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

Optimizing nuclear-renewable hybrid energy systems for cost efficiency based on energy security concerns in Puerto-Rico.

Scientific reports·2026
Same author

Optimization, implementation, and performance of TMS coils with maximum focality and various stimulation depths.

Journal of neural engineering·2026
Same author

Integrated Use of Oxidative Stress and Histological Biomarkers of T. tinca as Indicators of 17-Alpha-Ethynylestradiol Exposure.

Environmental toxicology·2025
Same author

Real-time computation of brain E-field for enhanced transcranial magnetic stimulation neuronavigation and optimization.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Novel Volume Integral Equation Approach for Low-Frequency E-Field Dosimetry of Transcranial Magnetic Stimulation.

IEEE transactions on magnetics·2024
Same author

A boundary element method of bidomain modeling for predicting cellular responses to electromagnetic fields.

Journal of neural engineering·2024

相关实验视频

Updated: Jun 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

使用正确的直角分解与深度学习网络集成的脑瘤检测.

Rita Appiah1, Venkatesh Pulletikurthi2, Helber Antonio Esquivel-Puentes3

  • 1School of Nuclear Engineering, Purdue University, West Lafayette, IN 47906, USA.

Computer methods and programs in biomedicine
|April 26, 2024
PubMed
概括

这项研究引入了一种新的方法,将正确直角分解 (POD) 与卷积神经网络 (CNN) 结合起来,以使用MRI扫描进行高效的脑瘤检测. POD-CNN模型在减少计算时间的情况下实现了高精度,有助于及时诊断.

关键词:
脑瘤检测 脑瘤检测 脑瘤检测深度学习是一种深度学习.可解释的人工智能有比例的正交分解.转移学习转移学习

更多相关视频

Multiparametric Tumor Organoid Drug Screening Using Widefield Live-Cell Imaging for Bulk and Single-Organoid Analysis
12:41

Multiparametric Tumor Organoid Drug Screening Using Widefield Live-Cell Imaging for Bulk and Single-Organoid Analysis

Published on: December 23, 2022

4.8K
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

1.0K

相关实验视频

Last Updated: Jun 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Multiparametric Tumor Organoid Drug Screening Using Widefield Live-Cell Imaging for Bulk and Single-Organoid Analysis
12:41

Multiparametric Tumor Organoid Drug Screening Using Widefield Live-Cell Imaging for Bulk and Single-Organoid Analysis

Published on: December 23, 2022

4.8K
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

1.0K

科学领域:

  • 医学成像分析 医学成像分析
  • 医疗保健中的人工智能
  • 计算神经科学是一种神经科学.

背景情况:

  • 大脑瘤破坏正常功能,需要准确及时检测.
  • 机器学习有助于诊断,但有限的数据给培训带来了挑战.
  • 与机器学习集成的低阶模型为可靠的检测提供了可行的解决方案.

研究的目的:

  • 为了比较正确的直角分解 (POD) 与卷积神经网络 (CNN) 的有效性,与在MRI扫描中识别脑瘤的最先进模型进行比较.
  • 评估POD-CNN模型和转移学习模型 (MobileNetV2,Inception-v3,ResNet101,VGG-19) 的可解释性和性能.
  • 以有限的数据来证明低模型方法的实用性,以提高大脑瘤检测的准确性.

主要方法:

  • 利用2D磁共振成像 (MRI) 扫描来检测大脑瘤.
  • 实现并比较了正确直角分解 (POD) 和卷积神经网络 (CNN) 合模型.
  • 评估的预训练转移学习模型:MobileNetV2,Inception-v3,ResNet101和VGG-19. 这两种学习模式都在进行预训练.
  • 采用可解释的人工智能技术,特别是SHAP,用于模型解释性.

主要成果:

  • 标准的CNN在瘤预测中实现了99.21%的准确性.
  • 结合的POD-CNN模型在计算时间的约三分之一时间内显示出可比的准确性 (95.88%).
  • 可解释性AI (SHAP) 表示MobileNetV2在划定瘤边界方面具有优越的性能.

结论:

  • 适当的正交分解 (POD) 与卷积神经网络 (CNN) 的整合代表了使用最小MRI数据进行脑瘤检测的新方法.
  • 这项研究强调了低模型机器学习方法的潜力,以提高瘤检测的准确性和效率.
  • 这些发现支持开发更容易获得和计算效率更高的AI工具用于医学诊断.