相关实验视频

Updated: Jun 14, 2025

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

超高分辨率地标检测网络用于医疗图像

Runshi Zhang¹, Hao Mo¹, Weini Hu²

¹School of Mechanical Engineering and Automation, Beihang University, 37 Xueyuan Road, Haidian District, 100191, Beijing, China.

Computers in biology and medicine

|September 5, 2024

概括

超分辨率方法在计算机辅助手术中显著提高了额面 (CMF) 和鼻地标检测准确度. 新的网络,SRLD-Net和SR-UNet,减少图像下采样和上采样中的错误,以实现更精确的医学成像分析.

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
机器学习机器学习

背景情况:

上面 (CMF) 和鼻地标检测对于计算机辅助手术至关重要.
目前基于热图的方法因图像下采样和上采样而与子像素位置错误作斗争.
以前涉及HR补丁和多阶段任务的方法可能会影响准确性.

研究的目的:

引入新的超高分辨率网络,以减少地标检测错误.
为了提高基于热图的医疗里程碑检测的准确性.
增强表达式学习能力,用于精确的特征提取.

主要方法:

提出了两个超分辨率网络:标准超分辨率地标检测网络 (SRLD-Net) 和超分辨率UNet (SR-UNet).
在SRLD-Net中包含了金字塔聚合,金字塔融合和超分辨率的融合块.
SR-UNet使用Pyramid聚合和超分辨率块,加上超分辨率的上采样层,用于详细的热图生成.

主要成果:

拟议的SRLD-Net和SR-UNet在CMF,鼻和下的骨数据集上表现出优异的性能,相比于最先进的方法.
在18个CMF标志上获得的平均误差为1.39 ± 1.04毫米,在6个鼻标志上获得的平均误差为1.31 ± 1.09毫米,在14个下标志上获得的平均误差为2.01 ± 4.33毫米.
超分辨率方法有效地减少了传统下采样和上采样过程中固有的网络错误.

结论:

超分辨率技术为推进医学里程碑检测提供了重大潜力.
拟议的SRLD-Net和SR-UNet为CMF和鼻地标检测提供了基于热图的有效解决方案.
该研究通过改进地标定位精度,为计算机辅助手术提供了宝贵的贡献.

关键词:

头骨,大和面部外科手术基于热图的方法方法医疗里程碑检测检测的医学里程碑检测鼻腔外科手术鼻腔外科手术超级分辨率的超级分辨率

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

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

相关概念视频

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...