Zhou Lu, Zhen Xin, Lu Wenting, Dou Jianhong, Zhou Linghong
School of Biomedical Engineering, Southern Medical University, Guangzhou, China.
Nan Fang Yi Ke Da Xue Xue Bao. 2012 Jan;32(1):40-5.
To validate the efficiency of an improved Demons deformable registration algorithm and evaluate its application in registration of the treatment image and the planning image in image-guided radiotherapy (IGRT).
Based on Brox's gradient constancy assumption and Malis's efficient second-order minimization algorithm, a grey value gradient similarity term was added into the original energy function, and a formula was derived to calculate the update of transformation field. The limited Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm was used to optimize the energy function for automatic determination of the iteration number. The proposed algorithm was validated using mathematically deformed images, physically deformed phantom images and clinical tumor images.
Compared with the original Additive Demons algorithm, the improved Demons algorithm achieved a higher precision and a faster convergence speed.
Due to the influence of different scanning conditions in fractionated radiation, the density range of the treatment image and the planning image may be different. The improved Demons algorithm can achieve faster and more accurate radiotherapy.
验证改进的Demons可变形配准算法的有效性，并评估其在图像引导放射治疗（IGRT）中治疗图像与计划图像配准中的应用。
基于Brox的梯度恒常性假设和Malis的高效二阶最小化算法，在原始能量函数中添加灰度值梯度相似性项，并推导了计算变换场更新的公式。采用有限的布罗伊登-弗莱彻-戈德法布-肖诺（L-BFGS）算法优化能量函数以自动确定迭代次数。使用数学变形图像、物理变形体模图像和临床肿瘤图像对所提出的算法进行验证。
与原始的加法Demons算法相比，改进后的Demons算法具有更高的精度和更快的收敛速度。
由于分次放疗中不同扫描条件的影响，治疗图像和计划图像的密度范围可能不同。改进后的Demons算法可实现更快、更精确的放射治疗。
