Search

Abstract The long-term association between mRNA-based coronavirus disease 2019 (COVID-19) vaccination and the development of autoimmune connective tissue diseases (AI-CTDs) remains unclear. In this nationwide, population-based cohort study involving 9,258,803 individuals, we aim to determine whether the incidence of AI-CTDs is associated with mRNA vaccination. The study spans over 1 year of observation and further analyses the risk of AI-CTDs by stratifying demographics and vaccination profiles and treating booster vaccination as time-varying covariate. We report that the risk of developing most AI-CTDs did not increase following mRNA vaccination, except for systemic lupus erythematosus with a 1.16-fold risk in vaccinated individuals relative to controls. Comparable results were reported in the stratified analyses for age, sex, mRNA vaccine type, and prior history of non-mRNA vaccination. However, a booster vaccination was associated with an increased risk of some AI-CTDs including alopecia areata, psoriasis, and rheumatoid arthritis. Overall, we conclude that mRNA-based vaccinations are not associated with an increased risk of most AI-CTDs, although further research is needed regarding its potential association with certain conditions.

Old photos that were captured about a century ago have archaeological and historical significance. Many of the old photos have been successfully digitized, but most of them suffer from severe and complicated distortion. Thus, prior studies have focused on image restoration tasks such as denoising, inpainting, and colorization. In this paper, we pay attention to the depth estimation of old photos, enabling a more enjoyable appreciation of them and helping better understand past human life, activities, and environments. Because most old photos are available as single-view images, monocular depth estimation techniques can be considered a solution. However, most high-performance techniques are based on supervised learning, which requires ground-truth depth maps. Because this kind of supervised learning is not feasible for old photos, in this paper, we present a learning framework that finetunes a pretrained monocular depth estimation network for each old photo. Specifically, the pretrained monocular depth estimation network predicts stereo depth maps for stereo image rendering. Then, the pretrained stereo network predicts depth estimates from the rendered stereo image pair. By extracting reliable depth estimates and using them for supervision of the monocular network, the monocular network can be gradually learned to produce a high-quality depth map of the given old photo. From the qualitative and quantitative performance evaluations on old photos, we demonstrate the effectiveness of the proposed method.

Abstract Deep-learning-based survival prediction can assist doctors by providing additional information for diagnosis by estimating the risk or time of death. The former focuses on ranking deaths among patients based on the Cox model, whereas the latter directly predicts the survival time of each patient. However, it is observed that survival time prediction for the patients, particularly with close observation times, possibly has incorrect orders, leading to low prediction accuracy. Therefore, in this paper, we present a whole slide image (WSI)-based survival time prediction method that takes advantage of both the risk as well as time prediction. Specifically, we propose to combine these two approaches by extracting the risk prediction features and using them as guides for the survival time prediction. Considering the high resolution of WSIs, we extract tumor patches from WSIs using a pre-trained tumor classifier and apply the graph convolutional network to aggregate information across these patches effectively. Extensive experiments demonstrate that the proposed method significantly improves the time prediction accuracy when compared with direct prediction of the survival times without guidance and outperforms existing methods.

Images captured from real-world environments often include blur artifacts resulting from camera movement, dynamic object motion, or out-of-focus. Although such blur artifacts are inevitable, most object detection methods do not have special considerations for them; therefore, they may fail to detect objects in blurry images. One possible solution is applying image deblurring prior to object detection. However, this solution is computationally demanding and its performance heavily depends on image deblurring results. In this study, we propose a novel blur-aware object detection framework. First, we construct a synthetic but realistic dataset by applying a diverse set of motion blur kernels to blur-free images. Subsequently, we leverage self-guided knowledge distillation between the teacher and student networks that perform object detection using blur-free and blurry images, respectively. The teacher and student networks share most of their network parameters and jointly learn in a fully-supervised manner. The teacher network provides image features as hints for feature-level deblurring and also renders soft labels for the training of the student network. Guided by the hints and the soft labels from the teacher, the student network learns and expands their knowledge on object detection in blurry images. Experimental results show that the proposed framework improves the robustness of several widely used object detectors against image blurs.

