Hip dysplasia in dogs is a developmental disorder caused by a lack of alignment between the acetabulum and femur. This disorder leads to an abnormal development of the hip joints between the caput femoris and the acetabulum. The study included Ventro-Dorsal pelvis radiographs of 2,306 dogs aged 12 months or older, without considering breed or sex. In the first part of the study, 2,306 radiographs in DICOM format were labelled both for the region encompassing the caput femoris and acetabulum and for four critical anatomical points (the centre of the right and left caput femoris and the dorsocranial projection of the right and left acetabulum). In the study, the performance of all configurations of the YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLOv12 object detection algorithms was systematically evaluated in terms of precision, recall, mAP@50, and mAP50-95 metrics. According to the evaluation results, YOLOv11 achieved the best performance on the mAP50-95 metric with a value of 0.95397, outperforming the other configurations. This was followed by YOLOv8 (0.95245), YOLOv9 (0.95183), YOLOv10 (0.95005), and YOLOv12 (0.93832), respectively. In the mAP@50 analysis, the ranking was identified as YOLOv8 (0.99409), YOLOv9 (0.99386), YOLOv11 (0.99355), YOLOv12 (0.99345), and YOLOv10 (0.9933). This study concludes that artificial intelligence is a reliable alternative for diagnosing hip dysplasia in dogs. It has been found to be a more practical and accurate diagnostic method.

To Cite This Article: Yönez MK, Alpman U, Aslan NE, Bahar FI and Alpman E 2025. Measurement of the norberg angle using artificial intelligence in diagnosing canine hip dysplasia. Pak Vet J. http://dx.doi.org/10.29261/pakvetj/2025.280