1 University Hospital for Companion Animals, Department of Veterinary Clinical and Animal Sciences, Faculty of Health and Medical Sciences, Københavns Universitet2 Spectroscopy and Chemometrics, Department of Food Science, Faculty of Science, Københavns Universitet3 Veterinary Imaging, Department of Veterinary Clinical and Animal Sciences, Faculty of Health and Medical Sciences, Københavns Universitet4 Veterinary Imaging, Department of Veterinary Clinical and Animal Sciences, Faculty of Health and Medical Sciences, Københavns Universitet5 Spectroscopy and Chemometrics, Department of Food Science, Faculty of Science, Københavns Universitet
evaluation of partial least squares discriminant analysis and artificial neural network models
As the number of images per study increases in the field of veterinary radiology, there is a growing need for computer-assisted diagnosis techniques. The purpose of this study was to evaluate two machine learning statistical models for automatically identifying image regions that contain the canine hip joint on ventrodorsal pelvis radiographs. A training set of images (120 of the hip and 80 from other regions) was used to train a linear partial least squares discriminant analysis (PLS-DA) model and a nonlinear artificial neural network (ANN) model to classify hip images. Performance of the models was assessed using a separate test image set (36 containing hips and 20 from other areas). Partial least squares discriminant analysis model achieved a classification error, sensitivity, and specificity of 6.7%, 100%, and 89%, respectively. The corresponding values for the ANN model were 8.9%, 86%, and 100%. Findings indicated that statistical classification of veterinary images is feasible and has the potential for grouping and classifying images or image features, especially when a large number of well-classified images are available for model training.
Veterinary Radiology and Ultrasound, 2013, Vol 54, Issue 2, p. 122-126