Biomedical Information from a National Collection of Spine X-Rays: Film to Content-Based Retrieval

Long LR, Antani S, Lee DJ, Krainak DM, Thoma GR
Proc. of SPIE Medical Imaging: PACS and Integrated Medical Information Systems. 2003 Feb;5033: 70-84.

We summarize research and development for the extraction and distribution of biomedical information from a collection of 17,000 spine x-ray images collected by the second National Health and Nutrition Examination Survey (NHANES II). We present a history of the technical milestones of this work, including the data collection as film, digitization, quality control, archiving technology, database organization, medical expert content evaluation, and Web data distribution. We conclude by presenting our current work in content-based image retrieval (CBIR) to exploit the information content of these images directly by using image processing. We provide an overview and current research results from this CBIR work, which includes: extensive segmentation research, focusing on Active Shape Modeling and Active Contour methods; alternative techniques for shape representation, including invariant moments, simple polygon approximation, and Fourier descriptors; neural network classification of shapes into biomedical categories, such as “anterior osteophytes present/not present”; and the implementation of a prototype CBIR system for the vertebrae that supports hybrid text/image queries using MATLAB and the MySQL relational database system.