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

SC-GROG followed by L+S reconstruction with multiple sparsity constraints for accelerated Golden-angle-radial DCE-MRI.

PloS one·2025
Same author

Cardiac MR image reconstruction using cascaded hybrid dual domain deep learning framework.

PloS one·2025
Same author

Brain tumor detection and segmentation using deep learning.

Magma (New York, N.Y.)·2024
Same author

Efficient motion estimation and discrete cosine transform implementation using the graphics processing units.

PloS one·2024
Same author

Federated Learning for Medical Image Analysis with Deep Neural Networks.

Diagnostics (Basel, Switzerland)·2023
Same author

Automated grading of chest x-ray images for viral pneumonia with convolutional neural networks ensemble and region of interest localization.

PloS one·2023

相关实验视频

Updated: May 21, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

448

降低复杂度深度神经网络的性能评估.

Shahrukh Agha1, Sajid Nazir2, Mohammad Kaleem1

  • 1Department of Electrical and Computer Engineering, COMSATS University, Islamabad, Pakistan.

PloS one
|March 20, 2025
PubMed
概括

这项研究简化了深度神经网络 (DNN) 用于在低功耗设备上进行医学图像分析. 一种新的通道缩小方法实现了显著的模型大小缩小,在疾病分类的性能损失最小.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K
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

932

相关实验视频

Last Updated: May 21, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

448
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K
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

932

科学领域:

  • 计算机科学 计算机科学
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 深度神经网络 (DNN) 在医学图像分类方面表现出色,但计算密集.
  • 降低复杂性对于在低功耗边缘应用中部署DNN至关重要.
  • 现有的方法往往涉及耗时的操作和性能权衡.

研究的目的:

  • 为DNNs提出一个简化的模型复杂性降低技术.
  • 为了证明ResNet-50集成在低功耗设备中的复杂性降低.
  • 为了评估胸部X射线 (CXR) 图像的多类分类的性能.

主要方法:

  • 一种新的通道缩小技术应用于DNN.
  • 对于低功耗边缘设备的ResNet-50模型复杂性降低.
  • 对CXR图像的多类分类 (正常,肺炎,COVID-19).
  • 模型概括和Grad-CAM可视化用于可解释性.
  • 理论VLSI架构设计以实现最佳性能.

主要成果:

  • 实现了75%,87%和93%的连续减小.
  • 最小的分类性能下降分别为0.5%,0.5%和0.8%.
  • 证明了可接受的模型概括和可解释的可视化.
  • 介绍了最佳性能模型的理论VLSI架构.

结论:

  • 拟议的通道减少技术有效地减少了低功耗医疗成像应用的DNN复杂性.
  • 可以实现显著的模型尺寸缩小,对分类性能的影响微不足道.
  • 该方法为在疾病诊断的边缘设备上部署先进的AI模型提供了一种实用方法.