The Inhibitory Effects of Propofol on Colorectal Cancer Progression through the NF-κB/HIF-1α Signaling Pathway.

BACKGROUND AND OBJECTIVE: Colorectal cancer (CRC) is a neoplastic disease that gradually develops due to genetic variations and epigenetic changes. Surgical excision is the first-line treatment for CRC. Accumulating evidence has shown that total intravenous anesthesia has beneficial effects for CRC patients as it decreases the probability of tumor recurrence and metastasis. Propofol is one of the most frequently used intravenous anesthetics in clinical practice. However, it remains unknown whether it can reduce recurrence and metastasis after surgery in cancer patients. METHODS: CRC cell lines (HCT116 and SW480) were cultured in vitro, and different concentrations of propofol were added to the cell culture medium. The proliferation effect of propofol on CRC cell lines was evaluated by CCK-8 assay. The effect of propofol on the migration and invasion of CRC cells was evaluated by scratch healing and Transwell experiments. The inhibitory effects of propofol on NF-κB and HIF-1α expressions in CRC cell lines were determined by Western blotting and immunofluorescence assays to further clarify the regulatory effects of propofol on NF-κB and HIF-1α. RESULTS: Compared to the control, propofol significantly inhibited the proliferation, migration, and invasion abilities of CRC cells (HCT116 and SW480) (P < 0.0001). The expression levels of NF-κB and HIF-1α gradually decreased with increasing propofol concentration in both cell lines. After activation and inhibition of NF-κB, the expression of HIF-1α changed. Further studies showed that propofol inhibited LPS-activated NF-κB-induced expression of HIF-1α, similar to the NF-κB inhibitor Bay17083 (P < 0.0001). CONCLUSION: In vitro, propofol inhibited the proliferation, migration, and invasion of CRC cells (HCT116 and SW480) in a dose-dependent manner, possibly by participating in the regulation of the NF-κB/HIF-1α signaling pathway.

Cytoprotective Metal-Phenolic Network Sporulation to Modulate Microalgal Mobility and Division.

Synthetic cell exoskeletons created from abiotic materials have attracted interest in materials science and biotechnology, as they can regulate cell behavior and create new functionalities. Here, a facile strategy is reported to mimic microalgal sporulation with on-demand germination and locomotion via responsive metal-phenolic networks (MPNs). Specifically, MPNs with tunable thickness and composition are deposited on the surface of microalgae cells via one-step coordination, without any loss of cell viability or intrinsic cell photosynthetic properties. The MPN coating keeps the cells in a dormant state, but can be disassembled on-demand in response to environmental pH or chemical stimulus, thereby reviving the microalgae within 1 min. Moreover, the artificial sporulation of microalgae resulted in resistance to environmental stresses (e.g., metal ions and antibiotics) akin to the function of natural sporulation. This strategy can regulate the life cycle of complex cells, providing a synthetic strategy for designing hybrid microorganisms.

Optimization of Heterotrophic Culture Conditions for the Microalgae Euglena gracilis to Produce Proteins.

Euglena gracilis is one of the few permitted edible microalgae. Considering consumer acceptance, E. gracilis grown heterotrophically with yellow appearances have wider food industrial applications such as producing meat analogs than green cells. However, there is much room to improve the protein content of heterotrophic culture cells. In this study, the effects of nitrogen sources, temperature, initial pH, and C/N ratios on the protein production of E. gracilis were evaluated under heterotrophic cultivation. These results indicated that ammonium sulfate was the optimal nitrogen source for protein production. The protein content of E. gracilis cultured by ammonium sulfate increased by 113% and 44.7% compared with that cultured by yeast extract and monosodium glutamate, respectively. The manipulation of the low C/N ratio further improved E. gracilis protein content to 66.10% (w/w), which was 1.6-fold of that in the C/N = 25 group. Additionally, amino acid analysis revealed that the nitrogen-to-protein conversion factor (NTP) could be affected by nitrogen sources. A superior essential amino acid index (EAAI) of 1.62 and a balanced amino acid profile further confirmed the high nutritional value of E. gracilis protein fed by ammonium sulfate. This study highlighted the vast potency of heterotrophic cultured E. gracilis as an alternative dietary protein source.

Block-Wise Partner Learning for Model Compression.

