摘要
2D-3D医学图像配准在解决放射治疗的摆位验证问题上发挥着至关重要的作用。针对现有配准方法精度不高、耗时较长等问题,提出一种基于训练-推理解耦架构的2D-3D医学图像配准方法。该方法在训练阶段采用多分支结构,利用多尺度卷积增强特征多样性,提高配准精度;在推理阶段,利用重参数化将多分支结构转换为单路结构,加快配准速度;另外,引入自适应激活函数Meta-ACON,提高网络的非线性表达能力。在胸部和骨盆两个数据集上进行训练和测试,实验结果表明,所提方法预测结果的位移误差约为0.08 mm,角度误差约为0.05°,配准时间仅需26 ms。所提方法有效解决了摆位验证中的医学图像配准问题,不仅提高了精度,还满足了临床实时性要求。
The registration of 2D-3D medical images is crucial in solving radiotherapy positioning verification.A 2D-3D medical image registration approach based on training-inference decoupling architecture is proposed to address the issues of low accuracy and time-consuming processes.The multibranch structure and multiscale convolution were employed in the training phase to enhance feature diversity and improve registration accuracy.During the inference phase,the multibranch structure was reparameterized into a single-channel structure to speed up the registration speed.Additionally,an adaptive activation function,Meta-ACON,was used to increase the network’s nonlinear expression.Two datasets of the chest and pelvis were used for training and testing.The experimental results show that the mean translation error of the proposed method is approximately0.08 mm,the mean angular error is approximately 0.05°,and the registration time reaches 26 ms.The proposed method significantly improves the accuracy of medical image registration in positioning verification while meeting the real-time requirements of clinical applications.
作者
李文举
孔德卿
曹国刚
李思诚
戴翠霞
Li Wenjü;Kong Deqing;Cao Guogang;Li Sicheng;Dai Cuixia(School of Computer Science&Information Engineering,Shanghai Institute of Technology,Shanghai 201418,China;School of Sciences,Shanghai Institute of Technology,Shanghai 201418,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第16期207-216,共10页
Laser & Optoelectronics Progress
基金
国家自然科学基金(62175156,61675134,81827807)
上海市科委科技创新行动计划(19441905800)
温州医科大学重点实验室开放项目(K181002)。
关键词
图像处理
2D-3D配准
卷积神经网络
重参数化
激活函数
image processing
2D-3D registration
convolution neural network
re-parameterization
activate function
