THE USE OF A COMPUTERIZED BRAIN ATLAS TO SUPPORT KNOWLEDGE-BASED TRAINING IN RADIOLOGY

Citation
S. Garlatti et M. Sharples, THE USE OF A COMPUTERIZED BRAIN ATLAS TO SUPPORT KNOWLEDGE-BASED TRAINING IN RADIOLOGY, Artificial intelligence in medicine, 13(3), 1998, pp. 181-205
Citations number
71
Categorie Soggetti
Computer Science Artificial Intelligence","Engineering, Biomedical","Computer Science Artificial Intelligence","Medical Informatics
ISSN journal
09333657
Volume
13
Issue
3
Year of publication
1998
Pages
181 - 205
Database
ISI
SICI code
0933-3657(1998)13:3<181:TUOACB>2.0.ZU;2-8
Abstract
Trainers of radiologists face the particular challenges of teaching no rmal and abnormal appearance for a variety of imaging modalities, prov iding access to a large appropriately-indexed case library, and teachi ng a consistent approach to the reporting of cases. The computer has t he potential to address these issues, to supplement conventional teach ing of radiology by providing case-based tutoring and diagnostic suppo rt based on a large library of images of normal and abnormal anatomy, described in a consistent terminology. The paper presents a new approa ch to computer-based training in radiology that combines a knowledge-b ased tutor with an on-line medical atlas. It describes two existing co mputer systems, the MR Tutor and ATLAS, and discusses the medical, com putational, epistemic, and pedagogic issues involved in developing a c ombined Atlas-Tutor. Integrating an atlas with a training system could significantly improve the teaching and support offered, but practical difficulties include the need to merge knowledge representations and to incorporate techniques for registering atlas plates on images that exhibit abnormalities. The paper addresses these problems, and conclud es by indicating how the Atlas-Tutor might be employed in practical ra diology training. (C) 1998 Published by Elsevier Science B.V. All righ ts reserved.