Pathology image classification is an important step in cancer diagnosis and precision treatment. Training a pathology image classification model in a fully supervised manner requires exhaustive pixel-level manual annotations from pathologists, which may not be practical in real applications. Semi-supervised learning (SSL) has been widely used to exploit large amounts of unlabeled data to facilitate model training with a small set of labeled data. However, due to the limited annotations, it still suffers from the issue of inaccurate pseudo-labels of unlabeled data. In this paper, we propose a novel framework for semi-supervised pathology image classification, which incorporates graph-based segmentation to refine initial pseudo-labels of tissue regions by considering local and global contextual relationships of patches in whole-slide images (WSIs). Moreover, we define a new energy function for graph construction that allows the graph to take into account the uncertainty of network predictions on unlabeled data. Extensive experiments on two different pathology image datasets demonstrate the effectiveness of our method compared with state-of-the-art SSL baselines. In particular, when using 5% labeled data, our approach outperforms a strong baseline by 2.81% AUC.

In this study, a combined convolutional neural network for the diagnosis of three benign skin tumors was designed, and its effectiveness was verified through quantitative and statistical analysis. To this end, 698 sonographic images were taken and diagnosed at the Department of Dermatology at Severance Hospital in Seoul, Korea, between 10 November 2017 and 17 January 2020. Through an empirical process, a convolutional neural network combining two structures, which consist of a residual structure and an attention-gated structure, was designed. Five-fold cross-validation was applied, and the train set for each fold was augmented by the Fast AutoAugment technique. As a result of training, for three benign skin tumors, an average accuracy of 95.87%, an average sensitivity of 90.10%, and an average specificity of 96.23% were derived. Also, through statistical analysis using a class activation map and physicians’ findings, it was found that the judgment criteria of physicians and the trained combined convolutional neural network were similar. This study suggests that the model designed and trained in this study can be a diagnostic aid to assist physicians and enable more efficient and accurate diagnoses.

Abstract In 2020, it is estimated that 73,750 kidney cancer cases were diagnosed, and 14,830 people died from cancer in the United States. Preoperative multi-phase abdominal computed tomography (CT) is often used for detecting lesions and classifying histologic subtypes of renal tumor to avoid unnecessary biopsy or surgery. However, there exists inter-observer variability due to subtle differences in the imaging features of tumor subtypes, which makes decisions on treatment challenging. While deep learning has been recently applied to the automated diagnosis of renal tumor, classification of a wide range of subtype classes has not been sufficiently studied yet. In this paper, we propose an end-to-end deep learning model for the differential diagnosis of five major histologic subtypes of renal tumors including both benign and malignant tumors on multi-phase CT. Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention. We trained and tested the model using CT data from 308 patients who underwent nephrectomy for renal tumors. The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes. We further validated the model on an independent dataset of 184 patients from The Cancer Imaging Archive (TCIA). The AUC for this dataset was 0.855, and the model performed comparably to the radiologists. These results indicate that our model can achieve similar or better diagnostic performance than radiologists in differentiating a wide range of renal tumors on multi-phase CT.

Lossy video compression achieves coding gains at the expense of the quality loss of the decoded images. Owing to the success of deep learning techniques, especially convolutional neural networks (CNNs), many compression artifacts reduction (CAR) techniques have been used to significantly improve the quality of decoded images by applying CNNs which are trained to predict the original artifact-free images from the decoded images. Most existing video compression standards control the compression ratio using a quantization parameter (QP), so the quality of the decoded images is strongly QP-dependent. Training individual CNNs for predetermined QPs is one of the common approaches to dealing with different levels of compression artifacts. However, compression artifacts are also dependent on the local characteristics of an image. Therefore, a CNN trained for specific QP cannot fully remove the compression artifacts of all images, even those encoded using the same QP. In this paper, we introduce a pixel-precise network selection network (PNSNet). From multiple reconstructed images obtained using multiple QP-specific CAR networks, PNSNet is trained to find the best CAR network for each pixel. The output of PNSNet is then used as an explicit spatial attention channel for an image fusion network that combines multiple reconstructed images. Experimental results demonstrated that the quality of decoded images can be significantly improved by the proposed multiple CAR network fusion method.

Depth maps acquired by low-cost sensors have low spatial resolution, which restricts their usefulness in many image processing and computer vision tasks. To increase the spatial resolution of the depth map, most state-of-the-art depth map super-resolution methods based on deep learning extract the features from a high-resolution guidance image and concatenate them with the features from the depth map. However, such simple concatenation can transfer unnecessary textures, known as texture copying artifacts, of the guidance image to the depth map. To address this problem, we propose a novel depth map super-resolution method using guided deformable convolution. Unlike standard deformable convolution, guided deformable convolution obtains 2D kernel offsets of the depth features from the guidance features. Because the guidance features are not explicitly concatenated with the depth features but are used only to determine the kernel offsets for the depth features, the proposed method can significantly alleviate the texture copying artifacts in the resultant depth map. Experimental results show that the proposed method outperforms the state-of-the-art methods in terms of qualitative and quantitative evaluations.

