RESUMEN
With the development of computer techniques and medical software in image analysis and visualization,medical image registration as a key step before image processing(e.g., image fusion)is important in research and medical diagnosis. Therefore, many studies have focused on medical registration methods and algorithms. Up to now, several registration methods have been applied in clinical practice. In this paper,we make a classification and analysis of registration methods clinically applied in radiotherapy. How to improve the accuracy,efficiency,and robustness of medical image registration remains an issue to be solved in the future.
RESUMEN
Objective: To correct the set-up error of patients during radiotherapy is very important for increasing treatment effective. Methods: This paper proposes a registration method based on portal images and reference images. Canny Operator was used to extract edge features. The extracted edge features were set as datum mark to calculate the maximal mutual information between the portal images and reference images. Parameters were optimized with simplex-simulated annealing optimization strategy. Results: The portal images and reference images of 29 patients with the cervix cancer and prostatic carcinoma were registrated in this paper. The results showed that the registration was precise, and the registration speed was increased remarkably. Conclusion: So this registration method can be applied for online estimation for set-up errors in clinical radiation.