Despite the great potential of convolutional neural networks (CNNs) in various tasks, the resource-hungry nature greatly hinders their wide deployment in cost-sensitive and low-powered scenarios, especially applications in remote sensing. Existing model pruning approaches, implemented by a "subtraction" operation, impose a performance ceiling on the slimmed model. Self-knowledge distillation (Self-KD) resorts to auxiliary networks that are only active in the training phase for performance improvement. However, the knowledge is holistic and crude, and the learning-based knowledge transfer is mediate and lossy. Here, we propose a novel model-compression method, termed block-wise partner learning (BPL), which comprises "extension" and "fusion" operations and liberates the compressed model from the bondage of baseline. Different from the Self-KD, the proposed BPL creates a partner for each block for performance enhancement in training. For the model to absorb more diverse information, a diversity loss (DL) is designed to evaluate the difference between the original block and the partner. Besides, the partner is fused equivalently instead of being discarded directly. After training, we can simply adopt the fused compressed model that contains the enhancement information of partners but with fewer parameters and less inference cost. As validated using the UC Merced land-use, NWPU-RESISC45, and RSD46-WHU datasets, the BPL demonstrates superiority over other compared model-compression approaches. For example, it attains a substantial floating-point operations (FLOPs) reduction of 73.97% with only 0.24 accuracy (ACC.) loss for ResNet-50 on the UC Merced land-use dataset. The code is available at https://github.com/zhangxin-xd/BPL.

HTD-TS 3 : Weakly Supervised Hyperspectral Target Detection Based on Transformer via Spectral-Spatial Similarity.

As an advanced technique in remote sensing, hyperspectral target detection (HTD) is widely concerned in civilian and military applications. However, the limitation of prior and heterogeneous backgrounds makes HTD models sensitive to data corruption under various interference from the environment. In this article, a novel united HTD framework based on the concept of transformer is proposed to extract HTD based on transformer via spectral-spatial similarity (HTD-TS 3 ) under weak supervision, which opens up more flexible ways to study HTD. For the first time, the transformer mechanism is introduced into the HTD task to extract spectral and spatial features in a unified optimization procedure. By modeling long-range dependence among spectra, it realizes spectral-spatial joint inference based on long-range context, which addresses the issues of insufficient utilization of spatial information. To provide samples for weakly supervised learning (WSL), the coarse sample selection and spectral sequence construction in an efficient way are proposed, which makes full use of limited prior information. Finally, an exponential constrained nonlinear function is adopted to acquire pixel-level prediction via combining discriminative spectral-spatial features and coarse spatial information. Experiments on real hyperspectral images (HSIs) captured by different sensors at various scenes verify the effectiveness and efficiency of HTD-TS 3 .

REAF: Remembering Enhancement and Entropy-Based Asymptotic Forgetting for Filter Pruning.

Neurologically, filter pruning is a procedure of forgetting and remembering recovering. Prevailing methods directly forget less important information from an unrobust baseline at first and expect to minimize the performance sacrifice. However, unsaturated base remembering imposes a ceiling on the slimmed model leading to suboptimal performance. And significantly forgetting at first would cause unrecoverable information loss. Here, we design a novel filter pruning paradigm termed Remembering Enhancement and Entropy-based Asymptotic Forgetting (REAF). Inspired by robustness theory, we first enhance remembering by over-parameterizing baseline with fusible compensatory convolutions which liberates pruned model from the bondage of baseline at no inference cost. Then the collateral implication between original and compensatory filters necessitates a bilateral-collaborated pruning criterion. Specifically, only when the filter has the largest intra-branch distance and its compensatory counterpart has the strongest remembering enhancement power, they are preserved. Further, Ebbinghaus curve-based asymptotic forgetting is proposed to protect the pruned model from unstable learning. The number of pruned filters is increasing asymptotically in the training procedure, which enables the remembering of pretrained weights gradually to be concentrated in the remaining filters. Extensive experiments demonstrate the superiority of REAF over many state-of-the-art (SOTA) methods. For example, REAF removes 47.55% FLOPs and 42.98% parameters of ResNet-50 only with 0.98% TOP-1 accuracy loss on ImageNet. The code is available at https://github.com/zhangxin-xd/REAF.

Study of Potential Synergistic Effect of Probiotic Formulas on Acrylamide Reduction.

