Search

Spectral reconstruction (SR) from multispectral images (MSIs) is a crucial task in remote sensing image processing, aiming to enhance the spectral resolution of MSIs to produce hyperspectral images (HSIs). However, most existing deep learning-based SR methods primarily focus on deeper network architectures, often overlooking the importance of extracting multiscale spatial and spectral features in the MSIs. To bridge this gap, this paper proposes a multiscale spatial–spectral dense residual attention fusion network (MS2Net) for SR. Specifically, considering the multiscale nature of the land-cover types in the MSIs, a three-dimensional multiscale hierarchical residual module is designed and embedded in the head of the proposed MS2Net to extract spatial and spectral multiscale features. Subsequently, we employ a two-pathway architecture to extract deep spatial and spectral features. Both pathways are constructed with a single-shot dense residual module for efficient feature learning and a residual composite soft attention module to enhance salient spatial and spectral features. Finally, the spatial and spectral features extracted from the different pathways are integrated using an adaptive weighted feature fusion module to reconstruct HSIs. Extensive experiments on both simulated and real-world datasets demonstrate that the proposed MS2Net achieves superior performance compared to state-of-the-art SR methods. Moreover, classification experiments on the reconstructed HSIs show that the proposed MS2Net-reconstructed HSIs achieve classification accuracy that is comparable to that of real HSIs.

Abstract Background We aimed to determine whether and how the combination of acetazolamide and remote ischemic preconditioning (RIPC) reduced the incidence and severity of acute mountain sickness (AMS). Methods This is a prospective, randomized, open-label, blinded endpoint (PROBE) study involving 250 healthy volunteers. Participants were randomized (1:1:1:1:1) to following five groups: Ripc (RIPC twice daily, 6 days), Rapid-Ripc (RIPC four times daily, 3 days), Acetazolamide (twice daily, 2 days), Combined (Acetazolamide plus Rapid-Ripc), and Control group. After interventions, participants entered a normobaric hypoxic chamber (equivalent to 4000 m) and stayed for 6 h. The primary outcomes included the incidence and severity of AMS, and SpO2 after hypoxic exposure. Secondary outcomes included systolic and diastolic blood pressure, and heart rate after hypoxic exposure. The mechanisms of the combined regime were investigated through exploratory outcomes, including analysis of venous blood gas, complete blood count, human cytokine antibody array, ELISA validation for PDGF-AB, and detection of PDGF gene polymorphisms. Results The combination of acetazolamide and RIPC exhibited powerful efficacy in preventing AMS, reducing the incidence of AMS from 26.0 to 6.0% (Combined vs Control: RR 0.23, 95% CI 0.07–0.70, P = 0.006), without significantly increasing the incidence of adverse reactions. Combined group also showed the lowest AMS score (0.92 ± 1.10). Mechanistically, acetazolamide induced a mild metabolic acidosis (pH 7.30 ~ 7.31; HCO3 − 18.1 ~ 20.8 mmol/L) and improved SpO2 (89 ~ 91%) following hypoxic exposure. Additionally, thirty differentially expressed proteins (DEPs) related to immune-inflammatory process were identified after hypoxia, among which PDGF-AB was involved. Further validation of PDGF-AB in all individuals showed that both acetazolamide and RIPC downregulated PDGF-AB before hypoxic exposure, suggesting a possible protective mechanism. Furthermore, genetic analyses demonstrated that individuals carrying the PDGFA rs2070958 C allele, rs9690350 G allele, or rs1800814 G allele did not display a decrease in PDGF-AB levels after interventions, and were associated with a higher risk of AMS. Conclusions The combination of acetazolamide and RIPC exerts a powerful anti-hypoxic effect and represents an innovative and promising strategy for rapid ascent to high altitudes. Acetazolamide improves oxygen saturation. RIPC further aids acetazolamide, which synergistically regulates PDGF-AB, potentially involved in the pathogenesis of AMS. Trial registration ClinicalTrials.gov NCT05023941.