X-ray baggage inspection has been widely used for maintaining airport and transportation security. Towards automated inspection, recent deep learning-based methods have attempted to detect hazardous objects directly from X-ray images. Since it is challenging to collect a large number of training images from real-world environments, most previous learning-based methods rely on image synthesis for training data generation. However, these methods randomly combine foreground and background images, restricting the effectiveness of synthetic images for object detection. To solve this problem, in this paper, we propose a learning-based X-ray image synthesis method for object detection. Specifically, for each foreground object to be synthesized, we first estimate positions difficult to detect by the object detector. These positions and their corresponding confidence values are then used to construct a difficulty map, which is used for sampling the target foreground position for image synthesis. The performance analysis using various state-of-the-art object detectors shows that the proposed synthesis method can produce more useful training data compared with the conventional random synthesis method.

Several recent studies have attempted to fully replace the conventional camera image signal processing (ISP) pipeline with convolutional neural networks (CNNs). However, the previous CNN-based ISPs, simply referred to as ISP-Nets, have not explicitly considered that images have to be lossy-compressed in most cases, especially by the off-the-shelf JPEG. To address this issue, in this paper, we propose a novel compression-aware deep camera ISP learning framework. At first, we introduce a new use case of compression artifacts simulation network (CAS-Net), which operates in the opposite way of commonly used compression artifacts reduction networks. Then, the CAS-Net is connected with an ISP-Net such that the ISP network can be trained with consideration of image compression. Throughout experimental studies, we show that our compression-aware camera ISP network can produce images with a better tradeoff between bit-rate and image quality compared to its compression-agnostic version when the performance is evaluated after JPEG compression.

Taking a high-quality selfie photo in a low-light environment is challenging. Because the foreground and background often have different illumination conditions, they suffer heavily from over/under-exposure issues and cannot be treated in the same manner when applying image enhancement algorithms. In this work, we propose DeepSelfie, a learning-based image enhancement framework for low-light selfie photos. We address selfie enhancement as a dual-layer image enhancement problem. The foreground and background are thus separately enhanced and combined together via image fusion. To train the selfie enhancement network, we also introduce a method of synthesizing pairs of noisy and dark raw selfie images and their corresponding well-illuminated images. Through extensive experiments of no-reference image quality assessment as well as human subjective evaluation, we show that DeepSelfie provides better results in comparison to several state-of-the-art methods. The code and datasets can be found at https://sites.google.com/view/deepselfie.

The census transform is a non-parametric local transform that is widely used in stereo matching. This transform encodes the structural information of a local patch into a binary code stream representing the relative intensity ordering of the pixels within the patch. Despite its high performance in stereo matching, the census transform often generates identical binary code streams for two different patches because it simply thresholds the pixels within the patch at the center pixel intensity. To overcome this problem, we introduce a quaternary census transform that encodes the local structural information into a quaternary code stream by employing both the relative intensity ordering and the minimum visibility threshold of the human eye known as the just-noticeable difference. Moreover, because the human eye activates different areas of the retina based on brightness, the patch size for the proposed quaternary census transform adaptively varies depending on the luminance of each pixel. Experimental results on well-known Middlebury stereo datasets prove that the proposed transform outperforms the other census transform-based methods in terms of the accuracy of stereo matching.

Semantic segmentation is one of the most commonly used techniques for road scene understanding. Recently developed deep learning-based semantic segmentation networks are typically based on the encoder-decoder structure and have made great progress in road scene understanding. However, these conventional networks still encounter difficulties in recovering spatial details. To overcome this problem, we introduce a lightweight prediction and boundary-aware refinement module that can hierarchically refine the segmentation results with spatial details. The proposed refinement module has two attention units called the upper-level prediction attention unit and the upper-level boundary attention unit. The upper-level prediction attention unit emphasizes the features in the regions that need to be refined by using predicted class probability from the upper-level, whereas the upper-level boundary attention unit focuses on the features near the semantic boundary of the upper-level segmentation result. By using the proposed prediction and boundary-aware refinement module in the decoder network, the segmentation result can gradually be improved in a top-down manner to a finer and more complete one. Experimental results on the Cityscapes and CamVid datasets demonstrate that the proposed prediction and boundary attention-based refinement module can achieve considerable performance improvement in segmentation accuracy with a marginal increase in computational complexity.

