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

Effects of Ecological Momentary Assessment Prompting Schedule on Affect Measurement Variability and Associations With Next-Day Health Behaviors.

Assessment·2026

Same author

Tunable dual-band THz metamaterial absorber with regression-learning-enabled numerical redesign.

Scientific reports·2026

Same author

Mothers' and adolescents' bicultural management difficulties reciprocally relate to their depressive and anxiety symptoms.

Child development·2026

Same author

Network-based artificial intelligence in mental healthcare: A systematic review of chatbots, artificial intelligence/machine learning models and ethical considerations in global healthcare networks.

Digital health·2026

Same author

Computational and experimental pathways to next-generation ultrawide-band-gap oxide semiconductors.

Nano convergence·2026

Same author

Neuromorphic robust framework for integrated estimation and control in dynamical systems using spiking neural networks.

Scientific reports·2025

Search research articles

相关实验视频

Updated: May 25, 2025

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

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

Published on: November 30, 2022

基于T1权重的MRI脑瘤分类,使用混合深度学习模型.

Mohsen Asghari Ilani¹, Dingjing Shi², Yaser Mike Banad³

¹School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA.

Scientific reports

|February 27, 2025

概括

通过U-Net深度学习,可以从MRI扫描中准确地分类大脑瘤,达到98.56%的准确率. 这种卷积神经网络方法增强了早期检测和治疗计划,以改善患者的治疗结果.

关键词:

大脑瘤是什么?卷积神经网络是一种卷积神经网络.医学成像医学成像转移学习转移学习这就是U-Net.

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

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

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

Published on: April 13, 2013

相关实验视频

Last Updated: May 25, 2025

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

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

Published on: November 30, 2022

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

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

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

Published on: April 13, 2013

科学领域:

神经成像和人工智能的人工智能
医学图像分析和深度学习

背景情况:

大脑健康对认知功能至关重要,磁共振成像 (MRI) 对诊断至关重要.
深度学习模型越来越多地用于医疗保健中的高性能图像处理.
准确的脑瘤分类对于有效的治疗计划至关重要.

研究的目的:

在MRI扫描上使用U-Net架构对脑瘤 (瘤,脑膜瘤,垂体瘤) 进行分类.
用转移学习来评估各种卷积神经网络 (CNN) 的性能.
评估U-Net用于神经成像的诊断潜力.

主要方法:

将U-Net细分架构应用于脑MRI扫描以进行瘤分类.
使用转移学习与像Inception-V3,EfficientNetB4和VGG19.9这样的CNN.
使用包括准确性,F-score,回忆和精度在内的指标进行绩效评估.

主要成果:

U-Net实现了优异的性能,准确率为98.56%,F-score为99%,AUC为99.8%,回忆/精度为99%.
交叉数据集验证证明了强大的性能,在外部队列上准确率为96.01%.
U-Net证明了对脑瘤细分和分类的有效性.

结论:

在神经成像中,U-Net在准确的脑瘤细分和分类方面表现出高效.
该研究强调了U-Net和转移学习的潜力,以提高诊断准确度.
这些发现支持加强临床决策和改善神经瘤学患者护理.