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

Enhancing Cross-scale Feature Mutual Information via Heterogeneous Graph Contrastive Learning for Drug-Target Binding Affinity Prediction.

IEEE journal of biomedical and health informatics·2026

Same author

Postoperative Length of Stay After Minimally Invasive Transforaminal Lumbar Interbody Fusion: Analysis of Perioperative Predictors.

Journal of visualized experiments : JoVE·2026

Same author

Juglone targets CBS to inhibit the Wnt/β-catenin pathway and promotes osteosarcoma cell apoptosis.

iScience·2026

Same author

Tunable particle-free region via acoustic force balance around an oscillating microbubble.

Ultrasonics·2026

Same author

Research Trends and Knowledge Evolution of Surgical Approaches in Primary Total Hip Arthroplasty: A Bibliometric Analysis.

Inquiry : a journal of medical care organization, provision and financing·2026

Same author

Fabrication of high-aspect-ratio sub-30 nm zone plates by a zone-deepening process for hard X-ray microscopy.

Optics express·2026

Same journal

A computational model of chemically- and mechanically-induced thrombus formation in cerebral aneurysms.

Computers in biology and medicine·2026

Same journal

An improved catch fish optimization based deep learning model for Parkinson disease classification using EEG signal.

Computers in biology and medicine·2026

Same journal

Assessing the robustness of evaluation metrics for synthetic ECG signal quality.

Computers in biology and medicine·2026

Same journal

Integrating stemness and epithelial-mesenchymal transition signatures with machine learning identifies RUNX1 as a therapeutic vulnerability in colorectal cancer.

Computers in biology and medicine·2026

Same journal

Differential regional textural attributes of tongue in normal and acidity patients in the light of traditional Chinese medicine.

Computers in biology and medicine·2026

Same journal

SC-MSDNet: Spatial-consistent multi-view self-distillation for retinal OCT classification.

Computers in biology and medicine·2026

查看所有相关文章

Search research articles

相关实验视频

Updated: Jul 16, 2025

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

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

Published on: October 28, 2018

基于金字塔的自主监督学习用于基因病理图像分类的图像分类.

Junjie Wang¹, Hao Quan², Chengguang Wang³

¹Ningbo Artificial Intelligence Institute of Shanghai Jiao Tong University, Zhejiang 315000, PR China; Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, PR China.

Computers in biology and medicine

|September 14, 2023

概括

此摘要是机器生成的。

本研究介绍了基于金字塔的局部波纹变压器 (PLWT),这是一种用于医学成像的自我监督学习方法. PLWT有效地从组织病理学图像中提取特征,在可转移性和竞争性性能方面优于传统方法.

关键词:

组织病理图像组织病理图像基于金字塔的变压器自主监督学习学习

更多相关视频

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

相关实验视频

Last Updated: Jul 16, 2025

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

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

Published on: October 28, 2018

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
机器学习机器学习

背景情况:

医学成像中的监督学习需要大型标记的数据集,这些数据集对于组织病理学来说很难获得.
自主监督学习 (SSL) 通过在未标记的数据上预训练模型提供了一个解决方案.

研究的目的:

为提议一种新的自主监督的基于金字塔的局部波纹变压器 (PLWT) 模型,用于在组织病理学中增强特征提取.
评估PLWT在下游任务的预培训模型中的有效性,使用未标记的基因病理图像.

主要方法:

开发了PLWT模型,其中包含波形变换,以减少特征提取过程中的信息损失.
集成了一个局部挤压和激发 (Local SE) 模块,在前网络中具有反向残余,以捕获本地图像信息.
使用自主监督方法,预先在大量未标记的组织病理图像的数据集上训练模型.

主要成果:

与其他SSL方法相比,PLWT在组织病理图像分析方面表现出了竞争力的表现.
由PLWT在组织病理学图像上学习的视觉表示的可转移性超过了在ImageNet.Net上训练的监督模型的可转移性.
基于波段的低采样显著减少了特征传输中的信息损失.

结论:

拟议的PLWT模型有效地利用自主监督学习从组织病理图像中提取丰富的本地和全球特征.
通过利用未标记的数据,PLWT显示了改善医疗图像分析的巨大潜力.
用PLWT进行自主监督的预训练可以提高学习到的表征的可转移性,用于组织病理学任务.