Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Assessment of Papillary Thyroid Carcinoma by Profiling Multiple Matrix Metalloproteinase Activities Using a Machine Learning-Assisted Peptide Microarray Sensing Platform.

Analytical chemistry·2026
Same author

Impact of Warm-Air Withering Methods on Aroma Quality of White Teas from Four Tea Cultivars.

Foods (Basel, Switzerland)·2026
Same author

Hydrogel dressings for diabetic foot ulcers: microenvironment-informed design, clinical scenario matching, and translational challenges.

Diabetes research and clinical practice·2026
Same author

Electrocatalytic Hydrogenation of Pyrazine by Cu<sub>0.95</sub>Co<sub>2.05</sub>O<sub>4</sub>: Kinetics, Mechanism, and Performance.

Chemistry, an Asian journal·2026
Same author

Plasmin-mediated fibrinolysis is required for hematopoietic recovery after 5-FU-induced myeloablation.

Blood advances·2026
Same author

Histology-guided 3D virtual staining of microCT-imaged lung tissue via deep learning.

Journal of the Royal Society, Interface·2026
Same journal

MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes.

ArXiv·2026
Same journal

A Positron Range Correction with Texture Preservation Framework in PET Imaging.

ArXiv·2026
Same journal

Automated optimization of force field parameters against ensemble-averaged measurements with Bayesian Inference of Conformational Populations.

ArXiv·2026
Same journal

Droplet Fusion as a Relaxation Process: Comparison with Shape Recovery of Newtonian and Viscoelastic Droplets.

ArXiv·2026
Same journal

Ridge-filter crosstalk in conformal proton FLASH planning: dependence on beamlet pitch and iterative mitigation.

ArXiv·2026
Same journal

Electrochemical DNA Hairpin Sensors for Differentiating Small Molecule Intercalation from Minor Groove Binding.

ArXiv·2026
查看所有相关文章

相关实验视频

Updated: Jul 16, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

计算机病理学的通用自主监督模型

Richard J Chen, Tong Ding, Ming Y Lu

    ArXiv
    |September 11, 2023
    PubMed
    概括
    此摘要是机器生成的。

    UNI是一个自我监督的模型,通过从超过1亿个组织补丁中学习,在计算病理学 (CPath) 任务中表现出色. 它使数据效率高的人工智能能够应对解剖病理学的各种诊断挑战.

    更多相关视频

    Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
    08:59

    Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

    Published on: October 28, 2018

    7.1K
    Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues
    06:44

    Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

    Published on: March 29, 2021

    2.6K

    相关实验视频

    Last Updated: Jul 16, 2025

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
    07:15

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

    Published on: August 16, 2020

    6.8K
    Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
    08:59

    Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

    Published on: October 28, 2018

    7.1K
    Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues
    06:44

    Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

    Published on: March 29, 2021

    2.6K

    科学领域:

    • 计算病理学计算病理学
    • 计算机视觉 计算机视觉 计算机视觉
    • 生物医学成像分析分析

    背景情况:

    • 全幻灯片成像 (WSI) 由于其高分辨率和形态多样性,给计算机视觉带来了重大挑战,阻碍了组织表型化的大规模数据注释.
    • 使用转移学习或在有限的病理学数据集上进行自我监督预训的现有方法显示出潜力,但需要在各种组织类型中进行更广泛的评估.
    • 对可扩展,可泛化计算病理学 (CPath) 模型的需求对于在解剖病理学中推进AI至关重要.

    研究的目的:

    • 引入UNI,一种通用的病理学自我监督模型,旨在对各种类型的病理学数据进行大规模预培训.
    • 评估UNI在广泛的CPath任务上的表现,并展示其在无监督表示学习方面的能力.
    • 为了实现对解剖病理学工作流程的数据效率高和可泛化的AI模型的开发.

    主要方法:

    • 预先训练有素的UNI在超过1亿个组织贴片上从10万个以上的诊断全幻灯片图像中获得了20种主要组织类型.
    • 在33个具有不同诊断难度的代表性计算病理学 (CPath) 临床任务上评估了UNI.
    • 评估能力包括分辨率不可知的分类,少数镜头幻灯片分类和疾病亚型概括.

    主要成果:

    • 在各种CPath任务上,UNI的表现优于之前的先进模型.
    • 演示了新的能力,如分辨率不可知组织分类和几次射击学习的幻灯片分类.
    • 在疾病亚型化方面实现了泛化,使用OncoTree分类系统分类高达108种癌症类型.

    结论:

    • UNI代表了计算机病理学 (CPath) 大规模无监督表示学习的重大进步.
    • 该模型的预训练数据规模和下游评估证明了其在实现数据效率和可泛化的AI模型方面的有效性.
    • UNI促进AI模型可转移到不同的,具有诊断挑战性的任务和解剖病理学临床工作流程.