Abstract
A three-dimensional multimodality medical image registration method using geometric invariant based on conformal geometric algebra (CGA) theory is put forward for responding to challenges resulting from many free degrees and computational burdens with 3D medical image registration problems. The mathematical model and calculation method of dual-vector projection invariant are established using the distribution characteristics of point cloud data and the point-to-plane distance-based measurement in CGA space. The translation operator and geometric rotation operator during registration operation are built in Clifford algebra (CA) space. The conformal geometrical algebra is used to realize the registration of 3D CT/MR-PD medical image data based on the dual vector geometric invariant. The registration experiment results indicate that the methodology proposed in this paper is of stronger commonality, less computation burden, shorter time consumption, and intuitive geometric meaning. Both subjective evaluation and objective indicators show that the methodology proposed here is of high registration accuracy and suitable for 3D medical image registration.
Highlights
Registration and fusion of medical images in different modalities are an important task in medical image processing, as it can be convenient for doctors to achieve treatment schedules, lesion locations, disease progress determination, and treatment assessment and provide more comprehensive information for understanding the process of medical image
The translation operator and geometric rotation operator during registration operation are built in Clifford algebra (CA) space
For intracranial 3D medical images, it has notable features: firstly, intracranial soft tissue is not deformed as it is protected by skull; as a result, whole image data can be viewed as a rigid body; secondly, intracranial image data is provided in distribution forms of sliced layers, and a three-dimensional can be rebuilt by stacking up these lamellar images in a fixed order
Summary
Registration and fusion of medical images in different modalities are an important task in medical image processing, as it can be convenient for doctors to achieve treatment schedules, lesion locations, disease progress determination, and treatment assessment and provide more comprehensive information for understanding the process of medical image. For intracranial 3D medical images (such as CT, MR, SPECT, and PET), it has notable features: firstly, intracranial soft tissue is not deformed as it is protected by skull; as a result, whole image data can be viewed as a rigid body; secondly, intracranial image data is provided in distribution forms of sliced layers, and a three-dimensional can be rebuilt by stacking up these lamellar images in a fixed order. Because of these two rezones described above, outer contour of different types of brain images for a patient has high degree of similarity. Experimental results show that the method presented here have characteristics of simple model, high execution efficiency, more intuitive geometric meaning, better registration performance, and not being easy to fall into the local extreme value
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have