OBJECTIVE: A fully automatic multimodality image registration algorithm is presented. The method is primarily designed for 3D registration of MR and PET images of the brain. However, it has also been successfully applied to CT-PET, MR-CT, and MR-SPECT registrations. MATERIALS AND METHODS: The head contour is detected on the MR image using a gradient threshold method. The head region in the MR image is then segmented into a set of connected components using the K-means clustering algorithm. When the two image sets are registered, the segmentation of the MR image indirectly generates a segmentation of the PET image. The best registration is taken to be the one that optimizes the segmentation induced on the PET image. In this article, the K-means minimum variance criterion is used as a cost function, and the optimization is performed using the method of coordinate descent. RESULTS: The algorithm was tested on 80 H2 15O PET and MR image pairs from 10 subjects. Qualitatively correct results were obtained in all cases. With use of external markers visible in both image modalities, the average registration error was estimated to be < 3 mm. CONCLUSION: The algorithm presented in this article requires no user interaction and can be applied to a wide range of registration problems. Quantitative and qualitative evaluations of the algorithm indicate a high degree of accuracy.
OBJECTIVE: A fully automatic multimodality image registration algorithm is presented. The method is primarily designed for 3D registration of MR and PET images of the brain. However, it has also been successfully applied to CT-PET, MR-CT, and MR-SPECT registrations. MATERIALS AND METHODS: The head contour is detected on the MR image using a gradient threshold method. The head region in the MR image is then segmented into a set of connected components using the K-means clustering algorithm. When the two image sets are registered, the segmentation of the MR image indirectly generates a segmentation of the PET image. The best registration is taken to be the one that optimizes the segmentation induced on the PET image. In this article, the K-means minimum variance criterion is used as a cost function, and the optimization is performed using the method of coordinate descent. RESULTS: The algorithm was tested on 80 H2 15O PET and MR image pairs from 10 subjects. Qualitatively correct results were obtained in all cases. With use of external markers visible in both image modalities, the average registration error was estimated to be < 3 mm. CONCLUSION: The algorithm presented in this article requires no user interaction and can be applied to a wide range of registration problems. Quantitative and qualitative evaluations of the algorithm indicate a high degree of accuracy.
Authors: Dara G Ghahremani; Buyean Lee; Chelsea L Robertson; Golnaz Tabibnia; Andrew T Morgan; Natalie De Shetler; Amira K Brown; John R Monterosso; Adam R Aron; Mark A Mandelkern; Russell A Poldrack; Edythe D London Journal: J Neurosci Date: 2012-05-23 Impact factor: 6.167
Authors: Babak A Ardekani; Arthika Bappal; Debra D'Angelo; Manzar Ashtari; Todd Lencz; Philip R Szeszko; Pamela D Butler; Daniel C Javitt; Kelvin O Lim; Jan Hrabe; Jay Nierenberg; Craig A Branch; Matthew J Hoptman Journal: Neuroreport Date: 2005-09-08 Impact factor: 1.837
Authors: Elizabeth A Reynolds Losin; Marco Iacoboni; Alia Martin; Katy A Cross; Mirella Dapretto Journal: Neuroimage Date: 2011-10-28 Impact factor: 6.556
Authors: M F Falangola; B A Ardekani; S-P Lee; J S Babb; A Bogart; V V Dyakin; R Nixon; K Duff; J A Helpern Journal: J Neurosci Methods Date: 2004-12-07 Impact factor: 2.390
Authors: Swetasudha Panda; Andrew J Asman; Michael P Delisi; Louise A Mawn; Robert L Galloway; Bennett A Landman Journal: Proc SPIE Int Soc Opt Eng Date: 2014-03-21
Authors: Po Lai Yau; David Javier; Wai Tsui; Victoria Sweat; Hannah Bruehl; Joan C Borod; Antonio Convit Journal: Psychiatry Res Date: 2009-11-10 Impact factor: 3.222
Authors: Hilary Bertisch; Dawei Li; Matthew J Hoptman; Lynn E Delisi Journal: Am J Med Genet B Neuropsychiatr Genet Date: 2010-06-05 Impact factor: 3.568