Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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

Voice pathology detection using optimized convolutional neural networks and explainable artificial intelligence-based analysis.

Computer methods in biomechanics and biomedical engineering·2023
Same author

Modeling nonlinear fractional-order subdiffusive dynamics in nuclear reactor with artificial neural networks.

International journal of dynamics and control·2023
Same author

A new and simple method to construct root locus of general fractional-order systems.

ISA transactions·2013
查看所有相关文章

相关实验视频

Updated: May 9, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

899

一个优化的深度神经网络与可解释的人工智能框架用于脑瘤分类.

Roohum Jegan1, Bhakti Kaushal2, Gajanan K Birajdar3

  • 1Department of Artificial Intelligence and Machine Learning, Saraswati College of Engineering, Navi Mumbai, India.

Network (Bristol, England)
|May 4, 2025
PubMed
概括

这项研究优化了ResNet深度学习模型,使用亨利气溶性优化 (HGSO) 算法在MRI扫描中对脑瘤进行分类. 改进后的模型实现了高精度,提高了诊断能力.

关键词:
脑瘤的分类 脑瘤的分类亨利气体溶解度优化优化 亨利气体溶解度优化这就是ResNet-50的特点.可以解释的人工智能AI优化了深度转移学习的优化

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.6K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

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

6.8K

相关实验视频

Last Updated: May 9, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

899
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.6K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

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

6.8K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算生物学 计算生物学

背景情况:

  • 准确的脑瘤分类对于有效的患者护理和治疗计划至关重要.
  • 磁共振成像 (MRI) 是可视化脑瘤的主要工具.
  • 深度学习模型为自动化和准确的图像分析提供了潜力.

研究的目的:

  • 开发和评估一个优化的ResNet框架,以使用MRI改进脑瘤分类.
  • 调整ResNet模型 (ResNet-18和ResNet-50) 的关键超参数,以提高性能.
  • 通过使用综合指标,对不同脑瘤数据集验证模型的有效性.

主要方法:

  • 实施ResNet-18和ResNet-50架构用于脑瘤分类.
  • 使用亨利气溶性优化 (HGSO) 算法优化ResNet超参数 (势头,学习率,时代,验证频率).
  • 在两个MRI数据库 (4个和3个瘤类别) 上对优化模型的评估,使用准确度,灵敏度,特异性,精度和F-score.
  • 使用梯度加权类激活映射 (GRAD-CAM) 进行模型解释.

主要成果:

  • 优化的ResNet-50框架在Database1.0上实现了0.9825的最高分类准确度.
  • HGSO算法有效调整了ResNet的超参数,从而实现了优越的分类性能.
  • GRAD-CAM可视化证实了该模型对相关瘤特征的关注,确保了可靠的预测.

结论:

  • 拟议的HGSO优化的ResNet框架显著提高了MRI脑瘤分类的准确性.
  • 这种深度学习优化策略为提高神经瘤学诊断精度提供了一个有希望的方法.
  • 由GRAD-CAM提供的可解释性为该模型的临床适用性建立了信心.