Automatic correspondence using the enhanced hexagonal centre-based inner search algorithm for point-based dental image registration

• Published in: Dento-maxillo-facial radiology 2008-05, Vol.37 (4), p.185-204
• Main Authors: Economopoulos, T, Matsopoulos, G K, Asvestas, P A, Gröndahl, K, Gröndahl, H-G
• Format: Article
• Language: English
• Subjects: Algorithms; Alveolar Bone Loss - diagnostic imaging; Animals; Dental Implants; Dentistry; Dogs; Humans; Image Processing, Computer-Assisted - methods; Mandible - diagnostic imaging; Neural Networks (Computer); Pattern Recognition, Automated - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Radiography, Dental; Radiography, Dental, Digital; Subtraction Technique
• ISSN: 0250-832X; 1476-542X
• DOI: 10.1259/dmfr/26553364

In this paper, the enhanced hexagonal centre-based inner search (EHCBIS) algorithm, for automatic point correspondence, is proposed for dental image registration. The presented algorithm is incorporated within a general registration scheme, which is based on extracting a set of candidate points on the reference image, finding their corresponding points in the image to be transformed (float image) using the proposed algorithm and applying a suitable geometrical transformation towards automatic registration. The performance of the proposed algorithm is evaluated against three well-known methods for automatic correspondence, the self-organizing maps, the automatic extraction of corresponding points and the trimmed iterative closest point method, in terms of registration accuracy. Qualitative and quantitative results on registering 123 dental pairs show that the proposed algorithm outperforms the other methods for automatic correspondence with or without the presence of noise. The EHCBIS method is capable of defining automatically corresponding points in dental image pairs. It can be incorporated within a general scheme for point-based registration of dental radiographs acquired with or without rigorous a priori standardization. The applied projective transformation provides a reliable model for registering intraoral radiographs. The methodology does not require any segmentation prior to alignment providing subtraction radiographs and fused images for clinical evaluation regarding the evolution of a disease or the response to a therapeutic scheme.