Search

Simple Summary: Canine hip dysplasia is a painful condition common in large dog breeds, leading to joint instability and osteoarthritis. Accurate diagnosis is crucial for guiding breeding decisions to help reduce its prevalence. However, evaluating hip health status can be challenging, as minor positioning changes during X-rays can distort images and hinder proper hip joint assessment. In this study, we developed an artificial intelligence tool for the automatic evaluation of pelvic alignment in X-rays. By detecting subtle asymmetries in bone structure, the tool determines whether a dog's hips are properly aligned. Our findings showed that the artificial intelligence tool performed as accurately as an expert human examiner in detecting misalignment. This automated approach could improve the reliability of canine hip dysplasia screenings, saving veterinarians time and reducing misdiagnosis risks due to human error. Ultimately, this technology has the potential to enhance medical care for dogs and support breeders in making more informed choices, contributing to canine health improvements and reducing canine hip dysplasia incidence in future generations. Canine hip dysplasia (CHD) screening relies on accurate positioning in the ventrodorsal hip extended (VDHE) view, as even mild pelvic rotation can affect CHD scoring and impact breeding decisions. This study aimed to assess the association between pelvic rotation and asymmetry in obturator foramina areas (AOFAs) and to develop a computer vision model for automated AOFA measurement. In the first part, 203 radiographs were analyzed to examine the relationship between pelvic rotation, assessed through asymmetry in iliac wing and obturator foramina widths (AOFWs), and AOFAs. A significant association was found between pelvic rotation and AOFA, with AOFW showing a stronger correlation (R2 = 0.92, p < 0.01). AOFW rotation values were categorized into minimal (n = 71), moderate (n = 41), marked (n = 37), and extreme (n = 54) groups, corresponding to mean AOFA ± standard deviation values of 33.28 ± 27.25, 54.73 ± 27.98, 85.85 ± 41.31, and 160.68 ± 64.20 mm2, respectively. ANOVA and post hoc testing confirmed significant differences in AOFA across these groups (p < 0.01). In part two, the dataset was expanded to 312 images to develop the automated AOFA model, with 80% allocated for training, 10% for validation, and 10% for testing. On the 32 test images, the model achieved high segmentation accuracy (Dice score = 0.96; Intersection over Union = 0.93), closely aligning with examiner measurements. Paired t-tests indicated no significant differences between the examiner and model's outputs (p > 0.05), though the Bland–Altman analysis identified occasional discrepancies. The model demonstrated excellent reliability (ICC = 0.99) with a standard error of 17.18 mm2. A threshold of 50.46 mm2 enabled effective differentiation between acceptable and excessive pelvic rotation. With additional training data, further improvements in precision are expected, enhancing the model's clinical utility. [ABSTRACT FROM AUTHOR]