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

Search research articles

相关实验视频

Updated: Jan 9, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

一个ResNet-50-UNet混合与鱼优化算法,用于准确的肝脏瘤细分.

Proloy Kumar Mondol¹, Md Ariful Islam Mozumder^1,2, Hee Cheol Kim¹

¹Institute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of Korea.

Diagnostics (Basel, Switzerland)

|December 11, 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

An Integrated Architecture for Colorectal Polyp Segmentation: The µ-Net Framework with Explainable AI.

Diagnostics (Basel, Switzerland)·2025

Same author

Machine Learning-Based Validation of LDHC and SLC35G2 Methylation as Epigenetic Biomarkers for Food Allergy.

Biomedicines·2025

Same author

Automatic Fracture Detection Convolutional Neural Network with Multiple Attention Blocks Using Multi-Region X-Ray Data.

Life (Basel, Switzerland)·2025

Same author

Automated Pipeline for Robust Cat Activity Detection Based on Deep Learning and Wearable Sensor Data.

Sensors (Basel, Switzerland)·2024

Same author

BFLIDS: Blockchain-Driven Federated Learning for Intrusion Detection in IoMT Networks.

Sensors (Basel, Switzerland)·2024

Same author

A multi-objective optimisation approach with improved pareto-optimal solutions to enhance economic and environmental dispatch in power systems.

Scientific reports·2024

此摘要是机器生成的。

这项研究介绍了一种混合深度学习模型,将U-Net和鱼优化算法 (WOA) 结合起来,用于准确的肝脏瘤细分. 这种新的方法显著提高了细分精度,有助于肝癌诊断和治疗规划.

科学领域:

医疗成像医学成像
人工智能的人工智能
在瘤学瘤学.

背景情况:

从3D医学图像中精确细分肝脏和肝脏瘤对于肝癌诊断和治疗规划至关重要.
细分的挑战来自具有相似特征的器官,导致精确划分的困难.

研究的目的:

开发一种混合深度学习模型,用于增强肝脏和肝脏瘤的细分.
使用鱼优化算法 (WOA) 优化深度学习模型的超参数,以提高细分性能.

主要方法:

提出了一个混合模型,将基于U-Net的结构与鱼优化算法 (WOA) 集成在一起.
使用WOA来微调LiTS-Res-UNet架构的超参数,以实现最佳的深度学习模型性能.

主要成果:

在一个基准数据集上,LiTS-Res-Unet + WOA混合模型实现了高精度 (99.54%),子系数 (92.38%) 和贾卡德指数 (86.73%).
拟议的模型在肝脏瘤细分任务中表现优于现有的最先进方法.

结论:

基于WOA的自适应搜索有效地确定了最佳的超参数,增强了深度学习模型的融合和准确性.
混合模型展示了强大的性能和临床适用性,用于精确的肝脏瘤细分.

关键词:

这是一个小的-UNET-WOAWOA.这就是ResNet-50的特点.联合国网络联合国网络联合国网络鱼优化算法鱼优化算法生物灵感优化优化方法深度学习是一种深度学习.进行元启发式优化优化.

更多相关视频

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

相关实验视频

Last Updated: Jan 9, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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