Non-rigid registration of medical images using a hierarchical framework with normalized mutual information

Abstract

Medical image registration plays a crucial role in medical field. Existing medical registration methods can be categorized as rigid registration and non-rigid registration methods. Compared with rigid registration, the non-rigid registration is more suitable for representing the anatomy's complicated deformation. In this study, we develop a non-rigid registration method in which Normalized Mutual Information (NMI) is used as similarity measurement and B-splines are used for transformation. The algorithm is implemented using a hierarchical framework such that the accuracy of registration is improved by the coarse-to-fine registration schema. Experiments demonstrate that the proposed method produces more accurate results than the affine and demons methods in registration of pelvis CBCT images, which provides an alternative approach to support non-rigid registration of medical images with intensity variation. The proposed algorithm shows potential for facilitating image-guided radiation therapy with higher treatment dose delivered to a precise location through the use of image registration.

Semantic segmentation of remote sensing images based on dual‐channel attention mechanism

“…However, in terms of overall segmentation effect and accuracy of details, the U-Net+DCAM algorithm proposed in this paper outperforms other models and is closer to the actual label values. In order to verify the precise performance of DeepLab V3, SETR, DAnet, OCnet, CCnet, and U-Net+DCAM semantic segmentation algorithms, we analyzed the experimental results using four objective indicators: Pixel Accuracy (PA), Mean Pixel Accuracy (MPA), Mean Intersection over Union (MIOU), and Kappa [24,25].…”