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

Racialized Heteroscedasticity in Neuroimaging Features, Behavior Measures, and Neuroimaging-Based Predictive Models.

Research square·2026

Same author

Automated FDG uptake/PET-CT fused scan diagnosis of various lymph node tumors using object detection AI techniques.

Scientific reports·2026

Same author

Different BI-RADS breast cancer diagnosis using MobileNetV1 and vision transformer based on explainable artificial intelligence (XAI).

Scientific reports·2026

Same author

A Hybrid Deep Learning Framework for Automated Dental Disorder Diagnosis from X-Ray Images.

Journal of clinical medicine·2026

Same author

AI/ML-Assisted Detection of <i>HMGA2</i> RNA Isoforms in Prostate Cancer Patient Tissue.

International journal of molecular sciences·2026

Same author

Improving dental disease diagnosis using a cross attention based hybrid model of DeiT and CoAtNet.

Scientific reports·2026

Search research articles

相关实验视频

Updated: Sep 13, 2025

Utilizing 3D Printing Technology to Merge MRI with Histology: A Protocol for Brain Sectioning

Utilizing 3D Printing Technology to Merge MRI with Histology: A Protocol for Brain Sectioning

Published on: December 6, 2016

基于组织病理的脑瘤分类,使用2D-3D多模CNN变压器与堆叠分类器相结合.

Naira Elazab¹, Fahmi Khalifa², Wael Gab Allah¹

¹Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura, 35516, Egypt.

Scientific reports

|July 30, 2025

概括

准确的脑瘤分类对于有效治疗至关重要. 这项研究引入了一种混合深度学习模型,该模型结合了2D-3D CNNs和视觉转换器,用于优越的组织病理图像分析和可靠的瘤分级.

关键词:

2D-3D卷积神经网络是一个神经网络.大脑瘤分级的分级组织病理学图像分析.混合深度学习架构混合深度学习架构堆叠分类器堆叠分类器视觉变压器视觉变压器

更多相关视频

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

相关实验视频

Last Updated: Sep 13, 2025

Utilizing 3D Printing Technology to Merge MRI with Histology: A Protocol for Brain Sectioning

Utilizing 3D Printing Technology to Merge MRI with Histology: A Protocol for Brain Sectioning

Published on: December 6, 2016

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

科学领域:

医学成像分析分析医学成像分析
计算病理学计算病理学
人工智能在瘤学中的应用

背景情况:

准确的组织病理图像分级对于可靠的脑瘤诊断和治疗至关重要.
目前的方法在复杂的空间关系的可扩展性,适应性和解释性方面存在局限性.
需要先进的方法来提高脑瘤分级的准确性.

研究的目的:

为改进脑瘤分级提出一个全面的混合学习架构.
克服现有捕获空间和上下文信息方法的局限性.
从组织病理学图像开发一个强大的模型,准确地对脑瘤进行分类.

主要方法:

一种混合深度学习架构,集成2D-3D卷积神经网络 (CNN) 来进行层次特征提取和视觉转换器 (ViT) 来进行全球关系学习.
补充特征提取技术,以捕捉瘤形态 (纹理,强度) 的特定领域知识.
一个堆叠集团机器学习分类器,将CNN和ViT的特征结合起来,以提高概括性.

主要成果:

拟议的模型在TCGA和DeepHisto数据集上实现了高性能,平均准确度,精度和特异性为TCGA上的97.1%,97.1%和97.0%,在DeepHisto上的95%,94%和95%.
广泛的实验,包括废除研究和交叉数据集评估,验证了该模型的有效性.
与现有方法相比,混合模型在准确性,精度和特异性方面取得了显著的改进.

结论:

开发的混合学习架构有效地将深度学习与领域专业知识相结合,用于可靠的脑瘤分级.
该模型能够捕捉到本地层次模式和全球图像关系,从而实现更高的诊断准确性.
这种方法为临床实践中准确且可扩展的脑瘤分级提供了一个有希望的解决方案.