Search

Abstract Many tomb murals have punctate losses, cracks, and craquelure due to underground subsidence and changes in their physical support. Visual non-destructive detection techniques enable rapid assessment of how much tomb murals are affected by cracking, providing suggestions for their conservation. However, tomb murals are typically created by sketching outlines and then colored. Detailed sketches can easily interfere with crack detection work, requiring the use of deep learning network to better learn crack features and improve detection accuracy. At the same time the limited data of tomb mural presents a challenge to build a deep learning network. To address these issues, this paper introduces a novel dual-attention detection network (DADNet) for crack segmentation of tomb murals. In this work, a customized dataset is first constructed by collecting mural images from the Tang Dynasty tombs. Then the ConvNeXt framework serves as the basis for feature extraction, enhancing the process. Lastly, a dual-attention module utilizing neighborhood attention and biaxial attention is employed to accurately identify the crack regions. Neighborhood attention performs a local self-attention operation around the pixel point, addressing the limitations of self-attention. This approach significantly reduces computational demands as the image size increases. Biaxial attention performs attention calculations in the horizontal and vertical directions. This compensates for the limitation of neighborhood attention in capturing global dependencies. Our DADNet outperformed the competing methods, achieving the highest recorded scores of 78.95% for MIoU and 61.05% for the Jaccard index.

Abstract Ancient murals embody profound historical, cultural, scientific, and artistic values, yet many are afflicted with challenges such as pigment shedding or missing parts. While deep learning-based completion techniques have yielded remarkable results in restoring natural images, their application to damaged murals has been unsatisfactory due to data shifts and limited modeling efficacy. This paper proposes a novel progressive reasoning network designed specifically for mural image completion, inspired by the mural painting process. The proposed network comprises three key modules: a luminance reasoning module, a sketch reasoning module, and a color fusion module. The first two modules are based on the double-codec framework, designed to infer missing areas’ luminance and sketch information. The final module then utilizes a paired-associate learning approach to reconstruct the color image. This network utilizes two parallel, complementary pathways to estimate the luminance and sketch maps of a damaged mural. Subsequently, these two maps are combined to synthesize a complete color image. Experimental results indicate that the proposed network excels in restoring clearer structures and more vivid colors, surpassing current state-of-the-art methods in both quantitative and qualitative assessments for repairing damaged images. Our code and results will be publicly accessible at https://github.com/albestobe/PRN .

Abstract Objective The prognosis for patients presenting with a large ischemic core (LIC) following endovascular thrombectomy is relatively poor. This study aimed to construct and validate a nomogram for predicting 3‐month unfavorable outcome in patients with anterior circulation occlusion‐related LIC who underwent endovascular thrombectomy. Methods A retrospective training cohort and a prospective validation cohort of patients with a large ischemic core were studied. The diffusion weighted imaging related radiomic features and pre‐thrombectomy clinical features were collected. After the selection of relevant features, a nomogram predicting modified Rankin Scale score of 3–6 as an unfavorable outcome was established. The discriminatory value of the nomogram was evaluated with a receiver operating characteristic curve. Results A total of 140 patients (mean age 66.3 ± 13.4 years, 35% female) were included in this study, consisting of a training cohort (n = 95) and a validation cohort (n = 45). The percentage of patients with an mRS scores of 0–2 was 30%, 0–3 was 40.7%, and 32.9% were dead. Age, National Institute of Health Stroke Scale (NIHSS) score, and two radiomic features, Maximum2DDiameterColumn and Maximum2DDiameterSlice, were identified as factors associated with unfavorable outcome in the nomogram. The nomogram demonstrated an area under the curve of 0.892 (95% confidence interval [CI], 0.812–0.947) in the training dataset and 0.872 (95% CI, 0.739–0.953) in the validation dataset. Interpretation This nomogram, which includes age, NIHSS score, Maximum2DDiameterColumn, and Maximum2DDiameterSlice, may predict the risk of unfavorable outcome in patients with LIC caused by anterior circulation occlusion.

Pan-sharpening is a significant task in remote sensing image processing, which merges a high-resolution panchromatic (PAN) image and a low-resolution multispectral (MS) image to create a high-resolution MS image. In this article, we propose a novel deep-learning-based MS image pan-sharpening method that combines a shallow-deep convolutional network (SDCN) and a spectral discrimination-based detail injection (SDDI) model. SDCN consists of a shallow network and a deep network, which can capture mid-level and high-level spatial features from PAN images. SDDI, inspired by the “Amélioration de la Résolution Spatial par Injection de Structures” concept, is developed to merge the spatial details extracted by SDCN into MS images with minimal spectral distortion. SDCN and SDDI are collaboratively learned for achieving high-spatial-resolution MS image and preserving more spectral information. Both the visual assessment and the quantitative assessment results on IKONOS and QuickBird datasets confirmed that the proposed method outperforms several state-of-the-art pan-sharpening methods.

