Abstract:
Medical image registration can quantify disease progression, study longitudinal and cross-sectional data, and guide computer-assisted diagnosis and treatment. Deformable registration for retinal optical coherence tomography (OCT) images is not well developed. This paper proposes OCTRexpert, a retinal OCT 3D registration method.
To our knowledge, the proposed algorithm is the first full 3D registration approach for retinal OCT images that can be applied to longitudinal OCT images for normal and serious pathological subjects. A pre-processing method removes eye motion artifact, followed by a novel design-detection-deformation strategy for registration.
Each image voxel is given two features during design. The detection step selects active voxels and establishes point-to-point correspondences between subject and template images. According to multi-resolution correspondences, the image is hierarchically deformed.
The proposed method is tested on longitudinal OCT images from 20 healthy subjects and 4 serious Choroidal Neovascularization (CNV) patients. The proposed registration algorithm consistently improves Dice similarity coefficient and average unsigned surface error over other registration methods.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
