Search

Effectively and efficiently retrieving images from remote-sensing databases is a critical challenge in the realm of remote-sensing big data. Utilizing hand-drawn sketches as retrieval inputs offers intuitive and user-friendly advantages, yet the potential of multi-level feature integration from sketches remains underexplored, leading to suboptimal retrieval performance. To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote-sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update. This approach employs only vision information and does not require semantic knowledge concerning the sketch and image. It starts by employing multi-level self-attention guided feature extraction to tokenize the query sketches, as well as self-attention feature extraction to tokenize the candidate images. It then employs cross-attention mechanisms to establish token correspondence between these two modalities, facilitating the computation of sketch-to-image similarity. Our method significantly outperforms existing sketch-based remote-sensing image retrieval techniques, as evidenced by tests on multiple datasets. Notably, it also exhibits robust zero-shot learning capabilities in handling unseen categories and strong domain adaptation capabilities in handling unseen novel remote-sensing data. The method's scalability can be further enhanced by the pre-calculation of retrieval tokens for all candidate images in a database. This research underscores the significant potential of multi-level, attention-guided tokenization in cross-modal remote-sensing image retrieval. For broader accessibility and research facilitation, we have made the code and dataset used in this study publicly available online. [ABSTRACT FROM AUTHOR]

Background: Thrombomodulin, a thrombin receptor with anticoagulant, anti-inflammatory, and cytoprotective properties, has been suggested to play a pivotal role in ischemic stroke. However, the association of plasma thrombomodulin with post-stroke cognitive impairment (PSCI) remains unclear. We aimed to prospectively investigate the associations of plasma thrombomodulin with PSCI among ischemic stroke patients in a multicenter cohort study., Methods: We measured plasma thrombomodulin levels at baseline among 615 ischemic stroke patients from a preplanned ancillary study of the CATIS (China Antihypertensive Trial in Acute Ischemic Stroke). We used Montreal Cognitive Assessment (MoCA) to evaluate cognitive function at 3-month follow-up after ischemic stroke, and PSCI was defined as MoCA score <23., Results: Plasma thrombomodulin was inversely associated with PSCI, and the adjusted odds ratio of PSCI for the highest versus lowest quartile of thrombomodulin was 0.50 (95 % CI: 0.28-0.92, P trend =0.026). Each standard deviation increment of log-transformed thrombomodulin was associated with a 23 % (odds ratio: 0.77, 95 % CI: 0.62-0.97, P=0.029) decreased risk of PSCI. In addition, plasma thrombomodulin could significantly improve the risk reclassification of PSCI beyond established risk factors (net reclassification index: 25.04 %, 95 % CI: 7.20 %-42.87 %, P=0.007; integrated discrimination improvement: 1.13 %, 95 % CI: 0.18 %-2.09 %, P=0.020)., Conclusions: High plasma thrombomodulin levels were associated with a decreased risk of PSCI among ischemic stroke patients. Our findings suggest that plasma thrombomodulin might be a predictive biomarker and potential therapeutic target for PSCI., Competing Interests: Declaration of competing interest There are no conflicts of interest to declare., (Copyright © 2024. Published by Elsevier Inc.)