Case report: Echocardiographic and computed tomographic features of congenital bronchoesophageal artery hypertrophy and fistula in a dog.

Introduction: Studies on aberrant bronchoesophageal arteries are limited. Herein, we report a case of a multi-origin systemic-to-pulmonary shunt with suspected bronchoesophageal artery hypertrophy and fistula in a dog. Case report: A 4-year-old castrated male beagle weighing 11 kg underwent routine medical screening. Physical examination revealed a right-sided continuous murmur of grades 1-2. Thoracic radiography revealed a mild cardiomegaly. Echocardiography revealed a continuous turbulent shunt flow distal to the right pulmonary artery (RPA) branch from the right parasternal short axis pulmonary artery view. Computed tomography demonstrated systemic-to-pulmonary shunts originating from the descending aorta at the level of T7-8, the right 5th and 6th dorsal intercostal arteries, and the right brachiocephalic trunk, which formed anomalous networks around the trachea and esophagus that anastomosed into a large tortuous vessel at the level of T6-7 and entered the RPA. Surgical ligation of multiple shunting vessels was performed. Postoperative echocardiography and computed tomography showed decreased left ventricular volume overload and markedly decreased size of the varices. Additionally, most of the shunting vessels were without residual shunt flow. Conclusion: The present study provides information regarding imaging features and the successful surgical management of multiple systemic-to-pulmonary shunts originating from the descending aorta, right brachiocephalic trunk, and intercostal arteries and terminating at the RPA. Multimodal imaging features after surgical ligation have also been described.

Detection of spondylosis deformans in thoracolumbar and lumbar lateral X-ray images of dogs using a deep learning network.

Introduction: Spondylosis deformans is a non-inflammatory osteophytic reaction that develops to re-establish the stability of weakened joints between intervertebral discs. However, assessing these changes using radiography is subjective and difficult. In human medicine, attempts have been made to use artificial intelligence to accurately diagnose difficult and ambiguous diseases in medical imaging. Deep learning, a form of artificial intelligence, is most commonly used in medical imaging data analysis. It is a technique that utilizes neural networks to self-learn and extract features from data to diagnose diseases. However, no deep learning model has been developed to detect vertebral diseases in canine thoracolumbar and lumbar lateral X-ray images. Therefore, this study aimed to establish a segmentation model that automatically recognizes the vertebral body and spondylosis deformans in the thoracolumbar and lumbar lateral radiographs of dogs. Methods: A total of 265 thoracolumbar and lumbar lateral radiographic images from 162 dogs were used to develop and evaluate the deep learning model based on the attention U-Net algorithm to segment the vertebral body and detect spondylosis deformans. Results: When comparing the ability of the deep learning model and veterinary clinicians to recognize spondylosis deformans in the test dataset, the kappa value was 0.839, indicating an almost perfect agreement. Conclusions: The deep learning model developed in this study is expected to automatically detect spondylosis deformans on thoracolumbar and lumbar lateral radiographs of dogs, helping to quickly and accurately identify unstable intervertebral disc space sites. Furthermore, the segmentation model developed in this study is expected to be useful for developing models that automatically recognize various vertebral and disc diseases.

A deep learning model for automated kidney calculi detection on non-contrast computed tomography scans in dogs.

Nephrolithiasis is one of the most common urinary disorders in dogs. Although a majority of kidney calculi are non-obstructive and are likely to be asymptomatic, they can lead to parenchymal loss and obstruction as they progress. Thus, early diagnosis of kidney calculi is important for patient monitoring and better prognosis. However, detecting kidney calculi and monitoring changes in the sizes of the calculi from computed tomography (CT) images is time-consuming for clinicians. This study, in a first of its kind, aims to develop a deep learning model for automatic kidney calculi detection using pre-contrast CT images of dogs. A total of 34,655 transverseimage slices obtained from 76 dogs with kidney calculi were used to develop the deep learning model. Because of the differences in kidney location and calculi sizes in dogs compared to humans, several processing methods were used. The first stage of the models, based on the Attention U-Net (AttUNet), was designed to detect the kidney for the coarse feature map. Five different models-AttUNet, UTNet, TransUNet, SwinUNet, and RBCANet-were used in the second stage to detect the calculi in the kidneys, and the performance of the models was evaluated. Compared with a previously developed model, all the models developed in this study yielded better dice similarity coefficients (DSCs) for the automatic segmentation of the kidney. To detect kidney calculi, RBCANet and SwinUNet yielded the best DSC, which was 0.74. In conclusion, the deep learning model developed in this study can be useful for the automated detection of kidney calculi.

Case report: Imaging features of aorta-right atrial tunnel in a dog using two-dimensional echocardiography and computed tomography.

