Issue No. 07 - July (1972 vol. 21)
R.N. Sutton , Department of Radiology, University of Missouri
The complete pattern recognition problem is considered for the practical solution to a current significant medical question. Automated screening of chest radiographs for the detection of textural type abnormalities is approached from the view of: 1) preprocessing for standardization and data reduction; 2) feature extraction of characteristic measures (feature selection by optimization of classification accuracy); and 3) overall classification using training and test sets of selected chest radiographs.
Feature extraction, image processing, pattern recognition, radiographic image processing.
E. Hall and R. Sutton, "Texture Measures for Automatic Classification of Pulmonary Disease," in IEEE Transactions on Computers, vol. 21, no. , pp. 667-676, 1972.