Search research articles

Search research articles

相关实验视频

Updated: Jan 13, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

基于深度学习的细菌食优化算法,以改进基于数字造乳镜的乳腺癌检测.

D Banumathy¹, D Karthikeyan², G Mohanraj³

¹Paavai Engineering College, Pachal, Namakkal, 637018, India. banumathydhanabalanpec@paavai.edu.in.

Scientific reports

|October 30, 2025

概括

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

Multi-domain feature fusion with variational mode decomposition and hybrid LightGBM-Logistic Regression for multi-class seizure classification.

BioData mining·2026

Same author

Machine learning-based MPPT integration with quadratic double-extended DC-DC converter for grid-connected PV-powered BLDC electric vehicles.

Scientific reports·2026

Same author

Synthesis, characterization and biological evaluation of a novel chalcone derivative: Spectroscopic, DFT, docking, ADMET and MD Studies.

Journal of molecular graphics & modelling·2025

Same author

Quantum-inspired seagull optimised deep belief network approach for cardiovascular disease prediction.

PeerJ. Computer science·2025

Same author

A Comparative Randomized Controlled Trial of Homeopathy versus Allopathy in Acute Otitis Media and Its Recurrence in Children.

Complementary medicine research·2025

Same author

Exploring the effect of disease causing mutations in metal binding sites of human ARSA in metachromatic leukodystrophy.

Advances in protein chemistry and structural biology·2024

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

这项研究通过使用深度学习和自动超参数优化来增强早期乳腺癌检测. 细菌食优化-卷积神经网络 (BFO-CNN) 模型显著提高了乳房图分析的准确性.

科学领域:

医疗成像医学成像
人工智能的人工智能
计算机科学计算机科学

背景情况:

乳腺扫描对于早期发现乳腺癌至关重要,但依赖于主观分析,导致潜在的不准确性.
深度学习模型,特别是卷积神经网络 (CNN),在图像分析任务中表现有前途,例如乳房图解读.
对于CNN的手动超参数调整是耗时和劳动密集型的,阻碍了最佳性能.

研究的目的:

通过使用深度学习技术,提高早期乳腺癌检测的准确性和效率.
探索各种计算机视觉模型的应用,包括VGG19,InceptionV3和定制的CNN,用于乳房图分析.
为CNN实现自动超参数优化,以提高其诊断能力.

主要方法:

使用了数字数据库查乳房学 (DDSM) 数据集进行乳房图像分析.
研究的深度学习模型:视觉几何组 (VGG) 19,Inception V3 和一个定制的20层卷积神经网络 (CNN).
采用细菌食优化 (BFO) 算法来自动优化CNN的超参数,包括过器大小,过器数量和隐藏层.

主要成果:

拟议的细菌食优化 - 卷积神经网络 (BFO-CNN) 方法在现有方法中表现出优异的性能.
在VGG19上实现了7.62%的精度改进,在InceptionV3上提高了9.16%,在定制CNN-20模型上提高了1.78%.

关键词:

优化细菌食的方法.乳腺癌乳腺癌乳腺癌卷积神经网络是一种卷积神经网络.开始V3 开始V3 乳房学乳房学乳房学视觉几何组 19 视觉几何组 19

更多相关视频

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

相关实验视频

Last Updated: Jan 13, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

使用BFO的自动超参数优化显著提高了CNN模型在乳腺癌检测中的有效性.

结论:

深度学习和自动超参数优化提供了一种强大的方法,通过乳房影像分析来增强乳腺癌检测.
与传统的CNN架构相比,BFO-CNN模型具有显著的潜力,可以提高乳腺癌诊断的准确性.
这项研究强调了元启发算法在优化医疗图像分析的深度学习模型中的价值.