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

Harnessing hybrid stacking ensemble learning for accurate pulmonary embolism diagnosis using tabular clinical data.

Scientific reports·2026

Same author

Improved pulmonary embolism detection in CT pulmonary angiogram scans with hybrid vision transformers and deep learning techniques.

Scientific reports·2025

Same author

A hybrid gazelle optimization and reptile search algorithm for optimal clustering in wireless sensor networks.

Scientific reports·2025

Same author

A deep learning based hybrid recommendation model for internet users.

Scientific reports·2024

Same author

Enhancing colorectal cancer histology diagnosis using modified deep neural networks optimizer.

Scientific reports·2024

Same author

MAC-ErrorReads: machine learning-assisted classifier for filtering erroneous NGS reads.

BMC bioinformatics·2024

Search research articles

相关实验视频

Updated: Jun 26, 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

微调深度学习模型用于乳腺瘤分类.

Abeer Heikal^1,2, Amir El-Ghamry³, Samir Elmougy³

¹Department of Computer Science, Faculty of Computers and Information, Mansoura University, Mansoura, 35516, Egypt. abeerheikal@std.mans.edu.eg.

Scientific reports

|May 10, 2024

概括

此摘要是机器生成的。

这项研究使用定制CNN和优化技术改善了乳腺瘤分类. MGTO优化实现了93.13%的准确性,优于其他模型,用于更好的乳腺癌诊断.

更多相关视频

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

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

相关实验视频

Last Updated: Jun 26, 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

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

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

科学领域:

医疗成像医学成像
计算病理学计算病理学
人工智能在医学中的应用

背景情况:

精确区分良性和恶性乳腺瘤 (BT) 对于有效治疗至关重要.
组织病理学图像对于BT诊断至关重要,但手动分析可能是主观的,耗时的.
开发用于BT分类的自动化系统可以提高诊断准确性和效率.

研究的目的:

建议和评估一种方法,以提高善性和恶性乳腺瘤的分类,使用组织病理学图像.
为了比较定制卷积神经网络 (CNN) 与经过预训练的乳腺瘤分化模型的性能.
研究元启发式优化算法的对改善CNN模型对乳腺瘤分类性能的影响.

主要方法:

这项研究利用了BreakHis数据集,包括乳腺瘤的组织病理学图像.
预处理涉及图像大小调整,数据分区和增强.
为特征提取和分类开发了一个定制的CNN,与预先训练的模型 (MobileNetV3,EfficientNetB0,Vgg16,ResNet50V2) 进行性能比较.
使用灰狼优化 (GWO) 和修改大猩猩部队优化 (MGTO) 的元启发算法进行了超参数调整.

主要成果:

定制的CNN模型实现了84%的初始精度,超过了预先训练的模型 (74-82%).
在使用MGTO进行超参数调整后,定制的CNN模型在10次代内获得了93.13%的显著改进的准确性.
与GWO和未优化的模型相比,MGTO优化在提高分类准确度方面表现出卓越的性能.

结论:

提出的方法,特别是用MGTO优化的定制CNN,显示了准确和高效的乳腺瘤分类的巨大潜力.
利用优化深度学习模型的自动化系统可以帮助病理学家区分良性和恶性乳腺瘤.
这项研究有助于在乳腺癌研究和临床实践中推进AI驱动的诊断工具.