With the advancement of remote sensing (RS) image technology, the availability of very high-resolution (VHR) image data has brought new challenges to change detection (CD). Currently, deep learning-based CD methods commonly employ bitemporal interaction networks using convolutional neural networks (CNNs) or transformers. Yet, these models overly emphasize object accuracy, leading to a significant increase in computational costs with limited performance gains. Additionally, the current bitemporal interaction mechanisms are simplistic, failing to adequately account for spatial positions and scale variations of different objects, resulting in an inaccurate modeling of dynamic feature changes between images. To address these issues, a bitemporal attention sharing network (BASNet) is proposed, which tackles the problems effectively by making bitemporal and multiscale attention sharing the primary mode of feature interaction. Specifically, The proposed bitemporal attention sharing module leverages pairs of features preliminarily encoded by a backbone to construct shared global features, directing attention to target changes. Then, through cross-scale attention guidance and weighted fusion, it achieves attention sharing of multiscale features, eliminating the need for over-relying on deep convolutional layers for feature extraction. Experiments on three public datasets demonstrate that, in comparison to several state-of-the-art methods, our model achieves superior performance with low computational cost. Our code is available at https://github.com/JasonWZC/BASNet .

In remote sensing image processing, the segmentation of clouds and their shadows is a fundamental and vital task. For cloud images, traditional deep learning methods often have weak generalization capabilities and are prone to interference from ground objects and noise, which not only results in poor boundary segmentation but also causes false and missed detections of small targets. To address these issues, we proposed a multi-branch attention fusion network (MAFNet). In the encoder section, the dual branches of ResNet50 and the Swin transformer extract features together. A multi-branch attention fusion module (MAFM) uses positional encoding to add position information. Additionally, multi-branch aggregation attention (MAA) in the MAFM fully fuses the same level of deep features extracted by ResNet50 and the Swin transformer, which enhances the boundary segmentation ability and small target detection capability. To address the challenge of detecting small cloud and shadow targets, an information deep aggregation module (IDAM) was introduced to perform multi-scale deep feature aggregation, which supplements high semantic information, improving small target detection. For the problem of rough segmentation boundaries, a recovery guided module (RGM) was designed in the decoder section, which enables the model to effectively allocate attention to complex boundary information, enhancing the network’s focus on boundary information. Experimental results on the Cloud and Cloud Shadow dataset, HRC-WHU dataset, and SPARCS dataset indicate that MAFNet surpasses existing advanced semantic segmentation techniques.

The segmentation task of cloud and cloud shadow has always been one of the important tasks in remote sensing image processing. At present, cloud detection based on deep learning methods lacks generalization, which is easy to cause the loss of space and detail information, and missed detection and false detection occur from time to time. Aiming at the above problems, this paper proposes a multi-path, multi-scale attention network (MMA). In this network, Muti-scale overlapping patch embedding (MSP) is introduced to extract multi-scale semantic information with multi-path PVT, and strip convolution is used to supplement the spatial detail information of the image, so as to realize the effective aggregation of fine and rough features at the same feature level. In order to aggregate the global information, the multi-scale global aggregation module (MGAM) is used for deep feature extraction to supplement the high semantic information. In the decoding stage, aiming at the problem of small target cloud detection, the attention guided fusion module (AGFM) is proposed to focus on the important information of the image, remove the network noise and increase the detection accuracy of small targets. Contextual information fusion (CIF) decoding method is proposed for the coarse segmentation boundary problem, which fully integrates the context information and effectively helps to restore the image. The experimental results on Biome 8 Dataset, HRC-WHU Dataset and SPARCS Dataset confirm that our method is superior to the current cutting-edge cloud and cloud shadow detection technology.