Acrylamide (AA) is a food processing contaminant commonly found in fried and baked food products. In this study, the potential synergistic effect of probiotic formulas in reducing AA was studied. Five selected probiotic strains (Lactiplantibacillus plantarum subsp. plantarum ATCC14917 (L. Pl.), Lactobacillus delbrueckii subsp. bulgaricus ATCC11842 (L. B.), Lacticaseibacillus paracasei subsp. paracasei ATCC25302 (L. Pa), Streptococcus thermophilus ATCC19258, and Bifidobacterium longum subsp. longum ATCC15707) were selected for investigating their AA reducing capacity. It was found that L. Pl. (108 CFU/mL) showed the highest AA reduction percentage (43-51%) when exposed to different concentrations of AA standard chemical solutions (350, 750, and 1250 ng/mL). The potential synergistic effect of probiotic formulas was also examined. The result demonstrated a synergistic AA reduction effect by the probiotic formula: L. Pl. + L. B., which also showed the highest AA reduction ability among the tested formulas. A further study was conducted by incubating selected probiotic formulas with potato chips and biscuit samples followed by an in vitro digestion model. The findings demonstrated a similar trend in AA reduction ability as those found in the chemical solution. This study firstly indicated the synergistic effect of probiotic formulas on AA reduction and its effect was also highly strain-dependent.

Filter Pruning via Learned Representation Median in the Frequency Domain.

In this article, we propose a novel filter pruning method for deep learning networks by calculating the learned representation median (RM) in frequency domain (LRMF). In contrast to the existing filter pruning methods that remove relatively unimportant filters in the spatial domain, our newly proposed approach emphasizes the removal of absolutely unimportant filters in the frequency domain. Through extensive experiments, we observed that the criterion for "relative unimportance" cannot be generalized well and that the discrete cosine transform (DCT) domain can eliminate redundancy and emphasize low-frequency representation, which is consistent with the human visual system. Based on these important observations, our LRMF calculates the learned RM in the frequency domain and removes its corresponding filter, since it is absolutely unimportant at each layer. Thanks to this, the time-consuming fine-tuning process is not required in LRMF. The results show that LRMF outperforms state-of-the-art pruning methods. For example, with ResNet110 on CIFAR-10, it achieves a 52.3% FLOPs reduction with an improvement of 0.04% in Top-1 accuracy. With VGG16 on CIFAR-100, it reduces FLOPs by 35.9% while increasing accuracy by 0.5%. On ImageNet, ResNet18 and ResNet50 are accelerated by 53.3% and 52.7% with only 1.76% and 0.8% accuracy loss, respectively. The code is based on PyTorch and is available at https://github.com/zhangxin-xd/LRMF.

Deep Hybrid 2-D-3-D CNN Based on Dual Second-Order Attention With Camera Spectral Sensitivity Prior for Spectral Super-Resolution.

A largely ignored fact in spectral super-resolution (SSR) is that the subsistent mapping methods neglect the auxiliary prior of camera spectral sensitivity (CSS) and only pay attention to wider or deeper network framework design while ignoring to excavate the spatial and spectral dependencies among intermediate layers, hence constraining representational capability of convolutional neural networks (CNNs). To conquer these drawbacks, we propose a novel deep hybrid 2-D-3-D CNN based on dual second-order attention with CSS prior (HSACS), which can excavate sufficient spatial-spectral context information. Specifically, dual second-order attention embedded in the residual block for more powerful spatial-spectral feature representation and relation learning is composed of a brand new trainable 2-D second-order channel attention (SCA) or 3-D second-order band attention (SBA) and a structure tensor attention (STA). Concretely, the band and channel attention modules are developed to adaptively recalibrate the band-wise and interchannel features via employing second-order band or channel feature statistics for more discriminative representations. Besides, the STA is promoted to rebuild the significant high-frequency spatial details for enough spatial feature extraction. Moreover, the CSS is first employed as a superior prior to avoid its effect of SSR quality, on the strength of which the resolved RGB can be calculated naturally through the super-reconstructed hyperspectral image (HSI); then, the final loss consists of the discrepancies of RGB and the HSI as a finer constraint. Experimental results demonstrate the superiority and progressiveness of the presented approach in terms of quantitative metrics and visual effect over SOTA SSR methods.

The effects of colloidal Fe and Mn on P distribution in groundwater system of Jianghan Plain, China.

