Renal fibrosis is a final common pathway of chronic kidney disease. Sustained activation of fibroblasts is considered to play a key role in perpetuating renal fibrosis but the driving force in the perpetuation stage is only partially understood. To date, some investigations have specifically identified overexpression of microRNA 21 (miR-21) in the progression of kidney fibrosis. Nevertheless, the precise role of miR-21 in fibroblast activation remains largely unknown. In this study, we found that miR-21 was significantly upregulated in activated fibroblasts and that it maintained itself at constant high levels by employing an auto-regulatory loop between miR-21, PDCD4 and AP-1. Persistently upregulated miR-21 suppressed protein expression of Smad7 and, eventually, enhanced the TGF-β1/Smad pathway to promote fibroblast activation. More importantly, we found miR-21 sequestration with miR-21 antagomir or AP-1 inhibitors attenuated unilateral ureteral obstruction (UUO)-induced renal fibrosis. miR-21-knockout mice also suffered far less interstitial fibrosis in response to kidney injury. Altogether, these data suggest that miR-21 is a main driving force of fibroblast activation and keeps its high expression level by employing a double negative autoregulatory loop. Targeting this aberrantly activated feedback loop may provide new therapeutic strategy in treating fibrotic kidneys.

Focal segmental glomerulosclerosis (FSGS) is a chronic glomerular disease with poor clinical outcomes. Podocyte loss via apoptosis is one important mechanism underlying the pathogenesis of FSGS. Recently, Yes-associated-protein (YAP), a key downstream protein in the Hippo pathway, was identified as an activator for multiple gene transcriptional factors in the nucleus to control cell proliferation and apoptosis. To investigate the potential role of YAP in the progression of FSGS, we examined kidney samples from patients with minimal change disease or FSGS and found that increases in podocyte apoptosis is positively correlated with the cytoplasmic distribution of YAP in human FSGS. Utilizing an established mT/mG transgenic mouse model and primary cultured podocytes, we found that YAP was distributed uniformly in nucleus and cytoplasm in the podocytes of control animals. Adriamycin treatment induced gradual nuclear exclusion of YAP with enhanced phospho-YAP/YAP ratio, accompanied by the induction of podocyte apoptosis both in vivo and in vitro. Moreover, we used verteporfin to treat an Adriamycin-induced FSGS mouse model, and found YAP inhibition by verteporfin induced nuclear exclusion of YAP, thus increasing podocyte apoptosis and accelerating disease progression. Therefore, our findings suggest that YAP nuclear distribution and activation in podocytes is an important endogenous anti-apoptotic mechanism during the progression of FSGS.

Deep neural networks have strong feature learning ability, but their vulnerability cannot be ignored. Current research shows that deep learning models are threatened by adversarial examples in remote sensing (RS) classification tasks, and their robustness drops sharply in the face of adversarial attacks. Therefore, many adversarial attack methods have been studied to predict the risks faced by a network. However, the existing adversarial attack methods mainly focus on single-modal image classification networks, and the rapid growth of RS data makes multimodal RS image classification a research hotspot. Generating multimodal adversarial examples needs to consider a high attack success rate, subtle perturbation, and collaborative attack ability between different modalities. In this article, we investigate the vulnerability of multimodal RS classification networks and propose a multifeature collaborative adversarial network (MFCANet) for generating multimodal adversarial examples. Two modality-specific generators are designed to generate the multimodal collaborative perturbations with strong attack ability, and two modality-specific discriminators make the generated multimodal adversarial examples closer to the real instances. In addition, a modality-specific generative loss and a modality-specific discriminative loss are proposed, and an alternating optimization strategy is designed for training the proposed MFCANet. Extensive experiments are carried out on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 2D dataset and ISPRS Potsdam 2D dataset. The results show that the attack performance of the proposed method is stronger than that of the fast gradient sign method (FGSM), project gradient descent (PGD), and Carlini and Wagner (C&W) attack methods.

The performance of a neural network is highly dependent on the labeled samples. However, the labeled samples are primarily clean, which prevents the network from capturing the features of the samples near the decision boundary. For hyperspectral images (HSIs), high spectral dimensions and same-spectra foreign matter lead to more boundary samples in the data. In this letter, we investigate an adversarial attack algorithm against these problems for HSIs. A modified DeepFool algorithm is implemented to generate boundary adversarial samples with minimal disturbance, and the generated boundary adversarial samples are simply added to the training set to improve the accuracy of the boundary samples in the data. Furthermore, we iteratively complete network training and boundary adversarial sample generation so that the decision boundary can be adjusted according to the real-time classification situation. Extensive experiments are carried out on the two HSI datasets, and the results demonstrate that the modified DeepFool algorithm can improve the accuracy of the decision boundary. Our findings also show that adversarial attacks are sensitive to high-dimensional and multiple-category data and are worthy of further study.

The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of potential feature extraction and nonlinear representation, deep clustering algorithms have become a hot topic in hyperspectral remote sensing. Different tasks often need different features. However, the current deep clustering algorithms generally separate feature extraction from clustering, which results in the extracted features that are not constrained by clustering tasks. Therefore, the features extracted by these algorithms may not be suitable for clustering. To address this issue, we adopt intraclass distance as a constraint condition and proposed an intraclass distance constrained deep clustering algorithm for hyperspectral images. The proposed algorithm propagates the clustering error back to the feature mapping process of the autoencoder network, so as to realize the constraint of clustering objective on feature extraction and make the extracted features more suitable for clustering tasks. In addition, the proposed algorithm simultaneously completes network optimization and clustering, which is more efficient. Experimental results demonstrate the intense competitiveness of the proposed algorithm in comparison with state-of-the-art clustering methods for hyperspectral images.

Recently, Transformer has achieved significant success in hyperspectral image (HSI) classification task. However, most Transformer and its variants focus more on spatial domain global feature learning, ignoring the complementary characteristics provided by frequency domain features. The Fast Fourier Transform (FFT), due to its sensitivity for frequency domain information, has become a primary tool for frequency domain analysis. However, different frequency bands are often assigned the same attention values, and the differences between different frequency bands are not considered. To fully explore and fusion spatial and frequency domain features, we propose a multi-scale spatial-frequency domain cross transformer (SFDCT-Former) network. We design a two-branch structure for spatial domain and frequency domain feature learning: one branch utilizes the multi-head self-attention (MHSA) module for spatial domain feature learning, while the other incorporates a Multi-Frequency Domain Transformer (MFre-Former) encoder for frequency domain feature learning. The MFre-Former encoder divides the frequency domain into non-overlapping frequency bands and assigns distinct attention to each frequency band, therefore, different frequency domain information can be captured more precisely. Furthermore, to fuse the spatial and frequency domain features, we design a Multi-Level Cross Attention (MLCA) fusion module. The MLCA module effectively combines spatial and frequency domain features at different levels to better capture their complementary characteristics. Extensive experiments conduct on four publicly available HSI datasets demonstrate that the proposed method outperforms nine state-of-the-art methods in classification performance. The code is available at https://github.com/AAAA-CS/SFDCT-Former.