Initial screening for dental abnormalities identified by labial and buccal photographs in dogs and cats.

OBJECTIVE: To evaluate the dental abnormalities by visually assessing the labial and buccal photographs in dogs and cats and analyze their prevalence based on age and breed. ANIMALS: 1,096 client-owned dogs and 775 client-owned cats. METHODS: Data were collected from patients who visited 26 private veterinary clinics from January to December 2022. Each animal was evaluated through dental photographs taken from the labial and buccal sides. Correlations between the prevalence of the identified dental abnormalities and age, craniofacial type, and breed, were analyzed. RESULTS: Calculus, discoloration, epulis, fractured teeth, gingival recession, gingivitis, malocclusion, missing teeth, and persistent deciduous teeth could be identified by analyzing the dental photographs in both dogs and cats. Enamel defects in dogs and tooth resorption in cats could be identified. Brachycephalic dogs had a significantly higher prevalence of malocclusion (OR, 1.93; 95% CI, 1.36 to 2.75) and missing teeth (OR, 3.63; 95% CI, 2.71 to 4.91) compared to nonbrachycephalic dogs. Brachycephalic cats had a significantly higher prevalence of fractured teeth (OR, 1.95; 95% CI, 1.24 to 3.04) and a lower prevalence of gingival recession (OR, 0.30; 95% CI, 0.15 to 0.55) compared to nonbrachycephalic cats. Calculus, persistent deciduous teeth, and possibly gingivitis could be identified in dogs and cats by analyzing labial and buccal photographs. The assessment of some dental abnormalities such as fractured teeth, missing teeth, and tooth resorption can be limited without a complete dental examination under anesthesia. CLINICAL RELEVANCE: Although the assessment of dental conditions may be underestimated, the data on the prevalence of the dental abnormalities evaluated through the photographs could be utilized for screening dental diseases.

Long-term evaluation of the effects of vitreous degeneration on cataracts and retinal detachment in dogs.

OBJECTIVE: We aimed to track and evaluate the association between vitreous degeneration and the development of cataracts or retinal detachments in dogs over a long period. ANIMAL STUDIED: Data on vitreous degeneration, cataracts, and retinal detachment in 102 eyes were collected from 68 dogs who underwent ocular ultrasonography at least twice between March 2017 and November 2021 at the Veterinary Medical Teaching Hospital, Konkuk University. The mean follow-up time was 515 ± 256 (mean ± standard deviation; range: 81-1196) days. PROCEDURE: Development of cataracts and retinal detachment, according to the severity of vitreous degeneration grade (VDG), was evaluated during long-term follow-up. RESULTS: In the cataract study (87 eyes, 61 dogs), the number of cataracts developed according to VDG (grade: 0-3) were as follows: VDG 0: 1 in 10 (10%) eyes, VDG 1: 15 in 35 (43%) eyes, VDG 2: 15 in 30 (50%) eyes, and VDG 3: 10 in 12 (83%) eyes. It was significantly different among grades (p = .026). In the retinal detachment study (95 eyes, 64 dogs), the number of retinal detachments developed according to each VDG were as follows: VDG 0: 0 in 11 (0%) eyes, VDG 1: 1 in 36 (3%) eyes, VDG 2: 5 in 35 (14%) eyes, and VDG 3: 4 in 13 (30%) eyes. It was also significantly different among grades (p = .019). CONCLUSIONS: During long-term follow-up, dogs with severe vitreous degeneration had an increased risk of cataract and retinal detachment development than those without or with mild vitreous degeneration.

Developing a diagnosis model for dry eye disease in dogs using object detection.

The purpose of this study was to develop an object detection method for the diagnosis of dry eye disease (DED) in dogs. To this end, a methodology was designed to evaluate ocular surface video images using the YOLOv5 model, which is an object detection algorithm that has been widely used because of its simple network structure and fast detection speed. Because the cornea is a transparent organ, an illuminator plate with grid squares was used to provide grid lines, which were analyzed as the reflected straight lines of the light source representing the precorneal tear film (PTF) stability. The original video consisted of the number of 12 normal images(normal, [Formula: see text] = 17) and the number of 15 abnormal images(abnormal, [Formula: see text] = 17), converted to JPEG images for labeling, learning, and model validation. The labeled image data were divided into a training image data set (normal, [Formula: see text] = 15,276; abnormal, [Formula: see text] = 26,196) to a validation image data set (normal, [Formula: see text] = 6546; abnormal, [Formula: see text] = 11,228). As a result of the experiment, the mean average precision ([Formula: see text]) achieved 0.995. This study proposes a method to effectively determine ocular surface status in dogs by using YOLOv5 and concludes that an object detection model can be used in the veterinary field.