Title :
Investigation and evaluation of optimal registration for medical CT images
Author :
Ying Jin ; Guangsheng Ma
Author_Institution :
Sch. of Comput. Sci. & Technol., Harbin Eng. Univ., Harbin, China
Abstract :
Due to its capability of maximizing the embedded information from a large amount of medical images captured from different imaging modalities and acquired from different scanning intervals, medical image registration plays an essential role in clinical applications including diagnosis, radiotherapy planning, assessment of patient´s response to the treatment. An intensive research on registration methodologies has been conducted during the last three decades. However, by far there is no general software solution to clinically acceptable registration. To sort out more appropriate registration for clinical CT images, in this paper, the-state-of-the-art registration methods were tested and compared. In particular, the multiresolution deformable registration was investigated for accommodating a wider range of deformations. Our experimental results on the clinical CT datasets demonstrated the superior performance of the B-spline deformable registration by multiresolution scheme.
Keywords :
computerised tomography; image registration; image resolution; medical image processing; patient treatment; splines (mathematics); B-spline deformable registration; medical CT images; medical diagnosis; medical image registration; medical radiotherapy planning; multiresolution deformable image registration; patient treatment response assessment; Biomedical imaging; Computed tomography; Image registration; Optimization; Spatial resolution; Spline; deformable registration; medical image; multiresolution; mutual information; optimization;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5647407