Introduction: The present study aimed to investigate whether and how normobaric intermittent hypoxic training (IHT) or remote ischemic preconditioning (RIPC) plus normoxic training (RNT) has a synergistic protective effect on lipid metabolism and vascular function compared with normoxic training (NT) in overweight or obese adults. Methods: A total of 37 overweight or obese adults (36.03 ± 10.48 years) were randomly assigned to 3 groups: NT group (exercise intervention in normoxia), IHT group (exercise intervention in normobaric hypoxic chamber), and RNT group (exercise intervention in normoxia + RIPC twice daily). All participants carried out the same 1-h exercise intervention for a total of 4 weeks, 5 days per week. Physical fitness parameters were evaluated at pre- and postexercise intervention. Results: After training, all three groups had a significantly decreased body mass index (p < 0.05). The IHT group had reduced body fat percentage, visceral fat mass (p < 0.05), blood pressure (p < 0.01), left ankle-brachial index (ABI), maximal heart rate (HRmax) (p < 0.05), expression of peroxisome proliferator-activated receptor-γ (PPARγ) (p < 0.01) and increased expression of SIRT1 (p < 0.05), VEGF (p < 0.01). The RNT group had lowered waist-to-hip ratio, visceral fat mass, blood pressure (p < 0.05), and HRmax (p < 0.01). Conclusion: IHT could effectively reduce visceral fat mass and improve vascular elasticity in overweight or obese individuals than pure NT with the activation of SIRT1-related pathways. And RNT also produced similar benefits on body composition and vascular function, which were weaker than those of IHT but stronger than NT. Given the convenience and economy of RNT, both intermittent hypoxic and ischemic training have the potential to be successful health promotion strategies for the overweight/obese population.

Recently, hyperspectral image (HSI) classification methods based on deep-learning have attracted widespread attention. Convolutional neural networks, as a crucial deep-learning technique, have exhibited outstanding performance in HSI classification. However, there are still some challenges, such as limited labeled samples, and feature extraction of complex land cover objects. To address these challenges, in this paper, we propose a multiscale cross-fusion network for HSI classification. It consists of three components: a spectral signatures extraction network, a spatial features extraction network and a classification network, which are utilized to extract spectral signatures, extract spatial contextual information and generate classification results, respectively. Specifically, the cross-branch multiscale convolutional block and the channel global contextual attention are integrated to extract spectral signatures, and the cross-hierarchy multiscale convolutional blocks and the spatial global contextual attention are combined to extract spatial features. Furthermore, special fusion strategies are proposed in these blocks to promote the interaction between features and achieve better feature connectivity. A series of experiments are conducted on three public HCI datasets, and the results show that the overall accuracy of the proposed network is 0.57%, 0.61%, and 0.3% higher than that of the state-of-the-art method on the PU, SV, and HH datasets, respectively.

Hyperspectral image (HSI) classification is one of the most crucial tasks in remote sensing processing. The attention mechanism is preferable to a convolutional neural network (CNN), due to its superior ability to express information during HSI processing. Recently, numerous methods combining CNNs and attention mechanisms have been applied in HSI classification. However, it remains a challenge to achieve high-accuracy classification by fully extracting effective features from HSIs under the conditions of limited labeled samples. In this paper, we design a novel HSI classification network based on multiscale hybrid networks and attention mechanisms. The network consists of three subnetworks: a spectral-spatial feature extraction network, a spatial inverted pyramid network, and a classification network, which are employed to extract spectral-spatial features, to extract spatial features, and to obtain classification results, respectively. The multiscale fusion network and attention mechanisms complement each other by capturing local and global features separately. In the spatial pyramid network, multiscale spaces are formed through down-sampling, which can reduce redundant information while retaining important information. The structure helps the network better capture spatial features at different scales, and to improve classification accuracy. Experimental results on various public HSI datasets demonstrate that the designed network is extremely competitive compared to current advanced approaches, under the condition of insufficient samples.

In recent years, convolutional neural networks (CNNs) have been introduced for pixel-wise hyperspectral image (HSI) classification tasks. However, some problems of the CNNs are still insufficiently addressed, such as the receptive field problem, small sample problem, and feature fusion problem. To tackle the above problems, we proposed a two-branch convolutional neural network with a polarized full attention mechanism for HSI classification. In the proposed network, two-branch CNNs are implemented to efficiently extract the spectral and spatial features, respectively. The kernel sizes of the convolutional layers are simplified to reduce the complexity of the network. This approach can make the network easier to be trained and fit the network to small sample size conditions. The one-shot connection technique is applied to improve the efficiency of feature extraction. An improved full attention block, named polarized full attention, is exploited to fuse the feature maps and provide global contextual information. Experimental results on several public HSI datasets confirm the effectiveness of the proposed network.

