Franco-Gonçalo Pedro, Leite Pedro, Alves-Pimenta Sofia, Colaço Bruno, Gonçalves Lio, Filipe Vítor, McEvoy Fintan, Ferreira Manuel, Ginja Mário
Department of Veterinary Science, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal.
Veterinary and Animal Science Research Centre (CECAV), University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, Portugal.
Vet Sci. 2024 Dec 7;11(12):630. doi: 10.3390/vetsci11120630.
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 ( = 0.92, < 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 mm, respectively. ANOVA and post hoc testing confirmed significant differences in AOFA across these groups ( < 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 -tests indicated no significant differences between the examiner and model's outputs ( > 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 mm. A threshold of 50.46 mm 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.
犬髋关节发育不良（CHD）筛查依赖于腹背位髋关节伸展（VDHE）视图中的精确定位，因为即使是轻微的骨盆旋转也会影响CHD评分并影响繁殖决策。本研究旨在评估骨盆旋转与闭孔面积（AOFA）不对称之间的关联，并开发一种用于自动测量AOFA的计算机视觉模型。在第一部分中，分析了203张X光片，以研究通过髂骨翼和闭孔宽度（AOFW）不对称评估的骨盆旋转与AOFA之间的关系。发现骨盆旋转与AOFA之间存在显著关联，AOFW显示出更强的相关性（ = 0.92， < 0.01）。AOFW旋转值分为最小（n = 71）、中度（n = 41）、明显（n = 37）和极端（n = 54）组，分别对应于平均AOFA±标准差为33.28±27.25、54.73±27.98、85.85±41.31和160.68±64.20 mm。方差分析和事后检验证实了这些组之间AOFA的显著差异（ < 0.01）。在第二部分中，数据集扩展到312张图像以开发自动AOFA模型，其中80%用于训练，10%用于验证，10%用于测试。在32张测试图像上，该模型实现了高分割精度（Dice分数 = 0.96；交并比 = 0.93），与检查者的测量结果密切吻合。配对 -检验表明检查者和模型输出之间没有显著差异（ > 0.05），尽管布兰德-奥特曼分析发现偶尔存在差异。该模型显示出出色的可靠性（ICC = 0.99），标准误差为17.18 mm。50.46 mm的阈值能够有效区分可接受的骨盆旋转和过度的骨盆旋转。有了更多的训练数据，预计精度会进一步提高，从而增强该模型的临床实用性。
