Abstract
The PET and CT fusion image, combining the anatomical and functional information, has important clinical meaning. An effective registration of PET and CT images is the basis of image fusion. This paper presents a multithread registration method based on contour point cloud for 3D whole-body PET and CT images. Firstly, a geometric feature-based segmentation (GFS) method and a dynamic threshold denoising (DTD) method are creatively proposed to preprocess CT and PET images, respectively. Next, a new automated trunk slices extraction method is presented for extracting feature point clouds. Finally, the multithread Iterative Closet Point is adopted to drive an affine transform. We compare our method with a multiresolution registration method based on Mattes Mutual Information on 13 pairs (246~286 slices per pair) of 3D whole-body PET and CT data. Experimental results demonstrate the registration effectiveness of our method with lower negative normalization correlation (NC = −0.933) on feature images and less Euclidean distance error (ED = 2.826) on landmark points, outperforming the source data (NC = −0.496, ED = 25.847) and the compared method (NC = −0.614, ED = 16.085). Moreover, our method is about ten times faster than the compared one.
Highlights
The fusion image of Positron Emission Tomography (PET) and Computed Tomography (CT) provides the functional and metabolic information, which could help medical diagnosis, treatment planning, and evaluation [1, 2]
To address the challenges and requirements mentioned above with considerable accuracy and efficiency, this paper proposed a multithread registration solution based on contour point cloud for PET and CT images
The speed and the accuracy are the main factors to evaluate the performance of a registration method [5]
Summary
The fusion image of Positron Emission Tomography (PET) and Computed Tomography (CT) provides the functional and metabolic information, which could help medical diagnosis, treatment planning, and evaluation [1, 2]. It is necessary to find an efficient and accurate registration method to improve the correspondence between PET and CT images before fusion, which is of great significance to clinical diagnosis and treatment [3, 4]. Image registration is the process of aligning one image (moving image) to another image (fixed image) by finding a transformation that maximizes the similarity metric between the transformed moving image and the fixed image [5]. There are many methods proposed in the field of image registration. They are generally classified into two categories: intensity-based and featurebased methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
