structure of the slow‐spreading ridge of the South China Sea with downward continued multichannel seismic data

AbstractHigh‐resolution shallow oceanic crust velocity models provide crucial information on the tectonothermal history of the oceanic crust. The ocean bottom seismometers record wide‐angle seismic reflection and refraction data to image deeper structures compared with streamer data set. However, most ocean bottom seismometers experiments produce low‐resolution velocity models with limited shallow crustal structure due to sparse ocean bottom seismometers spacing. Multichannel seismic data recorded by towed streamers provide complementary seismic images of the oceanic crust but yield little information on subseafloor velocity because most subseafloor refractions are masked by seafloor reflections. Therefore, it is difficult to obtain fine‐scale velocity structure of shallow upper oceanic crust with both ocean bottom seismometers and multichannel seismic data. Downward continuation technique redatumed the shots and receivers to the seafloor to collapse the seafloor reflections to the zero offset and extract refractions as first arrivals from nearly zero offset, enabling dense ray coverage at the shallow crust. We applied the downward continuation and traveltime tomography methods to two synthetic models, Marmousi and SEAM Phase I Salt models, to demonstrate the performance of the strategy in the situations of flat seafloor and rough seafloor topography. We conducted the first‐arrival traveltime tomography on downward continued towed‐streamer multichannel seismic data across a slow‐spreading ridge of the South China Sea, providing unprecedented details of shallow velocity structure in the sediments. The low velocity sediments revealed by traveltime tomography match well with the prestack depth migration profile.

Co-Mask R-CNN: collaborative learning-based method for tooth instance segmentation.

Traditional tooth image analysis methods primarily focus on feature extraction from individual images, often overlooking critical tooth shape and position information. This paper presents a novel computer-aided diagnosis method, Collaborative learning with Mask Region-based Convolutional Neural Network (Co-Mask R-CNN), designed to enhance tooth image analysis by leveraging the integration of complementary information. First, image enhancement is employed to generate an edge-enhanced tooth edge image. Then, a collaborative learning strategy combined with Mask R-CNN is introduced, where the original and edge images are input simultaneously, and a two-stream encoder extracts feature maps from complementary images. By utilizing an attention mechanism, the output features from the two branches are dynamically fused, quantifying the relative importance of the two complementary images at different spatial positions. Finally, the fused feature map is utilized for tooth instance segmentation. Extensive experiments are conducted using a proprietary dataset to evaluate the effectiveness of Co-Mask R-CNN, and the results are compared against those of an alternative segmentation network. The results demonstrate that Co-Mask R-CNN outperforms the other networks in terms of both segmentation accuracy and robustness. Consequently, this method holds considerable promise for providing medical professionals with precise tooth segmentation results, establishing a reliable foundation for subsequent tooth disease diagnosis and treatment.

Laser Scanning Microscopy for Tomographic Imaging of Roughness and Point Absorbers in Optical Surfaces

High-precision laser interferometric instruments require optical surfaces with a close to perfect contour, as well as low scattering and absorption. Especially, point absorbers are problematic because they heat up and locally deform the otherwise flat surface, resulting in correlations between absorption and contour. Here, we present a spiral laser scanning microscopy approach for the reconstruction of the 2 complementary images of an optical surface. The “phase image” is related to the surface profile including roughness. Our experiment achieves a sensitivity of up to (3.1±1.4) fm/ Hz with a (5.29±0.06)-μm transversal resolution. The “loss image” localizes point absorbers. The 2 images show correlations for some features proving the particular strength of our tomographic approach, which should help further improving optical surfaces or to understand dynamic processes of surface physics.

A PSCLC Pattern Prepared Based on Handedness Inversion for Anti-counterfeiting.

Handedness inversion has been widely studied in supramolecular chemistry and material sciences. Herein, a photoisomerizable chiral dopant was synthesized, which could induce the formation of a cholesteric phase with right-handedness. The Bragg reflection band of the cholesteric liquid crystal (CLC) mixture shifted to the long wavelength with extending 365 nm UV light irradiation time. Based on this photochromic property, a colourful polymer-stabilized CLC (PSCLC) film was prepared using a grayscale mask. A handedness reversible CLC mixture was prepared using a mixture of this chiral dopant and S5011. With extending the UV light irradiation time, the handedness of the CLC mixture changed from right- to left-handedness. A patterned PSCLC film was prepared using this CLC mixture. Complementary images were observed under right- and left-handedness circularly polarized lights. The results shown here not only give us a better understanding the competition between photopolymerization and photoisomerization, but also lay the foundations for decoration and anti-counterfeiting.

