Classification of radiographic lung pattern based on texture analysis and machine learning

This study evaluated the feasibility of using texture analysis and machine learning to distinguish radiographic lung patterns. A total of 1200 regions of interest (ROIs) including four specific lung patterns (normal, alveolar, bronchial, and unstructured interstitial) were obtained from 512 thoracic radiographs of 252 dogs and 65 cats. Forty-four texture parameters based on eight methods of texture analysis (first-order statistics, spatial gray-level-dependence matrices, gray-level-difference statistics, gray-level run length image statistics, neighborhood gray-tone difference matrices, fractal dimension texture analysis, Fourier power spectrum, and Law's texture energy measures) were used to extract textural features from the ROIs. The texture parameters of each lung pattern were compared and used for training and testing of artificial neural networks. Classification performance was evaluated by calculating accuracy and the area under the receiver operating characteristic curve (AUC). Forty texture parameters showed significant differences between the lung patterns. The accuracy of lung pattern classification was 99.1% in the training dataset and 91.9% in the testing dataset. The AUCs were above 0.98 in the training set and above 0.92 in the testing dataset. Texture analysis and machine learning algorithms may potentially facilitate the evaluation of medical images.

Novel vertebral computed tomography indices in normal and spinal disorder dogs

This study was carried out to derive and evaluate reference computed tomography (CT)-based indices for normal canine spine. CT and magnetic resonance images were acquired from 12 clinically normal Beagle dogs (normal group) and 50 dogs with 56 spinal disorders (patient group). Image acquisition regions were cervical spine (C2–T1), thoracic spine (T1–T13), and lumbar spine (L1–L7). Measured indices were: the ratios of width to height of the spinal cord including the dura matter (CR) and of the vertebral foramen (FR), and the ratio of the cross-sectional area of the spinal cord to that of the vertebral foramen (CFAR). Reliability analysis was performed to evaluate intermodality agreement. Student's t-tests and receiver operating characteristic curves were used to discriminate the normal and patient groups on CT. Intermodality agreements of the normal and patient groups were acceptable to excellent. The highest discriminating levels of CR at the vertebral body level and the intervertebral disc space level were 1.25 or more and 1.44 or more, respectively. FR and CFAR had the highest discriminating level at the cervical region. This report presents quantitative information on canine spinal morphometry; the obtained indices may be helpful for CT screening of dogs with spinal disorders.