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

Brain Imaging

Brain Imaging

Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...

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

Eye Movement Classification Using Neuromorphic Vision Sensors.

Journal of eye movement research·2026

Same author

An investigation of pre-stimulus eeg for prediction of driver reaction time.

Biomedical physics & engineering express·2025

Same author

Real-Time Anomaly Detection for an ADMM-Based Optimal Transmission Frequency Management System for IoT Devices.

Sensors (Basel, Switzerland)·2022

Same author

Exploring the relationships between fundamental movement skills and health related fitness components in children.

European journal of sport science·2020

Same author

Recognition and Repetition Counting for Local Muscular Endurance Exercises in Exercise-Based Rehabilitation: A Comparative Study Using Artificial Intelligence Models.

Sensors (Basel, Switzerland)·2020

Same author

Bio-inspired Surface Texture Modification as a Viable Feature of Future Aquatic Antifouling Strategies: A Review.

International journal of molecular sciences·2020

Search research articles

相关实验视频

Updated: Jan 13, 2026

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

在MRI扫描中使用边缘计算和浅层注意力引导CNN的脑瘤分类.

Niraj Anil Babar¹, Junayd Lateef¹, ShahNawaz Syed¹

¹Sensor Signal and Information Processing (SenSIP) Center, Arizona State University, Arizona, AZ 85281, USA.

|October 29, 2025

概括

此摘要是机器生成的。

这项研究引入了一种高效的注意力引导的深度学习模型,用于使用MRI扫描进行脑瘤分类,以实现高精度,减少模型大小,用于实际医疗应用.

关键词:

生物医学图像处理卷积神经网络是一种卷积神经网络.边缘计算是一种边缘计算.图像的分类图像的分类.磁共振成像技术的使用模型压缩压缩模型.

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

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

相关实验视频

Last Updated: Jan 13, 2026

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

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

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

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:

大脑瘤需要精确的磁共振成像 (MRI) 来诊断和治疗.
深度学习 (AI) 在MRI分析中表现有前途,但通常会导致大型,缓慢的模型不适合边缘计算.
高效的AI模型对于大脑瘤分类的实际临床部署至关重要.

研究的目的:

开发一种新的,轻量级的,以注意力为导向的脑瘤分类模型.
研究方法来减少模型参数而不会影响诊断准确度.
为了提高人工智能驱动的大脑瘤分析的实用性,用于医学边缘计算.

主要方法:

开发了一个浅层的注意力引导卷积神经网络 (ANSA_Ensemble).
模型压缩技术和蒙特卡洛模拟用于评估.
该模型在三个不同的,开源的大脑瘤数据集上得到了验证.

主要成果:

ANSA_Ensemble模型实现了高精度:98.04% (最佳) 和96.69% (平均) 在成数据集上.
在Bhuvaji (95.16%) 和Sherif (95.20%) 数据集中获得了可比的结果.
深度可分离的卷积提供了准确性和速度之间的最佳平衡.

结论:

提出的以注意力为导向的模型表现出与最先进的方法相匹配的性能.
越来越多的注意力障碍始终提高了模型的准确性.
该研究提供了一种高效的AI解决方案,用于大脑瘤分类,并提供公开可用的代码.