A 7-year-old castrated male Pomeranian dog weighing 5 kg presented with a right-sided continuous murmur without any clinical signs. Thoracic radiographs indicated cardiomegaly and right atrial (RA) bulging. Echocardiography revealed a tunnel originating from the right coronary sinus of Valsalva and terminating in the RA. Contrast echocardiography revealed pulmonary arteriovenous anastomoses. Computed tomography (CT) demonstrated a tortuous shunting vessel that originated from the aorta extending in a ventral direction, ran along the right ventricular wall, and was inserted into the RA. Based on these diagnostic findings, the dog was diagnosed with the aorta-RA tunnel. At the 1-year follow-up visit without treatment, the dog showed no significant change except for mild left ventricular volume overload and mildly decreased contractility. To the best of our knowledge, this is the first case report of an aorta-RA tunnel that has been described in detail using echocardiography and CT in a dog. In conclusion, the aorta-RA tunnel should be included in the clinical differential diagnoses if a right-sided continuous murmur is heard or shunt flow originating from the aortic root is identified.

Evaluation of urethral thickness using ultrasonography in healthy small-breed dogs.

Introduction: Urethral thickness measurements can be indicative of the pathological state of a patient; however to the best of our knowledge, no measurement reference range has been established in small-breed dogs. This study aimed to establish reference ranges for total urethral thickness and urethral wall thickness in healthy small-breed dogs; "urethral wall thickness" was assumed to be 1/2 of the "total urethral thickness." Methods: Total urethral thickness was measured by ultrasonography in 240 healthy small-breed dogs. In both female and male dogs, the thickness was measured in the mid-sagittal plane. In female dogs, it was measured immediately before the pelvic bone. In male dogs, it was measured caudal to the prostate and cranial to the pelvic bone. The total urethral thickness we measured is the total thickness of the collapsed urethra, which is the sum of the thicknesses of the dorsal and ventral urethral wall. Results: The mean value of total urethral thickness was 3.15 ± 0.83 mm (urethral wall thickness, 1.58 ± 0.41 mm) in 240 small-breed dogs. The total urethral thickness was significantly greater in male dogs than in female dogs (p < 0.001), even when compared among the same breeds (p < 0.05). The mean value of the total urethral thickness in females was 2.78 ± 0.60 mm (urethral wall thickness, 1.39 ± 0.30 mm), and 3.53 ± 0.86 mm (urethral wall thickness, 1.76 ± 0.43 mm) in males. There was very weak positive correlation between body weight (BW) and total urethral thickness (R2 = 0.109; ß = 0.330; p < 0.001). Intraobserver reliability measured by intraclass correlation coefficient (ICC) was 0.986 (p < 0.001) and interobserver reliability measured by ICC was 0.966 (p < 0.001). Discussion: This study described the differences in total urethral thickness between breeds, sexes, and sterilization status, and the correlation between BW and total urethral thickness. Furthermore, this is the first study to provide reference ranges of total urethral thickness and urethral wall thickness in small-breed dogs using ultrasonography, and is expected to be useful for urethral evaluation in veterinary diagnostic imaging.

A deep learning model for CT-based kidney volume determination in dogs and normal reference definition.

Kidney volume is associated with renal function and the severity of renal diseases, thus accurate assessment of the kidney is important. Although the voxel count method is reported to be more accurate than several methods, its laborious and time-consuming process is considered as a main limitation. In need of a new technology that is fast and as accurate as the manual voxel count method, the aim of this study was to develop the first deep learning model for automatic kidney detection and volume estimation from computed tomography (CT) images of dogs. A total of 182,974 image slices from 386 CT scans of 211 dogs were used to develop this deep learning model. Owing to the variance of kidney size and location in dogs compared to humans, several processing methods and an architecture based on UNEt Transformers which is known to show promising results for various medical image segmentation tasks including this study. Combined loss function and data augmentation were applied to elevate the performance of the model. The Dice similarity coefficient (DSC) which shows the similarity between manual segmentation and automated segmentation by deep-learning model was 0.915 ± 0.054 (mean ± SD) with post-processing. Kidney volume agreement analysis assessing the similarity between the kidney volume estimated by manual voxel count method and the deep-learning model was r = 0.960 (p < 0.001), 0.95 from Lin's concordance correlation coefficient (CCC), and 0.975 from the intraclass correlation coefficient (ICC). Kidney volume was positively correlated with body weight (BW), and insignificantly correlated with body conditions score (BCS), age, and sex. The correlations between BW, BCS, and kidney volume were as follows: kidney volume = 3.701 × BW + 11.962 (R 2 = 0.74, p < 0.001) and kidney volume = 19.823 × BW/BCS index + 10.705 (R 2 = 0.72, p < 0.001). The deep learning model developed in this study is useful for the automatic estimation of kidney volume. Furthermore, a reference range established in this study for CT-based normal kidney volume considering BW and BCS can be helpful in assessment of kidney in dogs.