Volume 16, Issue 1 (Spring 2014)
Advances in Cognitive Sciences 2014, 16(1): 11-20 |
Back to browse issues page
1- Department of Electrical Engineering, Faculty of Engineering, Arak University, Arak, Iran.
2- Professor, Biomedical Engineering Department, Faculty of Electrical & Computer Engineering, K.N Toosi University of Technology, Tehran, Iran.
3- Professor, GRAMFC Inserm U1105, Faculty of Medicine, University of Picardie Jules Verne, Amiens, France
4- Professor, Neuroradiology Unit, Amiens University Hospital, Amiens, France.
2- Professor, Biomedical Engineering Department, Faculty of Electrical & Computer Engineering, K.N Toosi University of Technology, Tehran, Iran.
3- Professor, GRAMFC Inserm U1105, Faculty of Medicine, University of Picardie Jules Verne, Amiens, France
4- Professor, Neuroradiology Unit, Amiens University Hospital, Amiens, France.
Abstract: (2289 Views)
Introduction: Quantification of the neonatal brain development has a significant role in understanding, prevention, diagnosis and treatment of nervous system diseases during infancy. Since brain development and the its corresponding morphological changes are very fast during the first days after birth, an age-related brain atlas representing fine anatomical features of a neonatal brain is deemed necessary.
Method: We constructed two neonatal brain atlases for the age ranges of 39-40 and 41-42 weeks of gestation, using 16 T1-weighted magnetic resonance images (MRI) through an improved group-wise registration paradigm.
Results: Neonatal images were normalized to the newly created and previously available neonatal atlases. The similarity between these atlases and normalized images were calculated via mutual information. The mean mutual information between normalized images and the new atlases using proposed algorithm was considered optimal.
Conclusion: This result confirms the greater similarity between normalized images and the atlases created through group-wise registrations of features retrieved from MRI
Method: We constructed two neonatal brain atlases for the age ranges of 39-40 and 41-42 weeks of gestation, using 16 T1-weighted magnetic resonance images (MRI) through an improved group-wise registration paradigm.
Results: Neonatal images were normalized to the newly created and previously available neonatal atlases. The similarity between these atlases and normalized images were calculated via mutual information. The mean mutual information between normalized images and the new atlases using proposed algorithm was considered optimal.
Conclusion: This result confirms the greater similarity between normalized images and the atlases created through group-wise registrations of features retrieved from MRI
Keywords: Neonatal Brain Atlas, Morphological Brain Development Analysis, Group-Wise Registration, Magnetic Resonance Imaging
Type of Study: Research |
Subject:
Special
Received: 2013/07/16 | Accepted: 2014/01/15 | Published: 2014/04/14
Received: 2013/07/16 | Accepted: 2014/01/15 | Published: 2014/04/14
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |