Aggarwal Vivek, Gupta Anupama
Department of Mechanical Engineering, I. K. Gujral Punjab Technical University, Main Campus, Kapurthala-144603, Punjab, India.
Department of Computer Science and Engineering, Giani Zail Singh Campus College of Engineering and Technology, Maharaja Ranjit Singh Punjab Technical University, Bathinda-151001, Punjab, India.
Curr Med Imaging Rev. 2019;15(3):292-300. doi: 10.2174/1573405614666180103163430.
Medical images are widely used within healthcare and medical research. There is an increased interest in precisely correlating information in these images through registration techniques for investigative and therapeutic purposes. This work proposes and evaluates an improved measure function for registration of carotid ultrasound and magnetic resonance images (MRI) taken at different times.
To achieve this, a morphological edge detection operator has been designed to extract the vital edge information from images which is integrated with the Mutual Information (MI) to carry out the registration process. The improved performance of proposed registration measure function is demonstrated using four quality metrics: Correlation Coefficient (CC), Structural Similarity Index (SSIM), Visual Information Fidelity (VIF) and Gradient Magnitude Similarity Deviation (GMSD). The qualitative validation has also been done through visual inspection of the registered image pairs by clinical radiologists.
The experimental results showed that the proposed method outperformed the existing method (based on integrated MI and standard edge detection) for both ultrasound and MR images in terms of CC by about 4.67%, SSIM by 3.21%, VIF by 18.5%, and decreased GMSD by 37.01%. Whereas, in comparison to the standard MI based method, the proposed method has increased CC by 16.29%, SSIM by 16.13%, VIF by 52.56% and decreased GMSD by 66.06%, approximately.
Thus, the proposed method improves the registration accuracy when the original images are corrupted by noise, have low intensity values or missing data.
医学图像在医疗保健和医学研究中被广泛使用。人们越来越有兴趣通过配准技术精确关联这些图像中的信息，以用于研究和治疗目的。这项工作提出并评估了一种改进的测量函数，用于对不同时间获取的颈动脉超声和磁共振图像（MRI）进行配准。
为实现这一目标，设计了一种形态学边缘检测算子，从图像中提取重要的边缘信息，并将其与互信息（MI）相结合以进行配准过程。使用四个质量指标来证明所提出的配准测量函数的改进性能：相关系数（CC）、结构相似性指数（SSIM）、视觉信息保真度（VIF）和梯度幅度相似性偏差（GMSD）。还通过临床放射科医生对配准后的图像对进行目视检查来进行定性验证。
实验结果表明，对于超声图像和MR图像，所提出的方法在CC方面比现有方法（基于集成MI和标准边缘检测）高出约4.67%，SSIM高出3.21%，VIF高出18.5%，GMSD降低了37.01%。而与基于标准MI的方法相比，所提出的方法的CC提高了约- 16.29%，SSIM提高了16.13%，VIF提高了52.56%，GMSD降低了66.06%。
因此，当原始图像受到噪声干扰、强度值较低或存在数据缺失时，所提出的方法提高了配准精度。
