Search for: All records

Traditional cancer rate estimations are often limited in spatial resolutions and lack considerations of environmental factors. Satellite imagery has become a vital data source for monitoring diverse urban environments, supporting applications across environmental, socio-demographic, and public health domains. However, while deep learning (DL) tools, particularly convolutional neural networks, have demonstrated strong performance in extracting features from high-resolution imagery, their reliance on local spatial cues often limits their ability to capture complex, non-local, and higher-order structural information. To overcome this limitation, we propose a novel LLM-based multi-agent coordination system for satellite image analysis, which integrates visual and contextual reasoning through a simplicial contrastive learning framework (Agent- SNN). Our Agent-SNN contains two augmented superpixel-based graphs and maximizes mutual information between their latent simplicial complex representations, thereby enabling the system to learn both local and global topological features. The LLM-based agents generate structured prompts that guide the alignment of these representations across modalities. Experiments with satellite imagery of Los Angeles and San Diego demonstrate that Agent-SNN achieves signi cant improvements over state-of-the-art baselines in regional cancer prevalence estimation tasks. 

Abstract Post‐traumatic osteoarthritis develops following an inciting injury to a joint and results in cartilage degeneration. Mechanical loading, including articulation, drives anabolic responses in cartilage clinically, in vivo, and in vitro. Tribological articulation, or sliding of cartilage on a glass counterface, has long been used as an in vitro tool to study cartilage tissue behavior. However, it is unclear if tribological articulation affects chondrocyte fate following injury, and if the timing of articulation impacts the resultant effect. The goal of this study was to investigate the effect of tribological articulation on injured cartilage tissue at two time points: (i) performed immediately after injury and (ii) 24 h after injury. Neonatal bovine femoral cartilage explants were injured using a rapid spring‐loaded impactor and subsequently subjected to tribological articulation. Cell death due to impact injury was highest near the articular surface, suggesting a strain‐dependent mechanism. Immediate articulation following injury mitigated cell death compared to injury alone or delayed articulation; markers for both general cell death and early‐stage apoptosis were markedly decreased in the explants that were immediately slid. Interestingly, mitigation of cell death due to sliding was most predominant at the cartilage surface. Tribological articulation is known to create fluid flow within the tissue, predominantly at the articular surface, which could drive the protective response seen here. Altogether, this work shows that perturbations to the cellular environment immediately following cartilage injury significantly impact chondrocyte fate.