The authors present an algorithm utilizing Markov random field modelin
g for identifying lung regions in a digitized chest radiograph (DCR).
Let x represent the classifications of each pixel in a DCR as either l
ung or nonlung. We model x as a realization of a spatially varying Mar
kov random field. This model is developed utilizing spatial and textur
al information extracted from samples of lung and nonlung region-types
in a training set of DCRs. With this model, the technique of Iterated
Conditional Modes is used to determine the optimal classification of
each pixel in a DCR. The algorithm's ability to identify lung regions
is evaluated on a testing set of DCRs. The algorithm performs well yie
lding a sensitivity of 90.7% +/- 4.4%, a specificity of 97.2% +/- 2.0%
, and an accuracy of 94.8% +/- 1.6%. In an attempt to gain insight int
o the meaning and level of the algorithm's performance numbers, the re
sults are compared to those of some easily implemented classification
algorithms. (C) 1998 American Association of Physicists in Medicine. [
S0094-2405(98)02206-8].