X-ray imaging is one of the most widely used security measures for maintaining airport and transportation security. Conventional X-ray imaging systems typically apply tone-mapping (TM) algorithms to visualize high-dynamic-range (HDR) X-ray images on a standard 8-bit display device. However, X-ray images obtained through traditional TM algorithms often suffer from halo artifacts or detail loss in inter-object overlapping regions, which makes it difficult for an inspector to detect unsafe or hazardous objects. To alleviate these problems, this article proposes a deep learning-based TM method for X-ray inspection. The proposed method consists of two networks called detail-recovery network (DR-Net) and TM network (TM-Net). The goal of DR-Net is to restore the details in the input HDR image, whereas TM-Net aims to compress the dynamic range while preserving the restored details and preventing halo artifacts. Since there are no standard ground-truth images available for the TM of X-ray images, we propose a novel loss function for unsupervised learning of TM-Net. We also introduce a dataset synthesis technique using the Beer-Lambert law for supervised learning of DR-Net. Extensive experiments comparing the performance of our proposed method with state-of-the-art TM methods demonstrate that the proposed method not only achieves visually compelling results but also improves the quantitative performance measures such as FSITM and HDR-VDP-2.2.

Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super‐resolution, and compression artifact reduction. By fully exploiting its characteristics, state‐of‐the‐art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN‐training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non‐negligible degradation of the objective image quality, including peak signal‐to‐noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression‐artifact reduction and super‐resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.

Facial expression recognition (FER) is a very challenging problem in computer vision. Although extensive research has been conducted to improve FER performance in recent years, there is still room for improvement. A common goal of FER is to classify a given face image into one of seven emotion categories: angry, disgust, fear, happy, neutral, sad, and surprise. In this paper, we propose to use a simple multi-layer perceptron (MLP) classifier that determines whether the current classification result is reliable or not. If the current classification result is determined as unreliable, we use the given face image as a query to search for similar images. In particular, facial action units are used to retrieve the images with a similar facial expression. Then, another MLP is trained to predict final emotion category by aggregating classification output vectors of the query image and its retrieved similar images. Experimental results on FER2013 dataset demonstrate that the performance of the state-of-the-art networks can be further improved by our proposed method.

Biologics are important treatment options for psoriasis; however, direct comparison of their efficacy, safety, and drug survival is insufficient in clinical practice. This retrospective single-center study aimed to compare the efficacy, safety, and drug survival of three commonly used psoriasis biologics (secukinumab, ustekinumab, and guselkumab) and identify the factors affecting drug survival in actual clinics in Korea. We enrolled 111 patients with moderate to severe psoriasis and for at least 56 weeks of follow-up; among these, 27, 23, and 61 were administered secukinumab, ustekinumab, and guselkumab, respectively. All groups were comparable with respect to their baseline characteristics. Secukinumab showed a rapid response, and guselkumab was superior in terms of a long-term response and complete remission compared with other biologics, while ustekinumab showed a lower efficacy compared with other biologics. All three biologics had a favorable and similar safety profile; however, allergic reactions and latent tuberculosis were more common with secukinumab and ustekinumab, respectively. Guselkumab was the most sustained biologic, and the survival rates of secukinumab and ustekinumab were similar. Drug survival was remarkably shorter in female patients and those with hypertension. Introduction of new biologics emerged as a negative factor for drug survival in clinical settings.

In this article, versatile video coding, the next-generation video coding standard, is combined with a deep convolutional neural network to achieve state-of-the-art image compression efficiency. The proposed hierarchical grouped residual dense network exhaustively exploits hierarchical features in each architectural level to maximize the image quality enhancement capability. The basic building block employed for hierarchical grouped residual dense network is residual dense block which exploits hierarchical features from internal convolutional layers. Residual dense blocks are then combined into a grouped residual dense block exploiting hierarchical features from residual dense blocks. Finally, grouped residual dense blocks are connected to comprise a hierarchical grouped residual dense block so that hierarchical features from grouped residual dense blocks can also be exploited for quality enhancement of versatile video coding intra-coded images. Various non-architectural and architectural aspects affecting the training efficiency and performance of hierarchical grouped residual dense network are explored. The proposed hierarchical grouped residual dense network respectively obtained 10.72% and 14.3% of Bjøntegaard-delta-rate gains against versatile video coding in the experiments conducted on two public image datasets with different characteristics to verify the image compression efficiency.

