DocumentCode :
1808895
Title :
Fast Fusion of Medical Images Based on Bayesian Risk Minimization and Pixon Map
Author :
Zhou, Hongbo ; Cheng, Qiang ; Zargham, Mehdi
Author_Institution :
Southern Illinois Univ., Carbondale, IL, USA
Volume :
2
fYear :
2009
fDate :
29-31 Aug. 2009
Firstpage :
1086
Lastpage :
1091
Abstract :
Fast fusion of multiple registered out-of-focus images is of great interest in medical imaging; for example, the thoracic cavity is always too bumpy to be focused on all parts at one shot even when we can omit the unavoidable hardware vibrations. Previous proposed methods in this field cannot fulfill the real-time requirement in our multiple camera medical imaging setting. In this paper, we propose a multiresolution Bayesian risk minimization based method to fuse these chest cavity images. The validity and efficiency of our method are verified by our experiments on both out-of-focus medical images and regional motion blurred images. By choosing special kernel functions for the Pixon map and adopting uniform distribution as the prior probability, our method can be applied to the real-time medical imaging situations such as surgical operation monitoring.
Keywords :
Bayes methods; image fusion; image resolution; medical image processing; minimisation; Pixon map; chest cavity image fusion; kernel function; medical images fast fusion; multiple camera medical imaging setting; multiple registered out-of-focus image; multiresolution Bayesian risk minimization; regional motion blurred image; surgical operation monitoring; thoracic cavity; unavoidable hardware vibration; uniform distribution; Bayesian methods; Biomedical imaging; Biomedical monitoring; Cameras; Fuses; Hardware; Image resolution; Kernel; Risk management; Surgery; Bayesian risk minimization; Pixon map; real-time image fusion; surgical operation monitoring;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Science and Engineering, 2009. CSE '09. International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
978-1-4244-5334-4
Electronic_ISBN :
978-0-7695-3823-5
Type :
conf
DOI :
10.1109/CSE.2009.59
Filename :
5283469
Link To Document :
بازگشت