Search

Images captured under low-light conditions are characterized by lower visual quality and perception levels than images obtained in better lighting scenarios. Studies focused on low-light enhancement techniques seek to address this dilemma. However, simple image brightening results in significant noise, blurring, and color distortion. In this paper, we present a low-light enhancement (LLE) solution that effectively synergizes Retinex theory with deep learning. Specifically, we construct an efficient image gradient map estimation module based on convolutional networks that can efficiently generate noise-free image gradient maps to assist with denoising. Second, to improve upon the traditional optimization model, we design a matrix-preserving optimization method (MPOM) coupled with deep learning modules, and it exhibits high speed and low memory consumption. Third, we incorporate image structure, image texture, and implicit prior information to optimize the enhancement process for low-light conditions and overcome prevailing limitations, such as oversmoothing, significant noise, and so forth. Through extensive experiments, we show that our approach has notable advantages over the existing methods and demonstrate superiority and effectiveness, surpassing the state-of-the-art methods by an average of 1.23 dB in PSNR for the LOL and VE-LOL datasets. The code for the proposed method is available in a public repository for open-source use: https://github.com/luxunL/DRNet. [ABSTRACT FROM AUTHOR]

Credit card fraud identification is an important issue in risk prevention and control for banks and financial institutions. In order to establish an efficient credit card fraud identification model, this article studied the relevant factors that affect fraud identification. A credit card fraud identification model based on neural networks was constructed, and in-depth discussions and research were conducted. First, the layers of neural networks were deepened to improve the prediction accuracy of the model; second, this paper increase the hidden layer width of the neural network to improve the prediction accuracy of the model. This article proposes a new fusion neural network model by combining deep neural networks and wide neural networks, and applies the model to credit card fraud identification. The characteristic of this model is that the accuracy of prediction and F1 score are relatively high. Finally, use the random gradient descent method to train the model. On the test set, the proposed method has an accuracy of 96.44% and an F1 value of 96.17%, demonstrating good fraud recognition performance. After comparison, the method proposed in this paper is superior to machine learning models, ensemble learning models, and deep learning models. [ABSTRACT FROM AUTHOR]

Background: Owing to the lack of evidence-based medical studies with large sample sizes, the surgical approach for the radical resection of rectal neuroendocrine tumors remains controversial. Methods: We retrospectively collected the medical records of patients with rectal neuroendocrine tumors who underwent radical resection at 17 large tertiary care hospitals in China between January 1, 2010, and April 30, 2022. All patients were divided into laparoscopic and open surgery groups. After propensity score matching to reduce confounders, the postoperative and oncologic outcomes were compared between the groups. Results: We enrolled 174 patients with rectal neuroendocrine tumors who underwent radical surgery. After random matching, 124 patients were included in the comparison (62, laparoscopic surgery group; 62, open surgery group). The laparoscopic surgery group had fewer complications (14.5% vs. 35.5%, P = 0.007) and superior relapse-free survival (P = 0.048). Subgroup analysis revealed that the laparoscopic surgery group had fewer complications (10.9% vs. 34.7%, P = 0.004), shorter postoperative hospital stays (9.56 ± 5.21 days vs. 12.31 ± 8.61 days, P = 0.049) and superior relapse-free survival (P = 0.025) in the rectal neuroendocrine tumors ≤ 4 cm subgroup. Conclusions: Laparoscopic surgery was associated with improved postoperative outcomes and oncologic prognosis for patients with rectal neuroendocrine tumors ≤ 4 cm; it can serve as a safe and feasible option for radical surgery of rectal neuroendocrine tumors. [ABSTRACT FROM AUTHOR]

Compelling evidence has shown that geomagnetic disturbances in vertical intensity polarization before great earthquakes are promising precursors across diverse rupture conditions. However, the geomagnetic vertical intensity polarization method uses the spectrum of smooth signals, and the anomalous waveforms of seismic electromagnetic radiation, which are basically nonstationary, have not been adequately considered. By combining pulse amplitude analysis and an experimental study of the cumulative frequency of anomalies, we found that the pulse amplitudes before the 2022 Luding M6.8 earthquake show characteristics of multiple synchronous anomalies, with the highest (or higher) values occurring during the analyzed period. Similar synchronous anomalies were observed before the 2021 Yangbi M6.4 earthquake, the 2022 Lushan M6.1 earthquake and the 2022 Malcolm M6.0 earthquake, and these anomalies indicate migration from the periphery toward the epicenters over time. The synchronous changes are in line with the recognition of previous geomagnetic anomalies with characteristics of high values before an earthquake and gradual recovery after the earthquake. Our study suggests that the pulse amplitude is effective for extracting anomalies in geomagnetic vertical intensity polarization, especially in the presence of nonstationary signals when utilizing observations from multiple station arrays. Our findings highlight the importance of incorporating pulse amplitude analysis into earthquake prediction research on geomagnetic disturbances. [ABSTRACT FROM AUTHOR]

