Search

Polyp segmentation is a challenging task, as some polyps exhibit similar textures to surrounding tissues, making them difficult to distinguish. Therefore, we present a parallel cross‐attention and texture‐aware network to address this challenging task. CATNet incorporates the parallel cross‐attention mechanism, Residual Feature Fusion Module, and texture‐aware module. Initially, polyp images undergo processing in our backbone network to extract multi‐level polyp features. Subsequently, the parallel cross‐attention mechanism sequentially captures channel and spatial dependencies across multi‐scale polyp features, thereby yielding enhanced representations. These enhanced representations are then input into multiple texture‐aware modules, which facilitate polyp segmentation by accentuating subtle textural disparities between polyps and the background. Finally, the Residual Feature Fusion module integrates the segmentation results with the previous layer of enhanced representations. This process serves to eliminate background noise and enhance intricate details. We assess the efficacy of our proposed method across five distinct polyp datasets. On three unseen datasets, CVC‐300, CVC‐ColonDB, and ETIS. We achieve mDice scores of 0.916, 0.817, and 0.777, respectively. Experimental results unequivocally demonstrate the superior performance of our approach over current models. The proposed CATNet addresses the challenges posed by textural similarities, setting a benchmark for future advancements in automated polyp detection and segmentation. [ABSTRACT FROM AUTHOR]

Background: The relationship between Protein Convertase Subtilisin Kexin Type 9 inhibitor (PCSK9i) and psychiatric adverse events (AEs) remains unclear due to the limitations of clinical trials. In this study, PCSK9i‐related psychiatric AEs were realistically observed and systematically summarized in the real world by data mining the FDA AE Reporting System (FAERS). Method: Total AEs between the third quarter of 2015 and the first quarter of 2023 were obtained from FAERS. Psychiatric AEs were identified using disproportionality analysis and clinical prioritization of signals using a rating scale, followed by univariate logistic regression to explore factors influencing psychiatric AEs. Results: Psychiatric AEs accounted for 6.7% of the total number of PCSK9i reports. Eighteen psychiatric AEs were defined as PCSK9i‐related psychiatric adverse events (ppAEs) (lower 95% CI of both ROR >1 and IC025 > 0). The median age of ppAE reports was 68 years, and female patients accounted for 22.67% of reports, including 41.40% of reports with a serious outcome. Eleven (61.11%) and seven (38.89%) ppAEs were classified as weak and moderate clinical priority, respectively. The median time to onset of ppAEs was 149 and 196 days after treatment with evolocumab and alirocumab, respectively. Patients weighing ≥80 kg were 1.59 times more likely to experience ppAEs. Conclusion: The results of this study facilitate the prioritization of psychiatric AE signals by healthcare professionals with the goal of mitigating the risk of PCSK9i‐related psychiatric AEs. However, as an exploratory study, our findings need to be confirmed in large‐scale prospective studies. [ABSTRACT FROM AUTHOR]