Abstract Background Crucian carp is a popular ornamental strain in Asia with variants in body color. To further explore the genetic mechanisms underlying gray and red body color formation in crucian carp, the skin transcriptomes and partial DNA methylation sites were obtained from red crucian carp (RCC) and white crucian carp (WCC). Here, we show significant differences in mRNA expression and DNA methylation sites between skin tissues of RCC and WCC. Results Totals of 3434 and 3683 unigenes had significantly lower and higher expression in WCC, respectively, compared with unigenes expressed in RCC. Some potential genes for body color development were further identified by quantitative polymerase chain reaction, such as mitfa, tyr, tyrp1, and dct, which were down-regulated, and foxd3, hpda, ptps, and gch1, which were up-regulated. A KEGG pathway analysis indicated that the differentially expressed genes were mainly related to mitogen activated protein kinase (MAPK), Wnt, cell cycle, and endocytosis signaling pathways, as well as variations in melanogenesis in crucian carp. In addition, some differentially expressed DNA methylation site genes were related to pigmentation, including mitfa, tyr, dct, foxd3, and hpda. The differentially expressed DNA methylation sites were mainly involved in signaling pathways, including MAPK, cAMP, endocytosis, melanogenesis, and Hippo. Conclusions Our study provides the results of comparative transcriptome and DNA methylation analyses between RCC and WCC skin tissues and reveals that the molecular mechanism of body color variation in crucian carp is strongly related to disruptions in gene expression and DNA methylation during pigmentation.

Food intake induces synthesis of N-acylphosphatidylethanolamines (NAPEs) in the intestinal tract. While NAPEs exert leptin-like (leptogenic) effects, including reduced weight gain and food intake, the mechanisms by which NAPEs induce these leptogenic effects remain unclear. One key question is whether intestinal NAPEs act directly on cognate receptors or first require conversion to N-acylethanolamides (NAEs) by NAPE-hydrolyzing phospholipase D (NAPE-PLD). Previous studies using Nape-pld−/− mice were equivocal because intraperitoneal injection of NAPEs led to nonspecific aversive effects. To avoid the aversive effects of injection, we delivered NAPEs and NAEs intestinally using gut bacteria synthesizing these compounds. Unlike in wild-type mice, increasing intestinal levels of NAPE using NAPE-synthesizing bacteria in Nape-pld−/− mice failed to reduce food intake and weight gain or alter gene expression. In contrast, increasing intestinal NAE levels in Nape-pld−/− mice using NAE-synthesizing bacteria induced all of these effects. These NAE-synthesizing bacteria also markedly increased NAE levels and decreased inflammatory gene expression in omental adipose tissue. These results demonstrate that intestinal NAPEs require conversion to NAEs by the action of NAPE-PLD to exert their various leptogenic effects, so that the reduced intestinal NAPE-PLD activity found in obese subjects may directly contribute to excess food intake and obesity.

The mechanisms driving lung inflammation and remodelling in chronic obstructive pulmonary disease (COPD) are incompletely understood. Here the authors show that lack of secretory IgA promotes bacterial invasion in small airways, resulting in leukocyte recruitment and a COPD-like phenotype.

To solve the problem of low efficiency and colour distortion in several typical tone mapping operators for high dynamic range (HDR) images, the authors propose a novel tone mapping algorithm based on fast image decomposition and multi‐layer fusion. An input HDR image is firstly decomposed into a base layer and a detail layer by an improved guided filtering method. For the base layer, its dynamic range is compressed by the simulated camera response function. For the detail layer, it is enhanced to produce more fine structures and reduce halo effect by applying the guided image filter. The colour balance correction method is adopted to suppress colour distortion. The experiments on HDR images demonstrate that the proposed technique could bring better brightness, contrast, and visibility with less halo effect than other state‐of‐the‐art methods both qualitatively and quantitatively in most cases.

To solve the problem of low efficiency and poor effect of the current tone mapping methods for the high dynamic range images, the authors propose a hierarchical tone mapping algorithm based on colour appearance model. The discrete Gaussian kernel is used to speed up the bilateral filter. The operation of tone compression in RGB colour space is adopted to correct the colour casts. The extreme values of the pixels are also adjusted in the detail layer. Moreover, after the tone mapping, the colour saturation is enhanced in the image regions of rich details and sharp edges. Experimental results show that the proposed algorithm with less computational cost reduces the halo effect significantly, and achieves the natural colour and the rich details. It outperforms the state‐of‐the‐art methods in terms of visual quality and objective indicators.

Based on the research method of combining simulation analysis with field testing by distinct element process UDEC, we have analyzed the roof deformation and failure laws and roadway support technology of gob-side entry retaining in a thin seam with a large inclined angle. The results show that during exploitation in seams with large inclined angle, rotational subsidence of the main roof under the gob area is small and can maintain balance, so there is no need to provide artificial permanent support resistance for the main roof near the upper side to control rotational subsidence. Obstructed by the dense scrap rail, waste rock from the immediate roof caving slides from the upper gob area to the lower area and fills it, which strikes a balance between the immediate roof under the goaf after it fractures into large pieces and filling waste rocks. Keywords: Large inclined angle, Gob-side entry retaining, Spontaneous caving, Thin seam, Field test

Leaf chlorophyll content plays a vital role in plant photosynthesis. The PROSPECT model has been widely used for retrieving leaf chlorophyll content from remote sensing data over various plant species. However, despite wide variations in leaf surface reflectance across different plant species and environmental conditions, leaf surface reflectance is assumed to be the same for different leaves in the PROSPECT model. This work extends the PROSPECT model by taking into account the variation of leaf surface reflection. In the modified model named PROSPECT-Rsurf, an additional surface layer with a variable refractive index is bounded on the N elementary layers. Leaf surface reflectance (Rs) is characterized by the difference between the refractive indices of leaf surface and interior layers. The specific absorption coefficients of the leaf total chlorophyll and carotenoids were recalibrated using a cross-calibration method and the refractive indices of leaf surface and interior layers were obtained during model inversion. Chlorophyll content (Cab) retrieval and spectral reconstruction in the visible spectral region (VIS, 400−750 nm) were greatly improved using PROSPECT-Rsurf, especially for leaves covered by heavy wax or hard cuticles that lead to high surface reflectance. The root mean square error (RMSE) of chlorophyll estimates decreased from 11.1 µg/cm2 to 8.9 µg/cm2 and the Pearson’s correlation coefficient (r) increased from 0.81 to 0.88 (p < 0.01) for broadleaf samples in validation, compared to PROSPECT-5. For needle leaves, r increased from 0.71 to 0.89 (p < 0.01), but systematic overestimation of Cab was found due to the edge effects of needles. After incorporating the edge effects in PROSPECT-Rsurf, the overestimation of Cab was alleviated and its estimation was improved for needle leaves. This study explores the influence of leaf surface reflectance on Cab estimation at the leaf level. By coupling PROSPECT-Rsurf with canopy models, the influence of leaf surface reflectance on canopy reflectance and therefore canopy chlorophyll content retrieval can be investigated across different spatial and temporal scales.

Lipid aldehydes including isolevuglandins (IsoLGs) and 4-hydroxynonenal modify phosphatidylethanolamine (PE) to form proinflammatory and cytotoxic adducts. Therefore, cells may have evolved mechanisms to degrade and prevent accumulation of these potentially harmful compounds. To test if cells could degrade isolevuglandin-modified phosphatidylethanolamine (IsoLG-PE), we generated IsoLG-PE in human embryonic kidney 293 (HEK293) cells and human umbilical cord endothelial cells and measured its stability over time. We found that IsoLG-PE levels decreased more than 75% after 6 h, suggesting that IsoLG-PE was indeed degraded. Because N-acyl phosphatidylethanolamine-hydrolyzing phospholipase D (NAPE-PLD) has been described as a key enzyme in the hydrolysis of N-acyl phosphatidylethanoamine (NAPE) and both NAPE and IsoLG-PE have large aliphatic headgroups, we considered the possibility that this enzyme might also hydrolyze IsoLG-PE. We found that knockdown of NAPE-PLD expression using small interfering RNA (siRNA) significantly increased the persistence of IsoLG-PE in HEK293 cells. IsoLG-PE competed with NAPE for hydrolysis by recombinant mouse NAPE-PLD, with the catalytic efficiency (Vmax/Km) for hydrolysis of IsoLG-PE being 30% of that for hydrolysis of NAPE. LC-MS/MS analysis confirmed that recombinant NAPE-PLD hydrolyzed IsoLG-PE to IsoLG-ethanolamine. These results demonstrate that NAPE-PLD contributes to the degradation of IsoLG-PE and suggest that a major physiological role of NAPE-PLD may be to degrade aldehyde-modified PE, thereby preventing the accumulation of these harmful compounds.