Cuproptosis-related DNA methylation signature predict prognosis and immune microenvironment in cutaneous melanoma.

The prognosis for Cutaneous Melanoma (CM), a skin malignant tumor that is extremely aggressive, is not good. A recently identified type of controlled cell death that is intimately related to immunotherapy and the development of cancer is called cuproptosis. Using The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) database, we developed and validated a DNA-methylation located in cuproptosis death-related gene prognostic signature (CRG-located DNA-methylation prognostic signature) to predict CM's prognosis. Kaplan-Meier analysis of our TCGA and GEO cohorts showed that high-risk patients had a shorter overall survival. The area under the curve (AUC) for the TCGA cohort was 0.742, while for the GEO cohort it was 0.733, according to the receiver operating characteristic (ROC) analysis. Furthermore, this signature was discovered as an independent prognostic indicator over CM patients based on Cox-regression analysis. Immunogenomic profiling indicated that majority immune-checkpoints got an opposite relationship with the signature, and patients in the group at low risk got higher immunophenoscore. Several immune pathways were enriched, according to functional enrichment analysis. In conclusion, a prognostic methylation signature for CM patients was established and confirmed. Because of its close relationship to the immune landscape, this signature may help clinicians make more accurate and individualized choices regarding therapy.

SOSNet: Real-Time Small Object Segmentation via Hierarchical Decoding and Example Mining.

Real-time semantic segmentation plays an important role in auto vehicles. However, most real-time small object segmentation methods fail to obtain satisfactory performance on small objects, such as cars and sign symbols, since the large objects usually tend to devote more to the segmentation result. To solve this issue, we propose an efficient and effective architecture, termed small objects segmentation network (SOSNet), to improve the segmentation performance of small objects. The SOSNet works from two perspectives: methodology and data. Specifically, with the former, we propose a dual-branch hierarchical decoder (DBHD) which is viewed as a small-object sensitive segmentation head. The DBHD consists of a top segmentation head that predicts whether the pixels belong to a small object class and a bottom one that estimates the pixel class. In this situation, the latent correlation among small objects can be fully explored. With the latter, we propose a small object example mining (SOEM) algorithm for balancing examples between small objects and large objects automatically. The core idea of the proposed SOEM is that most of the hard examples on small-object classes are reserved for training while most of the easy examples on large-object classes are banned. Experiments on three commonly used datasets show that the proposed SOSNet architecture greatly improves the accuracy compared to the existing real-time semantic segmentation methods while keeping efficiency. The code will be available at https://github.com/StuLiu/SOSNet.

Pixel-Centric Context Perception Network for Camouflaged Object Detection.

Camouflaged object detection (COD) aims to identify object pixels visually embedded in the background environment. Existing deep learning methods fail to utilize the context information around different pixels adequately and efficiently. In order to solve this problem, a novel pixel-centric context perception network (PCPNet) is proposed, the core of which is to customize the personalized context of each pixel based on the automatic estimation of its surroundings. Specifically, PCPNet first employs an elegant encoder equipped with the designed vital component generation (VCG) module to obtain a set of compact features rich in low-level spatial and high-level semantic information across multiple subspaces. Then, we present a parameter-free pixel importance estimation (PIE) function based on multiwindow information fusion. Object pixels with complex backgrounds will be assigned with higher PIE values. Subsequently, PIE is utilized to regularize the optimization loss. In this way, the network can pay more attention to those pixels with higher PIE values in the decoding stage. Finally, a local continuity refinement module (LCRM) is used to refine the detection results. Extensive experiments on four COD benchmarks, five salient object detection (SOD) benchmarks, and five polyp segmentation benchmarks demonstrate the superiority of PCPNet with respect to other state-of-the-art methods.

FSNet: Focus Scanning Network for Camouflaged Object Detection.

Camouflaged object detection (COD) aims to discover objects that blend in with the background due to similar colors or textures, etc. Existing deep learning methods do not systematically illustrate the key tasks in COD, which seriously hinders the improvement of its performance. In this paper, we introduce the concept of focus areas that represent some regions containing discernable colors or textures, and develop a two-stage focus scanning network for camouflaged object detection. Specifically, a novel encoder-decoder module is first designed to determine a region where the focus areas may appear. In this process, a multi-layer Swin transformer is deployed to encode global context information between the object and the background, and a novel cross-connection decoder is proposed to fuse cross-layer textures or semantics. Then, we utilize the multi-scale dilated convolution to obtain discriminative features with different scales in focus areas. Meanwhile, the dynamic difficulty aware loss is designed to guide the network paying more attention to structural details. Extensive experimental results on the benchmarks, including CAMO, CHAMELEON, COD10K, and NC4K, illustrate that the proposed method performs favorably against other state-of-the-art methods.

