Premium
Texture detection of simulated microcalcification susceptibility effects in magnetic resonance imaging of breasts
Author(s) -
James David,
Clymer Bradley D.,
Schmalbrock Petra
Publication year - 2001
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.1125
Subject(s) - microcalcification , magnetic resonance imaging , texture (cosmology) , predictive value , sensitivity (control systems) , mammography , radiology , breast cancer , nuclear magnetic resonance , artificial intelligence , medicine , computer science , image (mathematics) , cancer , physics , electronic engineering , engineering
The presence, size, structure and clustering characteristics of microcalcifications can indicate breast cancer. The magnetic susceptibility of microcalcifications differs from soft biological tissues, leading to directional blurring effects that can be detected by statistical image processing methods. A study of the ability of statistical texture analysis to detect simulated localized blurring in magnetic resonance imaging (MRI) of dense breast is presented. This method can detect localized blurring with sensitivity of 88.89% to 94.44%, specificity of 99.72% to 100%, positive predictive value of 73.91% to 100% and negative predictive value of 99.91% to 99.95%. J. Magn. Reson. Imaging 2001;13:876–881. © 2001 Wiley‐Liss, Inc.