Feature selection for the characterization of ultrasonic images of the placenta using texture classification

Abstract

The characterization of ultrasonic images of the placenta is one of the clinical procedures followed for assessing the progress of pregnancy. In this work, the classification of scans of the placenta according with Grannum grading is attempted. Feature selection was used for determining the relevant textural features that were extracted from the scans. Three different sets of textural features, namely cooccurrence matrices, Laws masks and neighborhood gray-tone difference matrices (NGTDM) were used. A set of 59 images corresponding to the four grades was sampled in subimages of different sizes, the textural features were computed and weighted using the relief-F algorithm. The strategy used for classification was the k-nearest neighbor algorithm using leave-one-out cross-validation. The percentage of correct classification or accuracy was computed for different subsets of features, with different sizes of the region of interest showing that generally a small number of features are enough for achieving the highest accuracy.