Many studies have confirmed groundwater phosphorus (P) enrichment by anthropogenic and geogenic sources. However, the effects of colloidal iron (Fe) and manganese (Mn) on the groundwater P distribution remain poorly-understood. This study investigated the spatial distribution of three forms of Fe, Mn, and P (particulate, colloidal, and truly soluble) in aquifers based on groundwater monitoring data and sediment core samples for the Jianghan Plain. High proportions of colloidal Fe, Mn, and P of up to 52%, 58%, and 76%, respectively were found in the phreatic and confined aquifers. Particulate and truly soluble P dominated the phreatic aquifer and the confined aquifer, respectively. However, the truly soluble Fe and Mn were dominant among the three forms in both the phreatic and confined aquifers. The distributions of Fe, Mn, and P in colloids and sediments were also studied by X-ray diffraction (XRD) and energy-dispersive X-ray spectroscopy (EDS). A comparison of the distributions of Fe, Mn, and P between site SD01 (riparian zones) and site SD02 (farmland) showed that both external inputs and the reduced release of Fe/Mn oxides/minerals from sediments contributed to the distributions of colloidal Fe, Mn, and P. Correlation analysis showed a strong relationship between colloidal Fe/Mn and P in both groundwater and sediment, implying that colloidal Fe/Mn play a role in regulating the distribution of P in the study area. This study provides a new understanding of the effects of colloidal Fe and Mn on the P distribution among the phreatic and confined aquifers.

E2E-LIADE: End-to-End Local Invariant Autoencoding Density Estimation Model for Anomaly Target Detection in Hyperspectral Image.

Hyperspectral anomaly target detection (also known as hyperspectral anomaly detection (HAD)] is a technique aiming to identify samples with atypical spectra. Although some density estimation-based methods have been developed, they may suffer from two issues: 1) separated two-stage optimization with inconsistent objective functions makes the representation learning model fail to dig out characterization customized for HAD and 2) incapability of learning a low-dimensional representation that preserves the inherent information from the original high-dimensional spectral space. To address these problems, we propose a novel end-to-end local invariant autoencoding density estimation (E2E-LIADE) model. To satisfy the assumption on the manifold, the E2E-LIADE introduces a local invariant autoencoder (LIA) to capture the intrinsic low-dimensional manifold embedded in the original space. Augmented low-dimensional representation (ALDR) can be generated by concatenating the local invariant constrained by a graph regularizer and the reconstruction error. In particular, an end-to-end (E2E) multidistance measure, including mean-squared error (MSE) and orthogonal projection divergence (OPD), is imposed on the LIA with respect to hyperspectral data. More important, E2E-LIADE simultaneously optimizes the ALDR of the LIA and a density estimation network in an E2E manner to avoid the model being trapped in a local optimum, resulting in an energy map in which each pixel represents a negative log likelihood for the spectrum. Finally, a postprocessing procedure is conducted on the energy map to suppress the background. The experimental results demonstrate that compared to the state of the art, the proposed E2E-LIADE offers more satisfactory performance.

Weakly Supervised Discriminative Learning With Spectral Constrained Generative Adversarial Network for Hyperspectral Anomaly Detection.

Anomaly detection (AD) using hyperspectral images (HSIs) is of great interest for deep space exploration and Earth observations. This article proposes a weakly supervised discriminative learning with a spectral constrained generative adversarial network (GAN) for hyperspectral anomaly detection (HAD), called weaklyAD. It can enhance the discrimination between anomaly and background with background homogenization and anomaly saliency in cases where anomalous samples are limited and sensitive to the background. A novel probability-based category thresholding is first proposed to label coarse samples in preparation for weakly supervised learning. Subsequently, a discriminative reconstruction model is learned by the proposed network in a weakly supervised fashion. The proposed network has an end-to-end architecture, which not only includes an encoder, a decoder, a latent layer discriminator, and a spectral discriminator competitively but also contains a novel Kullback-Leibler (KL) divergence-based orthogonal projection divergence (OPD) spectral constraint. Finally, the well-learned network is used to reconstruct HSIs captured by the same sensor. Our work paves a new weakly supervised way for HAD, which intends to match the performance of supervised methods without the prerequisite of manually labeled data. Assessments and generalization experiments over real HSIs demonstrate the unique promise of such a proposed approach.

Self-spectral learning with GAN based spectral-spatial target detection for hyperspectral image.

