Form follows function: Nuclear morphology as a quantifiable predictor of cellular senescence

Enlarged or irregularly shaped nuclei are frequently observed in tissue cells undergoing senescence. However, it remained unclear whether this peculiar morphology is a cause or a consequence of senescence and how informative it is in distinguishing between proliferative and senescent cells. Recent research reveals that nuclear morphology can act as a predictive biomarker of senescence, suggesting an active role for the nucleus in driving senescence phenotypes. By employing deep learning algorithms to analyze nuclear morphology, accurate classification of cells as proliferative or senescent is achievable across various cell types and species both in vitro and in vivo. This quantitative imaging-based approach can be employed to establish links between senescence burden and clinical data, aiding in the understanding of age-related diseases, as well as assisting in disease prognosis and treatment response.     

组学时代下机器学习方法在临床决策支持中的应用

随着组学技术的不断发展,对于不同层次和类型的生物数据的获取方法日益成熟。在疾病诊治过程中会产生大量数据,通过机器学习等人工智能方法解析复杂、多维、多尺度的疾病大数据,构建临床决策支持工具,辅助医生寻找快速且有效的疾病诊疗方案是非常必要的。在此过程中,机器学习等人工智能方法的选择显得尤为重要。基于此,本文首先从类型和算法角度对临床决策支持领域中常用的机器学习等方法进行简要综述,分别介绍了支持向量机、逻辑回归、聚类算法、Bagging、随机森林和深度学习,对机器学习等方法在临床决策支持中的应用做了相应总结和分类,并对它们的优势和不足分别进行讨论和阐述,为临床决策支持中机器学习等人工智能方法的选择提供有效参考。     

Developmental switch in the function of inhibitory commissural V0d interneurons in zebrafish

1. Download : Download high-res image (134KB)
2. Download : Download full-size image

     

Applied artificial intelligence in healthcare: Listening to the winds of change in a post-COVID-19 world

This editorial article aims to highlight advances in artificial intelligence (AI) technologies in five areas: Collaborative AI, Multimodal AI, Human-Centered AI, Equitable AI, and Ethical and Value-based AI in order to cope with future complex socioeconomic and public health issues.