Digital hand atlas and web-based bone age assessment: system design and implementation

Citation
F. Cao et al., Digital hand atlas and web-based bone age assessment: system design and implementation, COMP MED IM, 24(5), 2000, pp. 297-307
Citations number
25
Categorie Soggetti
Radiology ,Nuclear Medicine & Imaging
Journal title
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
ISSN journal
08956111 → ACNP
Volume
24
Issue
5
Year of publication
2000
Pages
297 - 307
Database
ISI
SICI code
0895-6111(200009/10)24:5<297:DHAAWB>2.0.ZU;2-1
Abstract
Bone age assessment is a procedure frequently performed in pediatric patien ts to evaluate their growth disorder. A simple method commonly used in bone age assessment is atlas matching by a radiological examination of a left-h and radiograph against a small reference set of Greulich-Pyle atlas pattern s of normal standards. The method however can lead to significant deviation in age assessment, due to a variety of observers with different levels of training. The Greulich-Pyle atlas developed in the 1950s based on middle up per class white populations, is also not fully applicable for children of t oday, especially regarding the standard development in other racial groups. In this paper, we present our system design and initial implementation of a digital hand atlas and computer-aided diagnostic (CAD) system for Web-base d bone age assessment. The CAD system is built on top of existing picture a rchiving and communication system (PACS), as well as recent advances in Int ernet technology. It consists of a hand atlas database, a CAD module and a Java-based Web user interface. The digital atlas is based on a large new se t of clinically normal hand images of diverse ethnic groups. A relational i mage database system is used to organize hand images, their extracted quant itative features and patient data. The digital atlas removes the disadvanta ges of the currently out-of-date Greulich-Pyle atlas and allows the bone ag e assessment to be computerized. The Java-based Web user interface allows u sers to interact with the hand image database from browsers. Users can use a Web browser to push a clinical hand image to the CAD server for a bone ag e assessment. Quantitative features on the examined image, which reflect th e skeletal maturity, are then extracted and compared with patterns from the atlas database to assess the bone age. The digital atlas method based on o pen system Internet technology provides an alternative to supplement or rep lace the traditional one for a quantitative, accurate and cost-effective as sessment of bone age. (C) 2000 published by Elsevier Science Ltd.