Feature Consistency-Based Prototype Network for Open-Set Hyperspectral Image Classification.

Hyperspectral image (HSI) classification methods have made great progress in recent years. However, most of these methods are rooted in the closed-set assumption that the class distribution in the training and testing stages is consistent, which cannot handle the unknown class in open-world scenes. In this work, we propose a feature consistency-based prototype network (FCPN) for open-set HSI classification, which is composed of three steps. First, a three-layer convolutional network is designed to extract the discriminative features, where a contrastive clustering module is introduced to enhance the discrimination. Then, the extracted features are used to construct a scalable prototype set. Finally, a prototype-guided open-set module (POSM) is proposed to identify the known samples and unknown samples. Extensive experiments reveal that our method achieves remarkable classification performance over other state-of-the-art classification techniques.

Insight into atrazine removal by fallen leaf biochar prepared at different pyrolysis temperatures: Batch experiments, column adsorption and DFT calculations.

The environmental pollution caused by atrazine in the agricultural production cannot be ignored. In this study, the fallen leaf biochar (LBC) was prepared at three different temperatures (500 °C, 600 °C, and 700 °C) using a simple pyrolysis method (500 LBC, 600 LBC, and 700 LBC) for atrazine adsorption. Batch experiments showed that the performance of LBC in atrazine adsorption improved with rising pyrolysis temperature, and the highest adsorption amount of 700 LBC reached 84.32 mg g-1. Kinetic and isotherm models showed that the adsorption behaviors were both monolayer and multilayer chemisorption. The findings of the characterizations (Elemental analysis, BET, XRD, Raman, FT-IR, and XPS) confirmed that the degree of aromatization determined the adsorption capacity of LBC to atrazine, and π-π electron donor-acceptor interaction was the main adsorption mechanism. Density functional theory (DFT) calculations showed that the highly aromatized biochar was more effective for atrazine adsorption, manifested as smaller molecular distances, higher adsorption energies, more stable complex structures, and stronger π-electron conjugation. In the column adsorption experiments, reducing the inlet flow rate or increasing the bed height extended the breakthrough time and exhaustion time of the breakthrough curves, and 700 LBC still showed good adsorption performance after five cycles. Overall, fallen leaf biochar as a reuse product of resource showed good potential for application in atrazine adsorption, which can be used for atrazine-contaminated water remediation.

Study on the performance of sewage sludge biochar modified by nZVI to remove Cu(II) and Cr(VI) in water.

In this study, to simultaneously dispose of sludge and wastewater containing heavy metals, sludge biochar loaded with nano zero-valent-iron (nZVI) was prepared at 700 °C (nBC700) to remove Cr(VI) and Cu(II). The results showed the removal capacity of biochar was greatly improved by loading nZVI, and the adsorption capacities of biochar for Cu(II) and Cr(VI) increased by 251.96% and 205.18%. Pseudo-second-order kinetic and Sips isotherm models were fitted to the removal processes. Intraparticle diffusion models showed the removal process was controlled by surface diffusion and intraparticle diffusion. Competitive experiments showed Cr(VI) can compete with Cu(II) for active sites, but Cr(VI) was more easily removed by nBC700 through cation bridge. The removal mechanism illustrated removing Cu(II) mainly depended on complex precipitation, followed by reduction reaction, while Cr(VI) was on the contrary. This work provided effective data for sludge disposal and heavy metal removal.

Performance and mechanism of tea waste biochar in enhancing the removal of tetracycline by peroxodisulfate.

In this work, tea waste biochar was prepared and used to activate peroxodisulfate (PDS) for the removal of tetracycline (TC) efficiently. And SEM, XRD, Raman, and FTIR were used to characterize the biochar. The effects of reaction conditions including initial pH, biochar dosage, and PDS concentration on the removal of TC were explored, and the result showed that compared with the biochar prepared at 400 °C and 500 °C, the biochar pyrolyzed at 600 °C (TBC600) had the highest TC removal performance due to its higher sp2 hybrid carbon content, richer defective structure, and stronger electron deliverability. Under the optimal dosage of PDS (4 mM) and TBC600 (0.8 g L-1), the removal efficiency of TC (10 mg L-1) reached 81.65%. After four cycles of TBC600, the removal rate could still reach 75.51%, indicating that TBC600 has excellent stability. In addition, quenching experiments and electron paramagnetic resonance (EPR) verified that the active oxygen including SO4·-, ·OH, O2·-, and singlet oxygen (1O2) was involved, among which 1O2 and OH were the main active substance in the TC removal. Therefore, this work provided a green and efficient persulfate activator and a method for recycling tea waste.