In recent years, hyperspectral image (HSI) classification has become a hot research direction in remote sensing image processing. Benefiting from the development of deep learning, convolutional neural networks (CNNs) have shown extraordinary achievements in HSI classification. Numerous methods combining CNNs and attention mechanisms (AMs) have been proposed for HSI classification. However, to fully mine the features of HSI, some of the previous methods apply dense connections to enhance the feature transfer between each convolution layer. Although dense connections allow these methods to fully extract features in a few training samples, it decreases the model efficiency and increases the computational cost. Furthermore, to balance model performance against complexity, the AMs in these methods compress a large number of channels or spatial resolutions during the training process, which results in a large amount of useful information being discarded. To tackle these issues, in this article, a novel one-shot dense network with polarized attention, namely, OSDN, was proposed for HSI classification. More precisely, since HSI contains rich spectral and spatial information, the OSDN has two independent branches to extract spectral and spatial features, respectively. Similarly, the polarized AMs contain two components: channel-only AMs and spatial-only AMs. Both polarized AMs can use a specially designed filtering method to reduce the complexity of the model while maintaining high internal resolution in both the channel and spatial dimensions. To verify the effectiveness and lightness of OSDN, extensive experiments were carried out on five benchmark HSI datasets, namely, Pavia University (PU), Kennedy Space Center (KSC), Botswana (BS), Houston 2013 (HS), and Salinas Valley (SV). Experimental results consistently showed that the OSDN can greatly reduce computational cost and parameters while maintaining high accuracy in a few training samples.

In hyperspectral remote sensing, the clustering technique is an important issue of concern. Affinity propagation is a widely used clustering algorithm. However, the complex structure of the hyperspectral image (HSI) dataset presents challenge for the application of affinity propagation. In this paper, an improved version of affinity propagation based on complex wavelet structural similarity index and local outlier factor is proposed specifically for the HSI dataset. In the proposed algorithm, the complex wavelet structural similarity index is used to calculate the spatial similarity of HSI pixels. Meanwhile, the calculation strategy of the spatial similarity is simplified to reduce the computational complexity. The spatial similarity and the traditional spectral similarity of the HSI pixels jointly constitute the similarity matrix of affinity propagation. Furthermore, the local outlier factors are applied as weights to revise the original exemplar preferences of the affinity propagation. Finally, the modified similarity matrix and exemplar preferences are applied, and the clustering index is obtained by the traditional affinity propagation. Extensive experiments were conducted on three HSI datasets, and the results demonstrate that the proposed method can improve the performance of the traditional affinity propagation and provide competitive clustering results among the competitors.

The detailed characteristics of strokes at high altitudes in diverse nations have not been extensively studied. We retrospectively enrolled 892 cases of first-ever acute ischemic strokes at altitudes of 20, 2550, and 4200 m in China (697 cases from Penglai, 122 cases from Huzhu, and 73 cases from Yushu). Clinical data and brain images were analyzed. Ischemic strokes at high altitudes were characterized by younger ages (69.14 ± 11.10 vs. 64.44 ± 11.50 vs. 64.45 ± 14.03, p < 0.001) and larger infract volumes (8436.37 ± 29,615.07 mm3 vs. 17,213.16 ± 47,044.74 mm3 vs. 42,459 ± 84,529.83 mm3, p < 0.001). The atherosclerotic factors at high altitude, including diabetes mellitus (28.8% vs. 17.2% vs. 9.6%, p < 0.001), coronary heart disease (14.3% vs. 1.6% vs. 4.1%, p < 0.001), and hyperlipidemia (20.2% vs. 17.2% vs. 8.2%, p = 0.031), were significantly fewer than those in plain areas. Polycythemia and hemoglobin levels (138.22 ± 18.04 g/L vs. 172.87 ± 31.57 g/L vs. 171.81 ± 29.55 g/L, p < 0.001), diastolic pressure (89.98 ± 12.99 mmHg vs. 93.07 ± 17.79 mmHg vs. 95.44 ± 17.86 mmHg, p = 0.016), the percentage of hyperhomocysteinemia (13.6% in Penglai vs. 41.8% in Huzhu, p < 0.001), and the percentage of smoking (33.1% in Penglai vs. 50.0% in Huzhu, p = 0.023) were significantly elevated at high altitudes. We concluded that ischemic stroke occurred earlier and more severely in the Chinese plateau. While the atherosclerotic factors were not prominent, the primary prevention of strokes at high altitudes should emphasize anticoagulation, reducing diastolic pressure, adopting a healthy diet, and smoking cessation.