RSNA 2003 

Abstract Archives of the RSNA, 2003


537-p

Computer-aided Assessment of Pediatric Skeletal Age

Scientific Posters

Presented on December 3, 2003
Presented as part of L13: Pediatric Pediatric Musculoskeletal

Participants

Yongguo Zhao PhD, PRESENTER: Nothing to Disclose

Abstract: HTML Purpose: Skeletal or bone age assessment by a radiological examination of a hand and wrist image is a frequently performed procedure in the pediatric radiology. To estimate the skeletal age, visual methods are used which are highly physician dependent and time-consuming. In order to overcome these disadvantages, various computer-aided skeletal assessments are being developed. In this paper, a computer based system for skeletal age assessment is presented. The performance of such a system was compared with the traditional visual methods. Method and Material Our approach to develop such a system was divided into several stages. At the initial stage, a semi-automatic program was developed. Digitized hand and wrist radiographs were input into such a system and visually compared with the standard atlas, radiographs and text information in the knowledge database by the physician. Three standards for estimating the skeletal age were provided by the system, including the Greulich and Pyle (G-P) atlas, the Tanner-Whitehouse II (TW2) method, and the Chinese (CHN) scoring method that is the national standard in assessing the skeletal age of Chinese children. The individual and total bone scores were automatically calculated by the computer and a value of skeletal age was given by the program. Results The system was tested on 39 pediatric hand images obtained from our clinical picture archiving and communication system (PACS) by two radiologists. Patient age ranges from 2 - 17 years. It recorded improved accuracy and time saving. Conclusion With accurate and robust results, the computer-aided system for the assessment of pediatric skeletal age has been proven as a useful tool for routine applications in pediatric endocrinology and radiology. In the next stage, we are developing a full automatic system for assessing skeletal age using techniques of image segmentation and pattern recognition.       Questions about this event email: telemedzy@yahoo.com

Cite This Abstract

Zhao PhD, Y, Computer-aided Assessment of Pediatric Skeletal Age.  Radiological Society of North America 2003 Scientific Assembly and Annual Meeting, November 30 - December 5, 2003 ,Chicago IL. http://archive.rsna.org/2003/3108972.html