Automated segmentation and area estimation of neural foramina with boundary regression model

详细信息    查看全文

• 作者：Xiaoxu He^a ; ^b ; ^{xhe244@uwo.ca}Author Vitae ; Andrea Lum^a ; ^bAuthor Vitae ; Manas Sharma^a ; ^bAuthor Vitae ; Gary Brahm^a ; ^bAuthor Vitae ; Ashley Mercado^a ; ^bAuthor Vitae ; Shuo Li^a ; ^b ; ^{slishuo@gmail.com}Author Vitae
• 关键词：Automated segmentation ; Area estimation ; Neural foramina stenosis ; Boundary regression model ; Multiple output support vector regression ; Multiple kernel learning
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：63
• 期：Complete
• 页码：625-641
• 全文大小：4596 K
• 卷排序：63

文摘

Application: it firstly achieved a fully automated and multi-modal segmentation tool for clinical diagnosis of NFS. Approach: it creatively formulated segmentation as boundary regression to leverage machine learning in a holistic way. Methodology: it proposed a highly nonlinear multi-kernel multi-output SVR to seamlessly combine MSVR and MKL together.