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

Dedicated First-Trimester Anomaly Scan in a National Prenatal Screening Program and Timing of Diagnosis: The Prospective IMITAS Cohort Study.

BJOG : an international journal of obstetrics and gynaecology·2026

Same author

Cost-Effectiveness Analysis of the Multicenter Scale-Up of the SAFE@Home Telemonitoring Platform for Blood Pressure and Symptoms in Women with Hypertensive Disorders of Pregnancy.

Telemedicine journal and e-health : the official journal of the American Telemedicine Association·2026

Same author

Preferences of Pregnant Women and Healthcare Professionals on First-Trimester Ultrasound Screening for Fetal Anomalies: A Discrete Choice Experiment.

Prenatal diagnosis·2026

Same author

Deep learning applied to standard radiographs improves detection of implant loosening in total knee arthroplasty: A proof-of-concept study.

Journal of experimental orthopaedics·2026

Same author

A Framework for Prenatal Counselling Recommendations in Congenital Diaphragmatic Hernia: A RAND-Modified Delphi Study.

Prenatal diagnosis·2026

Same author

Early versus late termination for fetal anomalies: Women's perspectives and psychological impact in a mixed methods study.

Acta obstetricia et gynecologica Scandinavica·2026

Search research articles

相关实验视频

Updated: Jul 12, 2025

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

使用Pix2pix与U-Net相比,胎盘血管细分使用Pix2pix.

Anouk van der Schot¹, Esther Sikkel¹, Marèll Niekolaas¹

¹Obstetrics & Gynecology, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands.

Journal of imaging

|October 27, 2023

概括

条件生成对抗网络 (cGAN) 在胎儿镜像中改善了胎盘血管细分,表现优于U-Net. 这一进步提高了计算机辅助手术的精度,但需要进一步研究以实现概括性.

关键词:

胎儿外科手术胎儿手术胎儿镜检查 (fetoscopy) 是一种对胎儿进行的检查.生成型的人工智能 (GAI)双胞胎对双胞胎输血综合征船舶细分船舶细分

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks

Published on: March 29, 2018

相关实验视频

Last Updated: Jul 12, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks

Published on: March 29, 2018

科学领域:

医疗成像医学成像
计算机辅助手术计算机辅助手术
深度学习 (Deep Learning) 是一种深度学习.

背景情况:

胎镜激光手术依赖于精确的胎盘血管细分.
目前的细分方法在程序内和程序间表现出显著的变化.
解决这种变化对于改善外科手术结果至关重要.

研究的目的:

为了比较条件生成对抗网络 (cGAN) 与胎盘血管细分在胎儿镜像中的U-Net模型的性能.
为了评估 pix2pix cGAN 模型对于这个特定应用的有效性.
评估深度学习在计算机辅助胎儿镜外科手术中降低细分变异性的潜力.

主要方法:

训练并评估了两个深度学习模型:U-Net和pix2pix (cGAN).
利用公开可用的数据集和内部验证集进行全面测试.
使用 Dice 和 Intersection over Union (IoU) 评分量化比较细分性能.

主要成果:

在公开数据集上,pix2pix模型在U-Net上表现优越 (Dice:0.80与0.75,IoU:0.70与0.66).
内部验证证实了pix2pix的优势 (Dice:0.68与0.53,IoU:0.59与0.49).
这两个指标都显示了cGAN方法的统计学显著改善 (p < 0.01).

结论:

与U-Net相比,条件生成对抗网络,特别是pix2pix,在胎盘图像中提供了较好的胎盘血管细分.
基于cGAN的方法在提高计算机辅助胎儿镜外科手术的精度方面表现有前途.
需要进一步的研究,以解决这些模型在各种手术场景中的通用性.