To correct an over-exposure within an image, the over-exposed region (OER) must first be detected. Detecting the OER accurately has a significant effect on the performance of the over-exposure correction. However, the results of conventional OER detection methods, which generally use the brightness and color information of each pixel, often deviate from the actual OER perceived by the human eye. To overcome this problem, in this paper, we propose a novel method for detecting the perceived OER more accurately. Based on the observation that recognizing the OER in an image is dependent on the saturation sensitivity of the human visual system (HVS), we detect the OER by thresholding the saturation value of each pixel. Here, a function of the proposed method, which is designed based on the results of a subjective evaluation on the saturation sensitivity of the HVS, adaptively determines the saturation threshold value using the color and the perceived brightness of each pixel. Experimental results demonstrate that the proposed method accurately detects the perceived OER, and furthermore, the over-exposure correction can be improved by adopting the proposed OER detection method.

Depth maps taken by the low cost Kinect sensor are often noisy and incomplete. Thus, post-processing for obtaining reliable depth maps is necessary for advanced image and video applications such as object recognition and multi-view rendering. In this paper, we propose adaptive directional filters that fill the holes and suppress the noise in depth maps. Specifically, novel filters whose window shapes are adaptively adjusted based on the edge direction of the color image are presented. Experimental results show that our method yields higher quality filtered depth maps than other existing methods, especially at the edge boundaries.

Segmentation of human bodies in images is useful for a variety of applications, including background substitution, human activity recognition, security, and video surveillance applications. However, human body segmentation has been a challenging problem, due to the complicated shape and motion of a non-rigid human body. Meanwhile, depth sensors with advanced pattern recognition algorithms provide human body skeletons in real time with reasonable accuracy. In this study, we propose an algorithm that projects the human body skeleton from a depth image to a color image, where the human body region is segmented in the color image by using the projected skeleton as a segmentation cue. Experimental results using the Kinect sensor demonstrate that the proposed method provides high quality segmentation results and outperforms the conventional methods.

Mesozooplankton are critical components of marine ecosystems, acting as key intermediaries between primary producers and higher trophic levels by grazing on phytoplankton and influencing fish populations. They play pivotal roles in the pelagic food web and export production, affecting the biogeochemical cycling of carbon and nutrients. Therefore, accurately modeling and visualizing mesozooplankton community dynamics is essential for understanding marine ecosystem patterns and informing effective management strategies. However, modeling these dynamics remains challenging due to the complex interplay among physical, chemical, and biological factors, and the detailed parameterization and feedback mechanisms are not fully understood in theory-driven models. Graph neural network (GNN) models offer a promising approach to forecast multivariate features and define correlations among input variables. The high interpretive power of GNNs provides deep insights into the structural relationships among variables, serving as a connection matrix in deep learning algorithms. However, there is insufficient understanding of how interactions between input variables affect model outputs during training. Here we investigate how the graph structure of ecosystem dynamics used to train GNN models affects their forecasting accuracy for mesozooplankton species. We find that forecasting accuracy is closely related to interactions within ecosystem dynamics. Notably, increasing the number of nodes does not always enhance model performance; closely connected species tend to produce similar forecasting outputs in terms of trend and peak timing. Therefore, we demonstrate that incorporating the graph structure of ecosystem dynamics can improve the accuracy of mesozooplankton modeling by providing influential information about species of interest. These findings will provide insights into the influential factors affecting mesozooplankton species and emphasize the importance of constructing appropriate graphs for forecasting these species.

In this paper, a high dynamic range (HDR) imaging method based on the stereo vision system is presented. The proposed method uses differently exposed low dynamic range (LDR) images captured from a stereo camera. The stereo LDR images are first converted to initial stereo HDR images using the inverse camera response function estimated from the LDR images. However, due to the limited dynamic range of the stereo LDR camera, the radiance values in under/over-exposed regions of the initial main-view (MV) HDR image can be lost. To restore these radiance values, the proposed stereo matching and hole-filling algorithms are applied to the stereo HDR images. Specifically, the auxiliary-view (AV) HDR image is warped by using the estimated disparity between initial the stereo HDR images and then effective hole-filling is applied to the warped AV HDR image. To reconstruct the final MV HDR, the warped and hole-filled AV HDR image is fused with the initial MV HDR image using the weight map. The experimental results demonstrate objectively and subjectively that the proposed stereo HDR imaging method provides better performance compared to the conventional method.

