Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Neoadjuvant Immunotherapy-Based Treatment Versus Chemotherapy Alone in Resectable Locally Advanced dMMR/MSI-H Gastric Cancer: A Real-World Study with Meta-Analysis.

Cancers·2026

Same author

Artesunate does not prevent cardiac hypertrophy but inhibits heart failure progression in mice.

The Journal of pharmacology and experimental therapeutics·2026

Same author

FPGA-Based Low-Latency Semantic Feedback System for Real-Time Instrument Localization in Telesurgery.

The international journal of medical robotics + computer assisted surgery : MRCAS·2026

Same author

Laparoscopic intersphincteric resection combined with rectal eversion and modified Bacon procedure plus left lateral pelvic lymph node dissection: A video vignette.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2026

Same author

Combining in-field and edge-of-field practices enhances nitrate reduction in tile-drained catchments.

Water research·2026

Same author

Superspreading and ultra-infiltrative coacervate mediates strong underwater adhesion on hydrated and lipidic substrates.

Nature chemistry·2026

Search research articles

相关实验视频

Updated: Jan 15, 2026

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

大型模型驱动的多颗粒度医学图像分析:一个模糊的逻辑引导的框架.

Guan Wang, Mingyu Xu, Chao Li

IEEE journal of biomedical and health informatics

|October 14, 2025

概括

此摘要是机器生成的。

本研究介绍了ULVM-MG,这是一种用于使用模糊逻辑和变压器分析多种细粒度的医疗图像的新框架. 它显著提高了复杂的病理结构的诊断准确性.

更多相关视频

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

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

Published on: August 16, 2020

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

相关实验视频

Last Updated: Jan 15, 2026

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

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

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

Published on: August 16, 2020

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

科学领域:

计算病理学计算病理学
医学中的人工智能
图像分析图像分析

背景情况:

医学图像分析需要先进的计算方法来解决病理结构中的复杂性和不确定性.
现有的基于变压器的方法在有效地捕捉多个尺度的病理特征方面面临挑战.

研究的目的:

开发一个大型模型驱动的框架,ULVM-MG,集成模糊逻辑和变压器用于多颗粒度医疗图像分析.
通过处理粗,中,细等级的病理图像来提高诊断准确度.

主要方法:

ULVM-MG框架使用多颗粒度特征提取策略.
使用模糊引导的交叉注意力机制,专注于具有诊断意义的区域,同时保留上下文信息.
该方法将模糊逻辑原则与变压器架构相结合.

主要成果:

与最先进的变压器方法相比,ULVM-MG在组织病理学数据集 (LC25000和NCT) 上取得了更高的性能.
准确率为98.76% (LC25000) 和97.34% (NCT),分别超过了基线的1.61%和2.17%.
该框架在区分类似组织类型和分类良性与恶性病例方面表现出特别强大的优势.

结论:

拟议的ULVM-MG框架通过多颗粒度处理和模糊不确定性建模有效地增强了医疗图像分析.
模糊逻辑和变压器的集成为病理图像的准确性和诊断能力提供了显著的改进.
ULVM-MG代表了计算病理学的重大进步,为图像解释提供了更有系统,更准确的方法.