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.

Ultrasonographic assessment of experimentally induced gastric perforation in beagle dogs / 대한수의학회지

The goals of this study were, first, to evaluate the feasibility of inducing gastric perforation with 99% alcohol injection after electrocautery (EA-method), and, second, to observe “enhanced peritoneal stripe sign (EPSS)” and other lesions upon induction of gastric perforation. Six clinically normal beagle dogs were prepared for gastric perforation using endoscopy. After gastric perforation, EPSS and other lesions on ultrasonography were observed eventually (at 0 h, 3 h, day 1, day 2, day 3, day 4, day 5, and day 6). We graded the EPSS depending on its width and number. EPSS was observed until day 4 of the examination in all the 6 dogs. The grades of EPSS were the highest at 3 h and declined gradually. Peritoneal effusion was observed in all dogs at 3 h and on day 1. Regional bright mesenteric fat was confirmed in all dogs on days 3 and 4. In conclusion, gastric perforation can be induced by EA-method. EPSS and peritoneal effusion appear at a very early stage, and regional bright mesenteric fat was identified on days 3 and 4 in almost all dogs with gastric perforation.

Congenital portal vein aplasia with portocaval shunting in two dogs / 대한수의학회지

Two dogs presented with vomiting and head pressing. In both dogs, a large vessel was revealed in computed tomography (CT) angiography, which was found to leave the portal vein (PV) cranial to the splenomesenteric confluence and enter the pre-hepatic caudal vena cava cranial to the right renal vein. The flow of portal blood to the liver was not identified. Based on CT angiography, the dogs were suspected to have congenital PV aplasia with portocaval shunting. Diagnostic imaging of potential malformations for PV continuation should be conducted before attempting shunt closure.

Hypertrophic obstructive cardiomyopathy in a Yorkshire Terrier

An 11-year-old, castrated male dog presented with a 3-month history of cough and depression. Auscultation revealed systolic murmur and thoracic radiographs showing enlargement of both the atrium and left ventricle. Echocardiography showed thickened mitral valve and moderate-to-severe left atrial enlargement. Additionally, M-mode echocardiography showed symmetric left ventricular wall thickening and systolic anterior motion of the mitral valve, while Doppler imaging revealed high velocity turbulent flow through the left ventricular outflow tract. Based on echocardiography, this case was diagnosed with hypertrophic obstructive cardiomyopathy. After 5 months, the dog was clinically static in radiography and echocardiography.

Ultrasonographic evaluation of skin thickness in small breed dogs with hyperadrenocorticism

The purpose of this study was to propose a standard for differentiation between normal dogs and patients with hyperadrenocorticism (HAC) by measuring skin thickness via ultrasonography in small breed dogs. Significant changes in skin thickness of patients treated with prednisolone (PDS) or patients with HAC treated with trilostane were evaluated. Skin thickness was retrospectively measured on three abdominal digital images obtained from small breed dogs weighing < 15 kg that underwent abdominal ultrasonography. Mean skin thickness of normal dogs was 1.03 ± 0.25 mm (mean ± SD). Both the HAC and PDS groups showed significantly thinner skin than that in the normal group. Seven of the 10 HAC patients treated with trilostane had increased skin thickness. The area under the curve value of 0.807 was based on the receiver operating characteristics (ROC) curve for differentiating normal dogs from HAC patients. Sensitivity was 76% and specificity was 73% when skin thickness was less than the 0.83 mm cutoff value. In conclusion, measurement of skin thickness in small breed dogs by using ultrasonography is likely to provide clinical information useful in differentiating HAC patients from normal dogs. However, exposure to PDS, trilostane, and other conditions may have a significant effect on skin thickness.

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.

Hypertrophic obstructive cardiomyopathy in a Yorkshire Terrier / 대한수의학회지

An 11-year-old, castrated male dog presented with a 3-month history of cough and depression. Auscultation revealed systolic murmur and thoracic radiographs showing enlargement of both the atrium and left ventricle. Echocardiography showed thickened mitral valve and moderate-to-severe left atrial enlargement. Additionally, M-mode echocardiography showed symmetric left ventricular wall thickening and systolic anterior motion of the mitral valve, while Doppler imaging revealed high velocity turbulent flow through the left ventricular outflow tract. Based on echocardiography, this case was diagnosed with hypertrophic obstructive cardiomyopathy. After 5 months, the dog was clinically static in radiography and echocardiography.