Moving objects of interest (MOOIs) in surveillance videos are detected and encapsulated by bounding boxes. Since moving objects are defined by temporal activities through the consecutive video frames, it is necessary to examine a group of frames (GoF) to detect the moving objects. To do that, the traces of moving objects in the GoF are quantified by forming a spatiotemporal gradient map (STGM) through the GoF. Each pixel value in the STGM corresponds to the maximum temporal gradient of the spatial gradients at the same pixel location for all frames in the GoF. Therefore, the STGM highlights boundaries of the MOOI in the GoF and the optimal bounding box encapsulating the MOOI can be determined as the local areas with the peak average STGM energy. Once an MOOI and its bounding box are identified, the inside and outside of it can be treated differently for object-aware size reduction. Our optimal encapsulation method for the MOOI in the surveillance videos makes it possible to recognize the moving objects even after the low bitrate video compressions.

Dokdo is an island located in the easternmost part of Korea, which has high levels of biodiversity of birds and fish, especially marine invertebrates. However, the biodiversity of microalgae, especially diatoms (Bacillariophyta), is relatively unknown, despite their ecological importance as primary producers of the marine food web and bioindicators of environmental conditions associated with climate change. To understand the biodiversity of seaweed-associated diatoms from Dokdo, we collected macroalgae present at a depth 5–15 m by SCUBA diving on 17 October 2017. There were a large number of diatoms (over 130 species), even though it was a one-time survey. As it includes too many taxa to cover at once, voucher flora for other taxonomic groups will be provided through the continuous serial papers. This is the first series of seaweed-associated diatoms, with 26 species belonging to the subphyla Melosirophytina and Coscinodisophytina, and the class Mediophyceae. Among these, seven species including one new taxon were reported for the first time in Korea, which, along with the geopolitical characteristics of the survey area, proved that there is no domestic interest in seaweed-related diatoms. In particular, the appearance of species that have been reported in subtropical waters, such as the order Ardissoneales, requires continuous monitoring of marine seaweed-associated diatoms to confirm whether their colonization in Dokdo waters was due to climate change or species-specific water temperature tolerance.

Chlamys farreri is primarily cultivated in Japan, China, and South Korea. Although mass mortality of scallops has been occurring recently, likely caused by high temperatures or infectious diseases, the underlying cause remains unclear. Little is known regarding the viral diseases affecting them. Therefore, we explored DNA virus diversity in the mid-gut gland of C. farreri and compared it with that of seawater. C. farreri was cultivated at depths below 5 m from the sea surface in the coastal waters of South Korea and sampled from May to August 2018. Different DNA viral communities were observed in both C. farreri and seawater. In C. farreri, prevalent groups included Mimiviridae (7%), Poxviridae (6%), and Phycodnaviridae (5%). Conversely, the dominant groups in seawater were Autographiviridae (20%), Kyanoviridae (12%), and Zobellviridae (10%). We identified C. farreri-specific viral communities and potentially infectious viruses, such as Ostreid herpesvirus 1 and Abalone herpesvirus Victoria/AUS/2009. Furthermore, C. farreri acts as a reservoir for various viruses, which impact microbial community dynamics and disease transmission in marine ecosystems. Understanding these viral communities is crucial to protecting and restoring coastal ecosystems by highlighting their role in the transmission of potential avian- and bivalve-specific viruses.

Among image restoration approaches, image deconvolution has been considered a powerful solution. In image deconvolution, a point spread function (PSF), which describes the blur of the image, needs to be determined. Therefore, in this paper, we propose an iterative PSF estimation algorithm which is able to estimate an accurate PSF. In real-world motion-blurred images, a simple parametric model of the PSF fails when a camera moves in an arbitrary direction with an inconsistent speed during an exposure time. Moreover, the PSF normally changes with spatial location. In order to accurately estimate the complex PSF of a real motion blurred image, we iteratively update the PSF by using a directional spreading operator. The directional spreading is applied to the PSF when it reduces the amount of the blur and the restoration artifacts. Then, to generalize the proposed technique to the linear shift variant (LSV) model, a piecewise invariant approach is adopted by the proposed image segmentation method. Experimental results show that the proposed method effectively estimates the PSF and restores the degraded images.