Optimal embedding for shape indexing in medical image databases. Academic Article

abstract

• Fast retrieval using organ shapes is crucial in medical image databases since shape is a clinically prominent feature. In this paper, we propose that 2-D shapes in medical image databases can be indexed by embedding them into a vector space and using efficient vector space indexing. An optimal shape space embedding is proposed for this purpose. Experimental results of indexing vertebral shapes in the NHANES II database are presented. The results show that vector space indexing following embedding gives superior performance than metric indexing.

authors

• Qian, Xiaoning

published proceedings

• Med Image Comput Comput Assist Interv

author list (cited authors)

• Qian, X., & Tagare, H. D.

citation count

• 7

complete list of authors

• Qian, Xiaoning||Tagare, Hemant D

publication date

• January 2005

publisher

• Springer Nature  Publisher

published in

• Lecture Notes in Computer Science  Journal

keywords

• Databases, Factual
• Documentation
• Humans
• Medical Records Systems, Computerized
• Radiographic Image Interpretation, Computer-Assisted
• Radiology Information Systems
• Spinal Osteophytosis

PubMed Central ID

• 16685982

Digital Object Identifier (DOI)

• 10.1007/11566489_47

start page

• 377

end page

• 384

volume

• 8

issue

• Pt 2