Zhang Jiaju, Fu Tianyu, Wang Yuanyuan, Li Jingshu, Xiao Deqiang, Fan Jingfan, Lin Yucong, Song Hong, Ji Fei, Yang Meng, Yang Jian
Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Electronics, Beijing Institute of Technology, Beijing 100081, People's Republic of China.
School of Medical Technology, Beijng Institute of Technology, Beijing 100081, People's Republic of China.
Phys Med Biol. 2023 Jul 7;68(14). doi: 10.1088/1361-6560/ace098.
3D ultrasound non-rigid registration is significant for intraoperative motion compensation. Nevertheless, distorted textures in the registered image due to the poor image quality and low signal-to-noise ratio of ultrasound images reduce the accuracy and efficiency of the existing methods.A novel 3D ultrasound non-rigid registration objective function with texture and content constraints in both image space and multiscale feature space based on an unsupervised generative adversarial network based registration framework is proposed to eliminate distorted textures. A similarity metric in the image space is formulated based on combining self-structural constraint with intensity to strengthen the robustness to abnormal intensity change compared with common intensity-based metrics. The proposed framework takes two discriminators as feature extractors to formulate the texture and content similarity between the registered image and the fixed image in the multiscale feature space respectively. A distinctive alternating training strategy is established to jointly optimize the combination of various similarity loss functions to overcome the difficulty and instability of training convergence and balance the training of generator and discriminators.Compared with five registration methods, the proposed method is evaluated both with small and large deformations, and achieves the best registration accuracy with average target registration error of 1.089 mm and 2.139 mm in cases of small and large deformations, respectively. The performance on peak signal to noise ratio (PSNR) and structural similarity (SSIM) also proves the effective constraints on distorted textures of the proposed method (PSNR is 31.693 dB and SSIM is 0.9 in the case of small deformation; PSNR is 28.177 dB and SSIM is 0.853 in the case of large deformation).The proposed 3D ultrasound non-rigid registration method based on texture and content constraints with the distinctive alternating training strategy can eliminate the distorted textures with improving the registration accuracy.
三维超声非刚性配准对于术中运动补偿具有重要意义。然而，由于超声图像质量差和信噪比低，配准图像中会出现纹理失真，这降低了现有方法的准确性和效率。基于无监督生成对抗网络的配准框架，提出了一种在图像空间和多尺度特征空间中具有纹理和内容约束的新型三维超声非刚性配准目标函数，以消除纹理失真。基于自结构约束与强度相结合，在图像空间中制定了一种相似性度量，与常见的基于强度的度量相比，增强了对异常强度变化的鲁棒性。所提出的框架采用两个鉴别器作为特征提取器，分别在多尺度特征空间中制定配准图像与固定图像之间的纹理和内容相似性。建立了一种独特的交替训练策略，以联合优化各种相似性损失函数的组合，克服训练收敛的困难和不稳定性，并平衡生成器和鉴别器的训练。与五种配准方法相比，所提出的方法在小变形和大变形情况下均进行了评估，在小变形和大变形情况下分别实现了最佳的配准精度，平均目标配准误差分别为1.089毫米和2.139毫米。在峰值信噪比（PSNR）和结构相似性（SSIM）方面的性能也证明了所提出方法对失真纹理的有效约束（小变形情况下PSNR为31.693 dB，SSIM为0.9；大变形情况下PSNR为28.177 dB，SSIM为0.853）。所提出的基于纹理和内容约束以及独特交替训练策略的三维超声非刚性配准方法能够消除失真纹理并提高配准精度。
