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

Deep learning-driven non-destructive quantification of chlorophyll and antioxidant activity in therapeutic plant powders using FT-IR spectroscopy.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Same author

A dynamic reward framework for scalable and efficient IoT-WSN routing using deep reinforcement learning.

Scientific reports·2026

Same author

<b>A catalogue of Zygaenidae (Lepidoptera: Zygaenoidea) from India</b>.

Zootaxa·2026

Same author

<b>On the taxonomy of genus <i>Compsoctena</i> Zeller, 1852 (Lepidoptera: Eriocottidae) from India and Bangladesh, with descriptions of three new species</b>.

Zootaxa·2026

Same author

<b>A catalogue of Bombycoidea of India (Lepidoptera)</b>.

Zootaxa·2026

Same author

A curated dataset of 3,477 high-resolution Grapevine (Vitis vinifera) leaf images for automated detection of Black Rot, Esca, and Leaf Blight diseases.

Scientific data·2026

Search research articles

相关实验视频

Updated: Jul 19, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

随机梯度下降优化用于卷积神经网络,用于医学图像细分.

Sanam Nagendram¹, Arunendra Singh², Gade Harish Babu³

¹Department of Artificial Intelligence, KKR & KSR Institute of Technology and Sciences, Guntur, India.

Open life sciences

|August 17, 2023

概括

这项研究引入了一个新的深度卷积神经网络 (CNN) 用于医学图像的细分,在精度和敏感性方面超过现有的U-net和FCN模型,用于诸如黑色素瘤和胸部X射线等疾病.

关键词:

在SGD上,SGD是SGD.卷积神经网络是一种卷积神经网络.机器学习是机器学习.医学胸部X射线图像医学胸部X射线图像

更多相关视频

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Jul 19, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

科学领域:

医学图像分析医学图像分析
医疗保健中的人工智能
计算机视觉计算机视觉

背景情况:

医疗图像细分面临着来自头发工件和照明变化的挑战.
准确的细分对于诊断和治疗规划至关重要.

研究的目的:

开发一种新的深卷积神经网络 (CNN) 用于医学图像的细分.
为了比较CNN架构 (U-net,FCN) 和损失函数,以提高细分精度.

主要方法:

开发了一种新的CNN集成方法,用于对胸部X射线和皮肤镜像进行细分.
这项研究比较了使用 Jaccard 距离和二进制交叉损失函数的 U-net 和 FCN 架构.
使用了优化的随机梯度下降与内斯特罗夫动量.

主要成果:

拟议的CNN模型与U-net和FCN架构相比,表现出优越的性能.
关键性能指标包括灵敏度 (0.9913),准确度 (0.9883) 和子系数 (0.0246).
使用值技术进行后处理,细化了细分界限.

结论:

开发的CNN方法为医疗图像细分提供了更高的效率.
这种方法改善了各种临床条件的诊断能力和治疗确定.
该模型有效地应对诸如头发工件和医学成像中的照明变化等挑战.