<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors></contributors><titles><title><style face="normal" font="default" size="100%">On Standardizing the MR Image Intensity Scale</style></title><secondary-title><style face="normal" font="default" size="100%">RADIOLOGY</style></secondary-title><short-title><style face="normal" font="default" size="100%">RADIOLOGY</style></short-title></titles><dates><year><style  face="normal" font="default" size="100%">1998</style></year><pub-dates><date><style  face="normal" font="default" size="100%">1998///</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">209</style></volume><pages><style face="normal" font="default" size="100%">581 - 582</style></pages><isbn><style face="normal" font="default" size="100%">0033-8419</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">PURPOSE: MR image intensities have varying ranges and meaningeven for the same protocol (P) and body region (D). This causes 
many difficulties in image display and analysis. This exhibit 
describes a method of standardizing the intensity scale, so that 
for the same P and D, similar intensities will have similar 
meaning.
MATERIALS AND METHODS: In the TRAINING phase (done only once for 
a given P and D), the parameters of the standardizing 
transformation are &quot;learnt&quot; from an image set. In the MAPPING 
phase, done for each MR study, these parameters are utilized to 
determine the mapping needed to deform its histogram into the 
standardized histogram. The method was tested quantitatively on 
90 brain FSE T2, PD and T1 studies of MS patients and 
qualitatively on an additional 15 SE PD, T1 and SPGR studies of 
the brain and foot.
RESULTS: As measured by mean squared difference, standardized 
images have statistically significantly (p&lt;0.01) more consistent 
range and meaning than those without. Fixed windows that do not 
require per study adjustment can be established for the 
standardized images.
CONCLUSIONS: Standardizing MR intensity scales to overcome the 
difficulties due to widely varying intensity meaning is feasible 
by protocol and body region. This can be implemented in a PACS 
via DICOM value of interest look up tables.
</style></abstract><issue><style face="normal" font="default" size="100%">SUPPL P</style></issue><notes><style face="normal" font="default" size="100%">84th Scientific Assembly and Annual Meeting of the RadiologicalSociety of North America (RSNA)
Chicago, IL, USA, 1998.11.29-1998.12.04.
</style></notes></record></records></xml>