Enhancing degradation of atrazine by Fe-phenol modified biochar/ferrate(VI) under alkaline conditions: Analysis of the mechanism and intermediate products.

In this study, Fe-phenol modified biochar was prepared to enhance atrazine (AT) degradation by ferrate (Fe(VI)) under alkaline conditions, and the properties, mechanism and transformation pathways were extensively investigated. Degradation experiments showed that Fe-phenol modified biochar was more beneficial for improving the oxidation capacity of Fe(VI) than unmodified biochar, and the biochar with a molar ratio of Fe3+ to phenol of 0.1:5 (BC-2) showed the best promoting effect, and more than 94% of AT was removed at pH = 8 within 30 min. Moreover, the rate of oxidation (kapp) of AT by Fe(VI) increased 1.86 to 4.11 times by the addition of BC-2 in the studied pH range. Fe(Ⅴ)/Fe(Ⅳ) and ·OH were the main active oxidizing species for AT degradation in the Fe(VI)/BC-2 group and contributed to 70% and 24%, respectively, of degradation. The formation of ·OH and Fe(Ⅴ)/Fe(Ⅳ) was mainly due to the persistent free radicals and reducing groups on the surface of BC-2. AT was oxidized to 12 intermediate products in the Fe(VI)/BC-2 group through 5 pathways: alkyl hydroxylation, dealkylation, dichlorination, hydroxylation, alkyl dehydrogenation and dichlorination. Compared with those of the initial solution, the total organic carbon content and toxicity after the reaction decreased by 32.8% and 19.02%, respectively. Therefore, the combination of Fe-phenol modified biochar and Fe(VI) could be a promising method for AT removal.

Regularizing Hyperspectral and Multispectral Image Fusion by CNN Denoiser.

Hyperspectral image (HSI) and multispectral image (MSI) fusion, which fuses a low-spatial-resolution HSI (LR-HSI) with a higher resolution multispectral image (MSI), has become a common scheme to obtain high-resolution HSI (HR-HSI). This article presents a novel HSI and MSI fusion method (called as CNN-Fus), which is based on the subspace representation and convolutional neural network (CNN) denoiser, i.e., a well-trained CNN for gray image denoising. Our method only needs to train the CNN on the more accessible gray images and can be directly used for any HSI and MSI data sets without retraining. First, to exploit the high correlations among the spectral bands, we approximate the desired HR-HSI with the low-dimensional subspace multiplied by the coefficients, which can not only speed up the algorithm but also lead to more accurate recovery. Since the spectral information mainly exists in the LR-HSI, we learn the subspace from it via singular value decomposition. Due to the powerful learning performance and high speed of CNN, we use the well-trained CNN for gray image denoising to regularize the estimation of coefficients. Specifically, we plug the CNN denoiser into the alternating direction method of multipliers (ADMM) algorithm to estimate the coefficients. Experiments demonstrate that our method has superior performance over the state-of-the-art fusion methods.

3-D Adaptive Sparsity Based Image Compression With Applications to Optical Coherence Tomography.

We present a novel general-purpose compression method for tomographic images, termed 3D adaptive sparse representation based compression (3D-ASRC). In this paper, we focus on applications of 3D-ASRC for the compression of ophthalmic 3D optical coherence tomography (OCT) images. The 3D-ASRC algorithm exploits correlations among adjacent OCT images to improve compression performance, yet is sensitive to preserving their differences. Due to the inherent denoising mechanism of the sparsity based 3D-ASRC, the quality of the compressed images are often better than the raw images they are based on. Experiments on clinical-grade retinal OCT images demonstrate the superiority of the proposed 3D-ASRC over other well-known compression methods.

Image fusion with guided filtering.

A fast and effective image fusion method is proposed for creating a highly informative fused image through merging multiple images. The proposed method is based on a two-scale decomposition of an image into a base layer containing large scale variations in intensity, and a detail layer capturing small scale details. A novel guided filtering-based weighted average technique is proposed to make full use of spatial consistency for fusion of the base and detail layers. Experimental results demonstrate that the proposed method can obtain state-of-the-art performance for fusion of multispectral, multifocus, multimodal, and multiexposure images.