TY - JOUR
T1 - Using machine learning to classify image features from canine pelvic radiographs
T2 - evaluation of partial least squares discriminant analysis and artificial neural network models
AU - McEvoy, Fintan
AU - Amigo Rubio, Jose Manuel
N1 - © 2012 Veterinary Radiology & Ultrasound.
PY - 2013/3
Y1 - 2013/3
N2 - 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.
AB - 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.
KW - Animals
KW - Artificial Intelligence
KW - Diagnosis, Computer-Assisted
KW - Discriminant Analysis
KW - Dogs
KW - Hip Joint
KW - Least-Squares Analysis
KW - Neural Networks (Computer)
KW - Pelvis
KW - Radiographic Image Interpretation, Computer-Assisted
U2 - 10.1111/vru.12003
DO - 10.1111/vru.12003
M3 - Journal article
C2 - 23228122
SN - 1058-8183
VL - 54
SP - 122
EP - 126
JO - Veterinary Radiology & Ultrasound
JF - Veterinary Radiology & Ultrasound
IS - 2
ER -