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

Novel Adipokine, FAM19A5, Inhibits Neointima Formation After Injury Through Sphingosine-1-Phosphate Receptor 2.

Circulation·2018

Same author

Liquid-Crystalline Dynamic Networks Doped with Gold Nanorods Showing Enhanced Photocontrol of Actuation.

Advanced materials (Deerfield Beach, Fla.)·2018

Same author

KCa(H<sub>2</sub> O)<sub>2</sub> [Fe<sup>III</sup> (CN)<sub>6</sub> ]⋅H<sub>2</sub> O Nanoparticles as an Antimicrobial Agent against Staphylococcus aureus.

Angewandte Chemie (International ed. in English)·2018

Same author

Warming deferentially altered multidimensional soil legacy induced by past land use history.

Scientific reports·2018

Same author

Advanced Modified Polyacrylonitrile Membrane with Enhanced Adsorption Property for Heavy Metal Ions.

Scientific reports·2018

Same author

Insulin-like growth factor 2 is a key mitogen driving liver repopulation in mice.

Cell death & disease·2018

Search research articles

相关实验视频

Updated: Jan 9, 2026

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

乳腺癌的分类深紫外线光图像使用补丁级视觉转换器框架.

Pouya Afshin, David Helminiak, Tongtong Lu

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|December 3, 2025

概括

这项研究引入了用于乳腺癌分类的深紫外光扫描显微镜 (DUV-FSM) 框架. DUV-FSM WSI分类框架达到98.33%的准确性,改善了业内利率评估.

更多相关视频

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery

Published on: September 19, 2014

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

相关实验视频

Last Updated: Jan 9, 2026

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery

Published on: September 19, 2014

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

科学领域:

在瘤学瘤学.
医疗成像医学成像
人工智能的人工智能

背景情况:

乳腺保护手术 (BCS) 需要精确的手术内边缘评估,以平衡癌症的去除和组织的保存.
深紫外光扫描显微镜 (DUV-FSM) 为切除的乳腺组织提供快速的全表面成像 (WSI),将恶性与正常组织区分开来.
从高分辨率的DUV WSIs中对乳腺癌进行分类,由于其复杂的遗传病理特征,因此存在挑战.

研究的目的:

开发和评估DUV WSI分类框架,以准确评估乳腺癌边际.
为了提高DUV WSI分析的解释性和诊断准确性,用于手术内利率评估.

主要方法:

采用补丁级视觉变压器 (ViT) 模型来分析DUV WSIs,捕获本地和全球遗传病理特征.
整合了Grad-CAM++突出权重,以突出显示WSIs中的关键空间区域,从而提高模型的可解释性.
采用五重交叉验证策略,严格评估拟议的分类框架的性能.

主要成果:

拟议的DUV WSI分类框架实现了高分类准确率98.33%,用于区分良性与恶性乳腺组织.
ViT模型有效地捕获了 DUV WSIs 中复杂的遗传学特征,超过了传统的深度学习方法.
Grad-CAM++突出权重提高了模型预测的解释性,识别了诊断相关的组织区域.

结论:

开发的DUV WSI分类框架,利用ViT模型和Grad-CAM++,显著提高了在BCS中进行手术内边缘评估的诊断准确性.
这种方法为手术期间实时准确分类乳腺组织提供了一个有希望的工具,可能降低重新切割率.
该框架展示了先进的人工智能技术在加强对乳腺癌管理的DUV光图像的基因病理分析方面的潜力.