In Situ Ultra-Small- and Small-Angle X-ray Scattering Study of ZnO Nanoparticle Formation and Growth through Chemical Bath Deposition in the Presence of Polyvinylpyrrolidone.

ZnO inverse opals combine the outstanding properties of the semiconductor ZnO with the high surface area of the open-porous framework, making them valuable photonic and catalysis support materials. One route to produce inverse opals is to mineralize the voids of close-packed polymer nanoparticle templates by chemical bath deposition (CBD) using a ZnO precursor solution, followed by template removal. To ensure synthesis control, the formation and growth of ZnO nanoparticles in a precursor solution containing the organic additive polyvinylpyrrolidone (PVP) was investigated by in situ ultra-small- and small-angle X-ray scattering (USAXS/SAXS). Before that, we studied the precursor solution by in-house SAXS at T = 25 °C, revealing the presence of a PVP network with semiflexible chain behavior. Heating the precursor solution to 58 °C or 63 °C initiates the formation of small ZnO nanoparticles that cluster together, as shown by complementary transmission electron microscopy images (TEM) taken after synthesis. The underlying kinetics of this process could be deciphered by quantitatively analyzing the USAXS/SAXS data considering the scattering contributions of particles, clusters, and the PVP network. A nearly quantitative description of both the nucleation and growth period could be achieved using the two-step Finke-Watzky model with slow, continuous nucleation followed by autocatalytic growth.

Synthetic Attenuation Correction Maps for SPECT Imaging Using Deep Learning: A Study on Myocardial Perfusion Imaging.

(1) Background: The CT-based attenuation correction of SPECT images is essential for obtaining accurate quantitative images in cardiovascular imaging. However, there are still many SPECT cameras without associated CT scanners throughout the world, especially in developing countries. Performing additional CT scans implies troublesome planning logistics and larger radiation doses for patients, making it a suboptimal solution. Deep learning (DL) offers a revolutionary way to generate complementary images for individual patients at a large scale. Hence, we aimed to generate linear attenuation coefficient maps from SPECT emission images reconstructed without attenuation correction using deep learning. (2) Methods: A total of 384 SPECT myocardial perfusion studies that used 99mTc-sestamibi were included. A DL model based on a 2D U-Net architecture was trained using information from 312 patients. The quality of the generated synthetic attenuation correction maps (ACMs) and reconstructed emission values were evaluated using three metrics and compared to standard-of-care data using Bland-Altman plots. Finally, a quantitative evaluation of myocardial uptake was performed, followed by a semi-quantitative evaluation of myocardial perfusion. (3) Results: In a test set of 66 test patients, the ACM quality metrics were MSSIM = 0.97 ± 0.001 and NMAE = 3.08 ± 1.26 (%), and the reconstructed emission quality metrics were MSSIM = 0.99 ± 0.003 and NMAE = 0.23 ± 0.13 (%). The 95% limits of agreement (LoAs) at the voxel level for reconstructed SPECT images were: [-9.04; 9.00]%, and for the segment level, they were [-11; 10]%. The 95% LoAs for the Summed Stress Score values between the images reconstructed were [-2.8, 3.0]. When global perfusion scores were assessed, only 2 out of 66 patients showed changes in perfusion categories. (4) Conclusion: Deep learning can generate accurate attenuation correction maps from non-attenuation-corrected cardiac SPECT images. These high-quality attenuation maps are suitable for attenuation correction in myocardial perfusion SPECT imaging and could obviate the need for additional imaging in standalone SPECT scanners.

MALDI IMS-Derived Molecular Contour Maps: Augmenting Histology Whole-Slide Images.

