Concatenated spatially-localized random forests for hippocampus labeling in adult and infant MR brain images

详细信息    查看全文

• 作者：Lichi Zhang^a ; ^b ; ^{lichizhang@sjtu.edu.cn}Author Vitae ; Qian Wang^a ; ^{wang.qian@sjtu.edu.cn}Author Vitae ; Yaozong Gao^b ; ^c ; ^{yzgao@cs.unc.edu}Author Vitae ; Hongxin Li^e ; ^{lhx3129@163.com}Author Vitae ; Guorong Wu^b ; ^{grwu@med.unc.edu}Author Vitae ; Dinggang Shen^b ; ^d ; ^{dgshen@med.unc.edu}Author Vitae
• 关键词：Image segmentation ; Random forest ; Brain MR images ; Atlas selection ; Clustering
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：15 March 2017
• 年：2017
• 卷：229
• 期：Complete
• 页码：3-12
• 全文大小：1511 K
• 卷排序：229

文摘

Automatic labeling of the hippocampus in brain MR images is highly demanded, as it has played an important role in imaging-based brain studies. However, accurate labeling of the hippocampus is still challenging, partially due to the ambiguous intensity boundary between the hippocampus and surrounding anatomies. In this paper, we propose a concatenated set of spatially-localized random forests for multi-atlas-based hippocampus labeling of adult/infant brain MR images. The contribution in our work is two-fold. First, each forest classifier is trained to label just a specific sub-region of the hippocampus, thus enhancing the labeling accuracy. Second, a novel forest selection strategy is proposed, such that each voxel in the test image can automatically select a set of optimal forests, and then dynamically fuses their respective outputs for determining the final label. Furthermore, we enhance the spatially-localized random forests with the aid of the auto-context strategy. In this way, our proposed learning framework can gradually refine the tentative labeling result for better performance. Experiments show that, regarding the large datasets of both adult and infant brain MR images, our method owns satisfactory scalability by segmenting the hippocampus accurately and efficiently.