To alleviate the shortcomings of target detection in only one aspect and reduce redundant information among adjacent bands, we propose a spectral-spatial target detection (SSTD) framework in deep latent space based on self-spectral learning (SSL) with a spectral generative adversarial network (GAN). The concept of SSL is introduced into hyperspectral feature extraction in an unsupervised fashion with the purpose of background suppression and target saliency. In particular, a novel structure-to-structure selection rule that takes full account of the structure, contrast, and luminance similarity is established to interpret the mapping relationship between the latent spectral feature space and the original spectral band space, to generate the optimal spectral band subset without any prior knowledge. Finally, the comprehensive result is achieved by nonlinearly combining the spatial detection on the fused latent features with the spectral detection on the selected band subset and the corresponding selected target signature. This paper paves a novel self-spectral learning way for hyperspectral target detection and identifies sensitive bands for specific targets in practice. Comparative analyses demonstrate that the proposed SSTD method presents superior detection performance compared with CSCR, ACE, CEM, hCEM, and ECEM.

Weakly Supervised Low-Rank Representation for Hyperspectral Anomaly Detection.

In this article, we propose a weakly supervised low-rank representation (WSLRR) method for hyperspectral anomaly detection (HAD), which formulates deep learning-based HAD into a low-lank optimization problem not only characterizing the complex and diverse background in real HSIs but also obtaining relatively strong supervision information. Different from the existing unsupervised and supervised methods, we first model the background in a weakly supervised manner, which achieves better performance without prior information and is not restrained by richly correct annotation. Considering reconstruction biases introduced by the weakly supervised estimation, LRR is an effective method for further exploring the intricate background structures. Instead of directly applying the conventional LRR approaches, a dictionary-based LRR, including both observed training data and hidden learned data drawn by the background estimation model, is proposed. Finally, the derived low-rank part and sparse part and the result of the initial detection work together to achieve anomaly detection. Comparative analyses validate that the proposed WSLRR method presents superior detection performance compared with the state-of-the-art methods.

Unsupervised spectral mapping and feature selection for hyperspectral anomaly detection.

Exploring techniques that breakthrough the unknown space or material species is of considerable significance to military and civilian fields, and it is a challenging task without any prior information. Nowadays, the use of material-specific spectral information to detect unknowns has received increasing interest. However, affected by noise and interference, high-dimensional hyperspectral anomaly detection is difficult to meet the requirements of high detection accuracy and low false alarm rate. Besides, there is a problem of insufficient and unbalanced samples. To address these problems, we propose a novel hyperspectral anomaly detection framework based on spectral mapping and feature selection (SMFS) in an unsupervised manner. The SMFS introduces the essential properties of hyperspectral data into an unsupervised neural network to construct the nonlinear mapping relationship from high-dimensional spectral space to low-dimensional deep feature space. And it searches the optimal feature subset from the candidate feature space for standing out anomalies. Because of the compelling characterization of the encoder, we develop it specifically for spectral signatures to reveal the hidden data. Quantitative and qualitative experiments on real hyperspectral datasets indicate that the proposed method can provide the compact features overcoming the problems of noise, interference, redundancy and time-consuming caused by high-dimensionality and limited samples. And it has advantages over some state-of-the-art competitors concerning detecting anomalies of different scales.

Effects of general anesthesia versus local anesthesia in primary hepatocellular carcinoma patients presenting for thermal ablation surgery: a multiple center retrospective cohort study with propensity score matching.

BACKGROUND: Whether anesthesia methods affect the prognosis of tumor patients is controversial. With the aim of comparing the effects of general anesthesia (GA) and local anesthesia (LA) in primary hepatocellular carcinoma (HCC) patients presenting for elective thermal ablation (TA) surgeries, a multiple center retrospective cohort study was designed and implemented. METHODS: Patients who received elective TA surgery under GA or LA from Jan. 2014 to Dec. 2016 and met the eligibility criteria were included. Survival analysis was used to identify the influence of anesthesia methods on recurrence-free survival (RFS) and overall survival (OS). Propensity score matching (PSM) was used to minimize the bias between the GA group and the LA group. RESULTS: A total of 244 patients with GA and 245 with LA were eligible for analysis. After PSM, 178 patients remained in each group. In the matched groups, GA showed a significantly higher recurrence rate compared with LA by both the Kaplan-Meier survival analyses (P=0.011) and multivariable Cox regression analyses (P=0.002). The multivariable Cox regression model also revealed that GA had a hazard ratio (HR) of 1.746 (P=0.036) for death compared with the LA group. CONCLUSIONS: GA is associated with decreased RFS and OS after surgery compared with LA in HCC patients undergoing TA surgery. Prospective trials exploring the effects of different anesthetic methods on cancer outcome in these patients are warranted.

