Current applications of artificial intelligence-based computer vision in laparoscopic surgery

Recent advances in artificial intelligence(AI)have sparked a surge in the application of computer vision(CV)in surgical video analysis.Laparoscopic surgery produces a large number of surgical videos,which provides a new opportunity for improving of CV technology in laparoscopic surgery.AI-based CV techniques may leverage these surgical video data to develop real-time automated decision support tools and surgeon training systems,which shows a new direction in dealing with the shortcomings of laparoscopic surgery.The effectiveness of CV applications in surgical procedures is still under early evaluation,so it is necessary to discuss challenges and obstacles.The review introduced the commonly used deep learning algorithms in CV and described their usage in detail in four application scenes,including phase recognition,anatomy detection,instrument detection and action recognition in laparoscopic surgery.The currently described applications of CV in laparoscopic surgery are limited.Most of the current research focuses on the identification of workflow and anatomical structure,while the identification of instruments and surgical actions is still awaiting further breakthroughs.Future research on the use of CV in laparoscopic surgery should focus on applications in more scenarios,such as surgeon skill assessment and the development of more efficient models.

Transcriptomic Analysis of Differentially Expressed Genes and Alternative Splicing Events Associated with Crassulacean Acid Metabolism in Orchids

Phalaenopsis equestris is an obligate crassulacean acid metabolism(CAM) plant with high ornamental and economic value. CAM photosynthesis is associated with drought tolerance and efficient water utilization, which enhances the survival rate of CAM plants in arid environments.The identification and analysis of CAM-related genes will be helpful to improve our understanding of the regulatory mechanisms of CAM metabolism. In this study, we analyzed RNA-Seq data to identify differentially expressed genes(DEGs) between circadian day and night in P.equestris leaves then performed GO and KEGG functional enrichment analysis. The pathways that were significantly enriched among these DEGs included carbon fixation, circadian clock regulation, glucose metabolism, photosynthesis, and plant hormone signaling. We also used Pac Bio long-read Iso-Seq technology, which identified many alternative splicing events for key genes in CAM-related pathways, including carbon fixation, circadian clock regulation, and stomatal movement. These findings suggested that alternative splicing events might be involved in CAM metabolism. Many unknown or uncharacterized genes were also found to be potentially involved in CAM metabolism. For example, the Peq000162 gene encodes a protein belonging to the Ldp A(light-dependent period) iron-sulfur protein family, and it was found to generate many alternatively spliced products. These findings shed light on CAM metabolic mechanisms in P. equestris along with the molecular functions of key CAM genes. Ultimately, the information may help enhance crop yield and drought tolerance through the introduction of CAM features into C3 crops.