With the continuous advancement of the economy and technology, the number of cars continues to increase, and the traffic congestion problem on some key roads is becoming increasingly serious. This paper proposes a new vehicle information feature map (VIFM) method and a multi-branch convolutional neural network (MBCNN) model and applies it to the problem of traffic congestion detection based on camera image data. The aim of this study is to build a deep learning model with traffic images as input and congestion detection results as output. It aims to provide a new method for automatic detection of traffic congestion. The deep learning-based method in this article can effectively utilize the existing massive camera network in the transportation system without requiring too much investment in hardware. This study first uses an object detection model to identify vehicles in images. Then, a method for extracting a VIFM is proposed. Finally, a traffic congestion detection model based on MBCNN is constructed. This paper verifies the application effect of this method in the Chinese City Traffic Image Database (CCTRIB). Compared to other convolutional neural networks, other deep learning models, and baseline models, the method proposed in this paper yields superior results. The method in this article obtained an F1 score of 98.61% and an accuracy of 98.62%. Experimental results show that this method effectively solves the problem of traffic congestion detection and provides a powerful tool for traffic management. [ABSTRACT FROM AUTHOR]

Unbalanced data in intrusion detection seriously affect the overall performance of intrusion detection methods. This paper proposes an intrusion detection algorithm based on unbalanced learning (ID-UL) for unbalanced learning. It uses two strategies to address the issues brought about by unbalanced data. First, the data grouping strategy based on integrated learning alleviates the extreme data imbalance and avoids the negative impact on imbalanced learning. Meanwhile, to avoid the possible negative impact brought by unbalanced data on the learning procedures of convolutional neural networks, the strategy of assigning weight to the loss function is adopted. Besides, a method for determining the weight value is designed to make the model supervise the learning of attack samples during the training process. Experimental results on the NSL-KDD dataset show that the method in this paper can effectively improve the detection of attack classes, and the overall detection accuracy reaches 81.48%. ID-UL has the same significant effect on other imbalanced datasets. [ABSTRACT FROM AUTHOR]

In this paper, we construct a deep framework for full-reference image quality assessment (FR-IQA) by combining convolution and self-attention features; this approach effectively uses multiscale features to mimic the image evaluation in human eyes. We achieve the integration of information from local to global. First, convolutional neural network (CNN) and encoder of Swin transformer are used to extract multiscale paired features. Second, for each type of features, we fuse them after converting them to a fixed number of channels. For the fused features, we use the square of the difference between two pixel values at the corresponding channel positions to represent the features of the distortion degree. Then, we introduce a recurrent neural network (RNN) to capture the global features. Finally, for the two types of features, we use the full connection (FC) layer to regress two scores and then add the weights to compute the ultimate perceived score. By training and testing on publicly available FR-IQA datasets, experimental results further validate the superiority of our approach. [ABSTRACT FROM AUTHOR]

CD8+ T cells play an important role in anti-tumor immunity. Better understanding of their regulation could advance cancer immunotherapies. Here we identify, via stepwise CRISPR-based screening, that CUL5 is a negative regulator of the core signaling pathways of CD8+ T cells. Knocking out CUL5 in mouse CD8+ T cells significantly improves their tumor growth inhibiting ability, with significant proteomic alterations that broadly enhance TCR and cytokine signaling and their effector functions. Chemical inhibition of neddylation required by CUL5 activation, also enhances CD8 effector activities with CUL5 validated as a major target. Mechanistically, CUL5, which is upregulated by TCR stimulation, interacts with the SOCS-box-containing protein PCMTD2 and inhibits TCR and IL2 signaling. Additionally, CTLA4 is markedly upregulated by CUL5 knockout, and its inactivation further enhances the anti-tumor effect of CUL5 KO. These results together reveal a negative regulatory mechanism for CD8+ T cells and have strong translational implications in cancer immunotherapy. CD8 + T cells are central players in anti-tumour immunity. Here authors identify Cul5, a ubiquitin E3 ligase as an important inhibitor of CD8 + T cell anti-tumour cytotoxicity and persistence via involvement with both T cell receptor and cytokine-regulated central pathways. [ABSTRACT FROM AUTHOR]