Imaging mass spectrometry (IMS) provides untargeted, highly multiplexed maps of molecular distributions in tissue. Ion images are routinely presented as heatmaps and can be overlaid onto complementary microscopy images that provide greater context. However, heatmaps use transparency blending to visualize both images, obscuring subtle quantitative differences and distribution gradients. Here, we developed a contour mapping approach that combines information from IMS ion intensity distributions with that of stained microscopy. As a case study, we applied this approach to imaging data from Staphylococcus aureus-infected murine kidney. In a univariate, or single molecular species, use-case of the contour map representation of IMS data, certain lipids colocalizing with regions of infection were selected using Pearson's correlation coefficient. Contour maps of these lipids overlaid with stained microscopy showed enhanced visualization of lipid distributions and spatial gradients in and around the bacterial abscess as compared to traditional heatmaps. The full IMS data set comprising hundreds of individual ion images was then grouped into a smaller subset of representative patterns using non-negative matrix factorization (NMF). Contour maps of these multivariate NMF images revealed distinct molecular profiles of the major abscesses and surrounding immune response. This contour mapping workflow also enabled a molecular visualization of the transition zone at the host-pathogen interface, providing potential clues about the spatial molecular dynamics beyond what histological staining alone provides. In summary, we developed a new IMS-based contour mapping approach to augment classical stained microscopy images, providing an enhanced and more interpretable visualization of IMS-microscopy multimodal molecular imaging data sets.

Dual-branch deep image prior for image denoising

In this work, we propose a two-stage denoising approach, which includes generation and fusion stages. Specifically, in the generation stage, we first split the expanding path of the UNet backbone of the standard DIP (deep image prior) network into two branches, converting it into a Y-shaped network (YNet). Then we adopt the initial denoised images obtained with DAGL (dynamic attentive graph learning) and Restormer methods together with the given noisy image as the target images. Finally, we utilize the standard DIP on-line training routine to generate two complementary basic images, whose image quality is quite improved, with the help of a novel automatic iteration termination mechanism. In the fusion stage, we first split the contracting path of the standard UNet network into two branches for receiving the two basic images generated in the previous stage, and obtain a fused image as the final denoised image in a fully unsupervised manner. Extensive experimental results confirm that our method has a significant improvement over the standard DIP or other unsupervised methods, and outperforms recently proposed supervised denoising models. The noticeable performance improvement is attributed to the proposed hybrid strategy, i.e., we first adopt the supervised denoising methods to process the common content of images substantially, then utilize the unsupervised method to fine-tune the specific details. In other words, we take full advantage of the high performance of the supervised methods and the flexibility of the unsupervised methods.

Fisiopatología y algoritmo diagnóstico y terapéutico del MINOCA

MINOCA es un síndrome que abarca varias patologías y que ocurre en el contexto clínico de un Síndrome Coronario Agudo. Su incidencia varía de acuerdo con la población estudiada, métodos de diagnósticos utilizados y si han incluido a la Miocarditis y Síndrome de Takotsubo, los cuáles, fueron excluidos recientemente de la definición de MINOCA. Por esta razón, consideramos que la novedad de esta publicación es la no inclusión de estas dos patologías y, por lo tanto, el objetivo de la presente revisión es actualizar este síndrome de forma concisa. También se aborda el manejo de los tres tipos de MINOCA, cuyo diagnóstico se basa fundamentalmente en la utilización de imágenes complementarias específicas, ya que la coronariografia tiene sus limitaciones. El tratamiento será en general farmacológico de acuerdo con el mecanismo fisiopatológico involucrado.

Facial Expression Recognition Through Cross-Modality Attention Fusion

Facial expressions are generally recognized based on handcrafted and deep-learning-based features extracted from RGB facial images. However, such recognition methods suffer from illumination/pose variations. In particular, they fail to recognize these expressions with weak emotion intensities. In this work, we propose a cross-modality attention-based convolutional neural network (CM-CNN) for facial expression recognition. We extract expression-related features from complementary facial images (gray-scale, local binary pattern, and depth images) to handle the illumination/pose variations and to capture appearance details that describe expressions with weak emotion intensities. Rather than directly concatenating the complementary features, we propose a novel cross-modality attention fusion network to enhance spatial correlations between any two types of facial images. Finally, the CM-CNN is optimized with an improved focal loss, which pays more attention to facial expressions with weak emotion intensities. The average classification accuracies on VT-KFER, BU-3DFE(P1), BU-3DFE(P2), and Bosphorus are 93.86%, 88.91%, 87.28%, and 85.16%, respectively. Evaluations on these databases demonstrate that our approach is competitive to state-of-the-art algorithms.

