Measurement of the Norberg Angle Using Artificial Intelligence in Diagnosing Canine Hip Dysplasia.
Saved in:
| Title: | Measurement of the Norberg Angle Using Artificial Intelligence in Diagnosing Canine Hip Dysplasia. |
|---|---|
| Authors: | Yönez, M. K.1, Alpman, U.1 umut_alpman@hotmail.com, Aslan, N. E.2, Bahar, F. İ.3, Alpman, E.4 |
| Source: | Pakistan Veterinary Journal. 2025, Vol. 45 Issue 4, p1930-1937. 8p. |
| Document Type: | Article |
| Subjects: | Artificial intelligence, Object recognition (Computer vision), Veterinary medicine, Joint diseases, Diagnostic imaging, Hip joint, Radioscopic diagnosis |
| Author-Supplied Keywords: | Artificial Canine Hip Dysplasia Intelligence Norberg Angle |
| Abstract: | 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. [ABSTRACT FROM AUTHOR] |
| Copyright of Pakistan Veterinary Journal is the property of Pakistan Veterinary Journal, Faculty of Veterinary Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Author Affiliations: | 1Deparment of Surgery, Faculty of Veterinary Medicine, University of Erciyes, 38280, Kayseri, Turkey 2Deparment of Surgery, Faculty of Veterinary Medicine, University of Bozok, 66000, Yozgat, Turkey 3Faculty of Veterinary Medicine, University of Erciyes, 38280, Kayseri, Turkey 4Deparment of Mechanical Engineering, Faculty of Engineering, Marmara University, 34854, Istanbul, Turkey |
| ISSN: | 0253-8318 |
| DOI: | 10.29261/pakvetj/2025.280 |
| Accession Number: | 191617465 |
| Database: | Veterinary Source |
| Abstract: | 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. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 02538318 |
| DOI: | 10.29261/pakvetj/2025.280 |