相关实验视频
Updated: Jul 19, 2025

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
Published on: November 23, 2019
对于2D/3D注册和投射空间变压器的完全可区分的框架
这项研究引入了一个深度学习框架,使用了一个新的投射空间变压器 (ProST) 模块来提高2D/3D图像注册精度和手术指导的捕获范围. ProST网络显著增强了传统方法,在现实应用中实现了更高的成功率.
科学领域:
- 医疗成像医学成像
- 计算机视觉 计算机视觉
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 2D/3D图像注册对于图像引导手术至关重要.
- 由于相似性函数中的局部最小值,传统方法的捕获范围有限.
研究的目的:
- 使用可差分的深度网络扩展2D/3D注册的捕获范围.
- 开发一个新的投射空间变压器 (ProST) 模块,以改进姿势估计.
主要方法:
- 开发了一个完全可差异化的深度网络框架.
- 该网络包含一个投射空间变压器 (ProST) 模块,具有独特的3D姿势参数可区分能力.
- 训练使用了双反向梯度驱动的损失函数.
主要成果:
- ProST网络学习了一个实用的相似性函数,显著扩大了注册捕获范围.
- 对于骨盆解剖学,ProST跟随CMAES在模拟中实现了4.4mm (65.6%SR) 的中位数TRE,在真实数据中达到2.2mm (73.2%SR).
- 这比单独CMAES (28.5%和36.0%SRs) 显著改善.
结论:
- 拟议的ProST网络有效地提高了基于强度的2D/3D注册的捕获范围.
- ProST的独特可区分性显示了在3D医学成像研究中更广泛应用的潜力.
更多相关视频
07:13Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
Published on: October 27, 2023
02:09Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
Published on: April 12, 2024
相关概念视频
Vector Transformation in Rotating Coordinate Systems
Transformation of Plane Strain
Under plane strain conditions, typical for members where one dimension significantly exceeds the others, deformations and resultant strains are...
Transformation
Transformers with Off-Nominal Turns Ratios
Relative Motion Analysis using Rotating Axes
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it...
Forced Transdifferentiation
Artificial...