A Perception-Aware Decomposition and Fusion Framework for Underwater Image Enhancement

This paper presents a perception-aware decomposition and fusion framework for underwater image enhancement (UIE). Specifically, a general structural patch decomposition and fusion (SPDF) approach is introduced. SPDF is built upon the fusion of two complementary pre-processed inputs in a perception-aware and conceptually independent image space. First, a raw underwater image is pre-processed to produce two complementary versions including a contrast-corrected image and a detail-sharpened image. Then, each of them is decomposed into three conceptually independent components, i.e., mean intensity, contrast, and structure, via structural patch decomposition (SPD). Afterwards, the corresponding components are fused using tailored strategies. The three components after fusion are finally integrated via inverting the decomposition to reconstruct a final enhanced underwater image. The main advantage of SPDF is that two complementary pre-processed images are fused in a perception-aware and conceptually independent image space and the fusions of different components can be performed separately without any interactions and information loss. Comprehensive comparisons on two benchmark datasets demonstrate that SPDF outperforms several state-of-the-art UIE algorithms qualitatively and quantitatively. Moreover, the effectiveness of SPDF is also verified on another two relevant tasks, i.e., low-light image enhancement and single image dehazing. The code will be made available soon.

RDCa-Net: Residual dense channel attention symmetric network for infrared and visible image fusion

Infrared and visible image fusion aims to generate the desired fusion image by fusing complementary images from different sensors. Artificially generated images are more appropriate for human visual perception or further image-processing tasks. Although a variety of infrared and visible image fusion methods have been proposed in recent years, the degradation of the intermediate features and the loss of details in the network are still difficult to solve, resulting in the loss of details and generation of artifacts in the fused images. In this paper, a symmetrical skip attention network is constructed to solve these problems. The skip attention mechanism used in our network can compensate for the information lost in the feature extraction stage, which can reduce the loss of details in the fused images effectually. Meanwhile, we designed a weight block to calculate the information weight in the loss function. Thus, the network can retain source image information adaptively. A U-net with self-attention is designed to achieve the feature extraction in the weight block. The self-attention helps the network to extract more detailed features. And we conducted ablation experiments to verify the performance of different modules in the network. Extensive experimental results prove that the proposed fusion RDCa-Net is superior to the latest fusion methods in subjective and objective evaluation. In addition, we apply the fused images generated by our method to object detection. Compared with other fusion algorithms, our method has a higher confidence level for both infrared and visible targets. It proves the potential of our method in promoting advanced visual tasks.

Non Sub-Sampled Contourlet with Joint Sparse Representation Based Medical Image Fusion

Medical Image Fusion is the synthesizing technology for fusing multimodal medical information using mathematical procedures to generate better visual on the image content and high-quality image output. Medical image fusion represents an indispensible role in fixing major solutions for the complicated medical predicaments, while the recent research results have an enhanced affinity towards the preservation of medical image details, leaving color distortion and halo artifacts to remain unaddressed. This paper proposes a novel method of fusing Computer Tomography (CT) and Magnetic Resonance Imaging (MRI) using a hybrid model of Non Sub-sampled Contourlet Transform (NSCT) and Joint Sparse Representation (JSR). This model gratifies the need for precise integration of medical images of different modalities, which is an essential requirement in the diagnosing process towards clinical activities and treating the patients accordingly. In the proposed model, the medical image is decomposed using NSCT which is an efficient shift variant decomposition transformation method. JSR is exercised to extricate the common features of the medical image for the fusion process. The performance analysis of the proposed system proves that the proposed image fusion technique for medical image fusion is more efficient, provides better results, and a high level of distinctness by integrating the advantages of complementary images. The comparative analysis proves that the proposed technique exhibits better-quality than the existing medical image fusion practices.

A multi‐view image fusion algorithm for industrial weld

Multi-view image fusion can be used to extract features from redundant and complementary multisource images. And the technique of obtaining high quality fusion images has become one of the research hotspots for image processing. In order to realize defect detection and intelligent grinding smoothly, multi-view fusion technology was applied in the field of overexposure and underexposure industrial welds, achieving high quality image enhancement. When preparing the data set of multi-view images, a hybrid registration algorithm with high matching ability is proposed. The data set of overexposure and underexposure weld images was obtained successfully by using the registration algorithm. In order to improve the fusion ability of overexposure and underexposure industrial welds, we propose a novel multi-view image fusion algorithm based on deep learning. The multi-view fusion algorithm uses an autoencoder network structure, and its innovation lies in a parallel branch network with lightweight structure and strong generalization ability. The experimental results demonstrate that compared with other classical multi-view algorithms, our proposed algorithm gets the best parameters on the industrial weld data set in peak signal to noise ratio (PSNR) and root mean square error (RMSE), reaching 59.12 and 0.084, respectively. And the ablation and performance comparison experiments verify that the proposed parallel branch network has better generalization ability and fusion accuracy than other classical multi branch networks.