相关实验视频

Updated: Jan 17, 2026

Murine Fetal Echocardiography

Murine Fetal Echocardiography

Published on: February 15, 2013

FetalDenseNet:用于在产前超声波中提升早期检测胎儿解剖平面的多层次深度学习

Samrat Kumar Dey^1,2, Arpita Howlader³, Md Shabukta Haider²

¹MU Institute for Data Science and Informatics, University of Missouri-Columbia, Columbia, MO, USA.

Journal of perinatal medicine

|September 22, 2025

概括

深度学习模型,特别是DenseNet169,显著提高了胎儿超声波解释的准确性. 这提高了诊断能力,并支持产前护理临床决策.

科学领域:

医疗成像医学成像
人工智能的人工智能
产科产科产科产科产科

背景情况:

对胎儿超声波图像的准确解释对于产前护理至关重要.
深度学习 (DL) 提供了改善医疗图像自动化分析的潜力.
胎儿解剖平面的分类是超声波解释的一个关键步骤.

研究的目的:

使用深度学习 (DL) 方法提高胎儿解剖平面分类的准确性.
为此任务评估各种卷积神经网络 (CNN) 架构的性能.
确定最有效的DL模型,以改善胎儿超声波的解释.

主要方法:

评估了五个CNN架构 (VGG16,ResNet50,InceptionV3,DenseNet169,MobileNetV2) 进行了评估,其中包括:
使用了12400张临床验证的胎儿超声波图像的大数据集.
模型进行了预处理,微调,并根据分类准确性进行评估.

主要成果:

DenseNet169实现了最高的分类准确率,达到92%.
所有测试的CNN模型都显示了提高分类准确性的潜力.
在不同的CNN架构中,性能有所不同.

结论:

基于CNN的模型,特别是DenseNet169,显著提高了胎儿超声波的诊断准确性.
这一进步有助于减少解释中的错误率.
这些发现支持在产前护理中改善临床决策.

关键词:

深度学习是一种深度学习.检测胎儿异常的检测产前护理产前护理产前诊断在产前诊断.超声波成像的成像方法

更多相关视频

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

Published on: November 8, 2018

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

相关概念视频

Body Planes

Body Planes

Body planes in anatomy are imaginary flat surfaces used as reference points to divide the body into sections for anatomical study. These planes are essential for understanding the orientation, relationships, and spatial organization of anatomical structures.
The sagittal plane is the plane that divides the body or an organ vertically into right and left sides. If this vertical plane runs directly down the middle of the body resulting in equal division, it is called the midsagittal or median...