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

相关实验视频

Updated: Jan 14, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K

精心调整的ResNet34用于高效的脑瘤分类.

Anas Shahin1

  • 1Faculty of Information Technology Engineering, Syrian Virtual University, Damascus, Syria. anas.shahen.2020@gmail.com.

Scientific reports
|October 22, 2025
PubMed
概括

这项研究展示了使用MRI图像进行脑瘤分类的深度转移学习方法. 微调的ResNet-34模型实现了99.66%的准确性,提高了对质瘤,脑膜瘤和垂体瘤的诊断精度.

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 journal

Effects of audio guided loving kindness meditation on psychological well being and laboratory stress responsiveness in healthy university students.

Scientific reports·2026
Same journal

Adaptive cognitive driven cross modal network for few shot fine grained recognition.

Scientific reports·2026
Same journal

Tegoprazan-based dual therapy versus bismuth-containing quadruple therapy for Helicobacter pylori eradication: a prospective, multicenter, open-label, non-inferiority, randomized controlled trial.

Scientific reports·2026
Same journal

Primary tumor resection prior to peptide receptor radionuclide therapy is associated with improved survival in metastatic gastroenteropancreatic neuroendocrine tumors: a systematic review and meta-analysis.

Scientific reports·2026
Same journal

Sleep duration among medical students and its association with bronchial asthma, anxiety, and depression.

Scientific reports·2026
Same journal

MGMT deficiency augments STING-mediated inflammatory responses accompanied by metabolic alterations in macrophages.

Scientific reports·2026

科学领域:

  • 医学成像分析 医学成像分析
  • 在瘤学中使用人工智能

背景情况:

  • 大脑瘤显著减少了预期寿命,需要早期,准确的诊断以获得有效的治疗.
  • 人工智能 (AI),特别是深度学习和卷积神经网络 (CNN),为医疗图像分析提供了自动化解决方案.

研究的目的:

  • 为了评估深度转移学习对从MRI扫描分类脑瘤的有效性.
  • 开发一种自动诊断工具,用于识别质瘤,脑膜瘤,垂体瘤和瘤的缺失.

主要方法:

  • 使用一个7023图像的大脑瘤MRI数据集 (Figshare,SARTAJ,Br35H) 分为训练,验证和测试集.
  • 采用了一个微调的ResNet-34模型,带有自定义分类头.
  • 集成的数据增强和Ranger优化器,以实现稳定的模型融合.

主要成果:

  • 提出的深度转移学习模型在分类脑瘤方面达到99.66%的高精度.
  • 性能超越了现有的最先进的脑瘤分类方法.

结论:

  • 深度转移学习,特别是微调的ResNet-34模型,对于准确的脑瘤分类非常有效.
  • 这种人工智能驱动的方法具有显著的潜力,可以提高早期诊断和患者存活率.
关键词:
脑瘤分类大脑瘤的分类深度卷积神经网络是一个深度卷积神经网络.核磁共振成像扫描转移学习转移学习

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
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

7.6K

相关实验视频

Last Updated: Jan 14, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
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

7.6K