Segmenting clouds and their shadows is a critical challenge in remote sensing image processing. The shape, texture, lighting conditions, and background of clouds and their shadows impact the effectiveness of cloud detection. Currently, architectures that maintain high resolution throughout the entire information-extraction process are rapidly emerging. This parallel architecture, combining high and low resolutions, produces detailed high-resolution representations, enhancing segmentation prediction accuracy. This paper continues the parallel architecture of high and low resolution. When handling high- and low-resolution images, this paper employs a hybrid approach combining the Transformer and CNN models. This method facilitates interaction between the two models, enabling the extraction of both semantic and spatial details from the images. To address the challenge of inadequate fusion and significant information loss between high- and low-resolution images, this paper introduces a method based on ASMA (Axial Sharing Mixed Attention). This approach establishes pixel-level dependencies between high-resolution and low-resolution images, aiming to enhance the efficiency of image fusion. In addition, to enhance the effective focus on critical information in remote sensing images, the AGM (Attention Guide Module) is introduced, to integrate attention elements from original features into ASMA, to alleviate the problem of insufficient channel modeling of the self-attention mechanism. Our experimental results on the Cloud and Cloud Shadow dataset, the SPARCS dataset, and the CSWV dataset demonstrate the effectiveness of our method, surpassing the state-of-the-art techniques for cloud and cloud shadow segmentation.

Background: Acquired ESR1 mutations are a dominant driver of distant metastasis in metastatic breast cancer, inducing a basal-like phenotype that is relatively resistant to ER antagonists with decreased progression free survival. The majority of ER+ patients also express the androgen receptor (AR), and although AR expression is associated with better outcomes, high AR expression has also been associated with resistance to endocrine therapy (ET). Thus, there is currently a conundrum on how best to target AR, and to define when it is participating as a proliferative/metastatic driver, or when it may be a potential tumor suppressor associated with good prognosis. Methods: We generated ESR1 Y537S or D538G homozygous mutations in MCF-7 cells using CRISPR Cas-9 technology. ChIP-Seq, transcriptome analyses, and quantitative analysis of ER ChIP-Seq profiles from patient biopsies were integrated. Nuclear fractionation and immunoblot analyses were performed. Results: Correlation and gene set enrichment analyses demonstrated that the androgen response pathway was significantly reduced in ESR1 mutant, compared to wild-type (WT) ER cells. A dramatic redistribution in AR binding sites to heterochromatin was observed in ESR1 mutant cells. AR and ER co-occupied DNA binding sites were redistributed only to ERE motifs present in a restricted set of gene enhancer regions. Quantitative analysis of ER DNA binding profiles from ER+ patients showed that the highest recruitment of ER to AR/ER binding sites were in patients with metastatic breast cancer. Integration of AR/ER co-bound sites with the differentially-expressed mutant transcriptome identified a gene signature that predicted poor disease-free and overall survival in ER+ primary breast cancer patients from the METABRIC database. Elevated gene expression of these AR/ER co-regulated genes, including NCOA3, BMP7, N4BP3, and FOXA1, were validated in a cohort of metastatic tumors (N=97), compared to primary tumors (N=276). AR protein levels were elevated in ESR1 mutant tumors. Mechanistic studies demonstrated that elevated AR phosphorylation at specific sites (pS515, pS650) and decreased phosphorylation (pS308) occurs in mutant cells. These sites are known to affect AR transcriptional activity, protein stability, and nuclear export. Decreased K48-AR ubiquitination was observed, suggesting that elevated AR protein levels result from altered post-transcriptional modification of AR in mutant cells. Conclusions: We propose a two-prong genomic activation mechanism in ESR1 mutant tumors with AR redistribution to heterochromatin, and genomic co-activation of AR and ER. We hypothesize that the loss of AR tumor suppressor function may help drive metastasis in ESR1 mutant tumors via AR’s collaboration with ESR1 mutant oncogenic activity. Efficacious targeting of AR may require disruption of this driver AR/ER-regulated transcriptional program. Citation Format: Sandra L. Grimm, Guowei Gu, Sarah K. Herzog, Thomas L. Gonzalez, Hangqing Lin, Amanda R. Beyer, Yassine Rechoum, Tasneem Bawa-Khalfe, Ashfia F. Khan, Lili Du, W. Fraser Symmans, Ralf Kittler, Cristian Coarfa, Suzanne A.W. Fuqua. Mutant ESR1 receptors antagonize the tumor suppressor function of androgen receptors [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr PD1-07.