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

Optimizing efficiency in CT services: a data-driven approach using action logs from the radiology information system.

Japanese journal of radiology·2026

Same author

Assessment of agreement of left ventricular myocardial strain derived from cardiac computed tomography with cardiac magnetic resonance.

The international journal of cardiovascular imaging·2026

Same author

A Semi-Automated Deep Learning Model for Diagnosing Placenta Accreta Spectrum (COMPAS): Comparison with Radiologists' Interpretations.

The Tohoku journal of experimental medicine·2026

Same author

Evaluation of GPT-5 for Esophageal Cancer Staging Using Fluorodeoxyglucose Positron Emission Tomography Maximum-Intensity Projection Images: Comparative Pilot Study.

JMIR cancer·2026

Same author

Age- and Sex-Specific Distribution and Reference Values of Coronary Artery Calcium in a Large Asymptomatic Japanese Cohort.

Journal of the American Heart Association·2026

Same author

Attenuated Li-Fraumeni syndrome with TP53 p.R181H in a Japanese patient with metastatic rectal adenocarcinoma: a case report.

Familial cancer·2026

Search research articles

相关实验视频

Updated: Feb 21, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

PlaNet-S:使用U-Net和SegNeXt为胎盘的自动语义细分模型.

Isso Saito¹, Shinnosuke Yamamoto¹, Eichi Takaya^2,3

¹Department of Clinical Imaging, Tohoku University Graduate School of Medicine, Sendai, Miyagi, Japan.

Journal of imaging informatics in medicine

|May 27, 2025

概括

一种新型的深度学习模型,即胎盘细分网络 (PlaNet-S),被开发用于MRI扫描中的自动化胎盘细分. 与现有模型相比,PlaNet-S在对胎盘结构进行细分方面表现出更高的准确性,改善了对胎盘异常的分析.

关键词:

自动语义细分的自动语义细分.深度学习是一种深度学习.磁共振成像技术磁共振成像技术胎盘胎盘胎盘胎盘视觉变压器视觉变压器

更多相关视频

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

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: Feb 21, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

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
深度学习 (Deep Learning) 是一种深度学习.

背景情况:

精确的胎盘细分对于使用MRI诊断胎盘异常至关重要.
手动细分是耗时和主观的.
深度学习模型为自动化和客观分析提供了潜力.

研究的目的:

使用集体学习开发和评估一个完全自动化的语义胎盘细分模型.
集成U-Net和SegNeXt架构,以提高细分性能.
将开发的模型与现有的最先进的方法进行比较.

主要方法:

通过组合U-Net和SegNeXt架构开发了胎盘细分网络 (PlaNet-S).
利用了来自218名怀孕妇女的1090张注释MRI图像的数据集,怀疑有胎盘异常.
通过交叉与联盟 (IoU) 和计数连接组件 (CCC) 的指标来评估性能.

主要成果:

而PlaNet-S的IOU (0.78) 比U-Net (0.73) 和DS-transUNet (0.64) (p<0.005) 的IOU要高得多.
PlaNet-S显示了与U-Net++ (0.77) 相似的IOU.
在CCC中,PlaNet-S显著优于所有相比模型,在86.0%的案例中与地面真相相匹配.

结论:

开发的PlaNet-S模型提供了准确和自动化的胎盘细分.
集体学习将U-Net和SegNeXt集成,提高了细分性能.
在胎盘成像分析中,PlaNet-S为临床应用提供了一个有前途的工具.