Scalable joint segmentation and registration framework for infant brain images

详细信息    查看全文

• 作者：Pei Dong^aAuthor Vitae ; Li Wang^aAuthor Vitae ; Weili Lin^aAuthor Vitae ; Dinggang Shen^a ; ^b ; ^{dgshen@med.unc.edu}Author Vitae ; Guorong Wu^a ; ^{grwu@med.unc.edu}Author Vitae
• 关键词：Joint segmentation and registration ; Multi-atlas patch based label fusion ; Longitudinal growth trajectory ; Infant brain MR images
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：15 March 2017
• 年：2017
• 卷：229
• 期：Complete
• 页码：54-62
• 全文大小：1181 K
• 卷排序：229

文摘

We developed an efficient approach to deal with the tissue segmentation and registration for the infant brain MR images. Our proposed framework is scalable to various registration tasks in early brain development studies. Promising results have been achieved for infant brain MR images aged from 2-week-old to 1-year-old. The proposed technique can be very useful for many ongoing early brain development studies.