Current treatments for T cell malignancies encounter issues of disease relapse and off-target toxicity. Using T cell receptor (TCR)Vβ2 as a model, here we demonstrate the rapid generation of an off-the-shelf allogeneic chimeric antigen receptor (CAR)-T platform targeting the clone-specific TCR Vβ chain for malignant T cell killing while limiting normal cell destruction. Healthy donor T cells undergo CRISPR-induced TRAC, B2M and CIITA knockout to eliminate T cell-dependent graft-versus-host and host-versus-graft reactivity. Second generation 4-1BB/CD3zeta CAR containing high affinity humanized anti-Vβ scFv is expressed efficiently on donor T cells via both lentivirus and adeno-associated virus transduction with limited detectable pre-existing immunoreactivity. Our optimized CAR-T cells demonstrate specific and persistent killing of Vβ2+ Jurkat cells and Vβ2+ patient derived malignant T cells, in vitro and in vivo, without affecting normal T cells. In parallel, we generate humanized anti-Vβ2 antibody with enhanced antibody-dependent cellular cytotoxicity (ADCC) by Fc-engineering for NK cell ADCC therapy. Clonal Vb2 usage is common among patients with mature T cell lymphoma. Here the authors report the generation of allogeneic CAR-T cells selectively targeting TCR Vb2+ on malignant T cells, with limited normal T cell destruction. [ABSTRACT FROM AUTHOR]

Cadmium (Cd) is a nonessential element in plants and has adverse effects on the growth and development of plants. However, the molecular mechanisms of Cd phytotoxicity, tolerance and accumulation in hyperaccumulators Solanum nigrum L. has not been well understood. Here, physiology, transcriptome, and metabolome analyses were conducted to investigate the influence on the S. nigrum under 0, 25, 50, 75 and 100 µM Cd concentrations for 7 days. Pot experiments demonstrated that compared with the control, Cd treatment significantly inhibited the biomass, promoted the Cd accumulation and translocation, and disturbed the balance of mineral nutrient metabolism in S. nigrum, particularly at 100 µM Cd level. Moreover, the photosynthetic pigments contents were severely decreased, while the content of total protein, proline, malondialdehyde (MDA), H 2 O 2 , and antioxidant enzyme activities generally increased first and then slightly declined with increasing Cd concentrations, in both leaves and roots. Furthermore, combined with the previous transcriptomic data, numerous crucial coding-genes related to mineral nutrients and Cd ion transport, and the antioxidant enzymes biosynthesis were identified, and their expression pattern was regulated under different Cd stress. Simultaneously, metabolomic analyses revealed that Cd treatment significantly changed the expression level of many metabolites related to amino acid, lipid, carbohydrate, and nucleotide metabolism. Metabolic pathway analysis also showed that S. nigrum roots activated some differentially expressed metabolites (DEMs) involved in energy metabolism, which may enhance the energy supply for detoxification. Importantly, central common metabolism pathways of DEGs and DEMs, including the "TCA cycle", "glutathione metabolic pathway" and "glyoxylate and dicarboxylate metabolism" were screened using conjoint transcriptomics and metabolomics analysis. Our results provide some novel evidences on the physiological and molecular mechanisms of Cd tolerance in hyperaccumulator S. nigrum plants., (© 2024. The Author(s).)

CD8 + T cells play an important role in anti-tumor immunity. Better understanding of their regulation could advance cancer immunotherapies. Here we identify, via stepwise CRISPR-based screening, that CUL5 is a negative regulator of the core signaling pathways of CD8 + T cells. Knocking out CUL5 in mouse CD8 + T cells significantly improves their tumor growth inhibiting ability, with significant proteomic alterations that broadly enhance TCR and cytokine signaling and their effector functions. Chemical inhibition of neddylation required by CUL5 activation, also enhances CD8 effector activities with CUL5 validated as a major target. Mechanistically, CUL5, which is upregulated by TCR stimulation, interacts with the SOCS-box-containing protein PCMTD2 and inhibits TCR and IL2 signaling. Additionally, CTLA4 is markedly upregulated by CUL5 knockout, and its inactivation further enhances the anti-tumor effect of CUL5 KO. These results together reveal a negative regulatory mechanism for CD8 + T cells and have strong translational implications in cancer immunotherapy., (© 2024. The Author(s).)

Monocytes play important and diverse roles in both homeostatic and inflammatory immune responses. The CRISPR-Cas9 system in lentiviral vectors has been widely used to manipulate specific genes of immortal monocyte cell lines to study monocyte functions. However, human primary monocytes are refractory to this method with low gene knockout (KO) efficiency. In this chapter, we developed an in vitro gene-editing procedure for primary human monocytes with a consistent and high-gene KO efficiency via a ribonucleoprotein (RNP) complex consisting of Cas9 protein and single-guide RNA (sgRNA). This method can be adapted to study the functions of targeted signaling molecules involved in modulating monocyte polarization in primary human monocytes., (© 2024. The Author(s), under exclusive license to Springer Science+Business Media, LLC, part of Springer Nature.)