An Improved Pulse-Coupled Neural Network Model for Pansharpening.

Pulse-coupled neural network (PCNN) and its modified models are suitable for dealing with multi-focus and medical image fusion tasks. Unfortunately, PCNNs are difficult to directly apply to multispectral image fusion, especially when the spectral fidelity is considered. A key problem is that most fusion methods using PCNNs usually focus on the selection mechanism either in the space domain or in the transform domain, rather than a details injection mechanism, which is of utmost importance in multispectral image fusion. Thus, a novel pansharpening PCNN model for multispectral image fusion is proposed. The new model is designed to acquire the spectral fidelity in terms of human visual perception for the fusion tasks. The experimental results, examined by different kinds of datasets, show the suitability of the proposed model for pansharpening.

Hyperspectral Pansharpening With Deep Priors.

Hyperspectral (HS) image can describe subtle differences in the spectral signatures of materials, but it has low spatial resolution limited by the existing technical and budget constraints. In this paper, we propose a promising HS pansharpening method with deep priors (HPDP) to fuse a low-resolution (LR) HS image with a high-resolution (HR) panchromatic (PAN) image. Different from the existing methods, we redefine the spectral response function (SRF) based on the larger eigenvalue of structure tensor (ST) matrix for the first time that is more in line with the characteristics of HS imaging. Then, we introduce HFNet to capture deep residual mapping of high frequency across the upsampled HS image and the PAN image in a band-by-band manner. Specifically, the learned residual mapping of high frequency is injected into the structural transformed HS images, which are the extracted deep priors served as additional constraint in a Sylvester equation to estimate the final HR HS image. Comparative analyses validate that the proposed HPDP method presents the superior pansharpening performance by ensuring higher quality both in spatial and spectral domains for all types of data sets. In addition, the HFNet is trained in the high-frequency domain based on multispectral (MS) images, which overcomes the sensitivity of deep neural network (DNN) to data sets acquired by different sensors and the difficulty of insufficient training samples for HS pansharpening.

Spectral constraint adversarial autoencoders approach to feature representation in hyperspectral anomaly detection.

Anomaly detection in hyperspectral images (HSIs) faces various levels of difficulty due to the high dimensionality, redundant information and deteriorated bands. To address these problems, we propose a novel unsupervised feature representation approach by incorporating a spectral constraint strategy into adversarial autoencoders (AAE) without any prior knowledge in this paper. Our approach, called SC_AAE (spectral constraint AAE), is based on the characteristics of HSIs to obtain better discrimination represented by hidden nodes. To be specific, we adopt a spectral angle distance into the loss function of AAE to enforce spectral consistency. Considering the different contribution rates of each hidden node to anomaly detection, we individually fuse the hidden nodes by an adaptive weighting method. A bi-layer architecture is then designed to suppress the variational background (BKG) while preserving features of anomalies. The experimental results demonstrate that our proposed method outperforms the state-of-the-art methods.

Trainable spectral difference learning with spatial starting for hyperspectral image denoising.

Because of the limited reflected energy and incoming illumination in an individual band, the reflected energy captured by a hyperspectral sensor might be low and there is inevitable noise that significantly decreases the performance of the subsequent analysis. Denoising is therefore of first importance in hyperspectral image (HSI) analysis and interpretation. However, most HSI denoising methods remove noise with the important spectral information being severely distorted. This paper presents an HSI denoising method using trainable spectral difference learning with spatial initialization (called HDnTSDL) aimed at preserving the spectral information. In the proposed HDnTSDL model, a key band is automatically selected and denoised. The denoised key band acts as a starting point to reconstruct the rest of the non-key bands. Meanwhile, a deep convolutional neural network (CNN) with trainable non-linearity functions is proposed to learn the spectral difference mapping. Then, the rest of the non-key bands are denoised under the guidance of the learned spectral difference with the key band as a starting point. Experiments have been conducted on five databases with both indoor and outdoor scenes. Comparative analyses validate that the proposed method: (i) presents superior performance in spatial recovery and spectral preservation, and (ii) requires less computational time than state-of-the-art methods.