相关实验视频
Updated: Jun 13, 2025

Cross-Modal Multivariate Pattern Analysis
Published on: November 9, 2011
核子子类型的分类使用跨模式学习
Lucas W Remedios1, Shunxing Bao2, Samuel W Remedios3,4
1Vanderbilt University, Department of Computer Science, Nashville, USA.
这项研究引入了跨模式学习,以在虚拟的血素和素 (H&E) 染料中识别更多细胞类型,推进数字病理学注释,以更好地理解生理学.
科学领域:
- 数字病理学数字病理学
- 计算生物学是一种计算生物学.
- 组织学成像分析分析分析.
背景情况:
- 细胞通信和空间关系对人类生理学至关重要.
- 血素和欧 (H&E) 染色是临床和研究环境中常见的方法.
- 目前的AI模型,如结肠核识别和分类 (CoNIC) 挑战,只能在H&E染色上标记有限数量的细胞类型.
研究的目的:
- 开发一种新的方法,在虚拟的H&E图像上标记以前无法标记的细胞类型.
- 通过将多重复合免疫光 (MxIF) 数据与H&E.数据相结合,利用跨模式学习.
- 在数字病理学中增强细胞类型分类的细粒度.
主要方法:
- 利用多重免疫光学 (MxIF) 组织学成像来识别14种不同的细胞子类.
- 采用风格转移技术,从MxIF数据生成虚拟的H&E图像.
- 将详细的细胞标签从MxIF转移到合成的虚拟H&E图像中进行分析.
主要成果:
- 在虚拟的H&E图像上成功识别了辅助T细胞和原始细胞核.
- 获得了0.34 ± 0.15的辅助T细胞和0.47 ± 0.1的祖先细胞的积极预测值.
- 通过使用跨模式学习,证明了将高密度标签从MxIF转移到虚拟H&E的可行性.
结论:
- 跨模式学习可以在虚拟的H&E图像上对更广泛的细胞类型进行注释.
- 这种方法显著扩大了AI在自动化数字病理学的细胞分类方面的潜力.
- 这些发现代表了在细胞病理学中详细的细胞分析的有希望的进步.
更多相关视频
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
12:27Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
Published on: February 15, 2017
相关概念视频
Classification of Neurotransmitters
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)
Neuron Structure
Nervous Tissue: Neuron Types
Structurally, neurons are categorized into three main types: multipolar, bipolar, and unipolar (or pseudounipolar). Multipolar neurons, which are the most common type in the brain and spinal cord, as well as all motor neurons, possess multiple dendrites and a single axon.
Bipolar neurons, on the other hand, have one primary dendrite and one axon. They are...
Neural Circuits
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Higher Mental Functions of Brain: Learning and Memory