No Detail Found!

Measurement of the Norberg Angle Using Artificial Intelligence in Diagnosing Canine Hip Dysplasia

Author(s)
M.K Yonez Department of Surgery, Faculty of Veterinary Medicine, University of Bozok,66000, Yozgat, Turkey
U Alpman Deparment of Surgery, Faculty of Veterinary Medicine, University of Bozok,66000, Yozgat,Turkey
N.E Aslan Deparment of Mechanical Engineering, Faculty of Engineering, Marmara University,34854, Istanbul,Turkey
F.İ Bahar Faculty of Veterinary Medicine, University of Erciyes,38280, Kayseri,Turkey:
E. Alpman Deparment of Mechanical Engineering, Faculty of Engineering, Marmara University,34854, Istanbul,Turkey
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.
Publication Details
Page(s) 1930-1937
Published Journal: Pakistan Veterinary Journal, Volume: 45, Issue: 4, Year: 2025

Request the full text from PASTIC

Keywords
Artificial, Intelligence, Canine, Norberg Angle, Hip dysplasia
References
Aghapour M,Bockstahler B,Kneissl S .2023 .Radiographic diagnosis of hip laxity in Rottweilers: interobserver agreement at eight- and twelve-months of age. Animals, 13(2) : 231.
Ajadi RA,Sanni JL,Sobayo EL .2018 .Radiographic coxofemoral measurements in Boerboel dogs. Folia Vet, 62(4) : 66-73.
Akinsulie OC .2024 .The potential application of artificial intelligence in veterinary clinical practice and biomedical research. Front Vet Sci, 11 : 1347550.
Akula S,Akula P,Kamati N .2022 .Pattern Recognition (ICAITPR). In: Proceedings of the First International Conference on Artificial Intelligence Trends, : 1-6.
Albadrani B .2024 .Artificial intelligence in veterinary care: A review of applications for animal health. Egypt J Vet Sci, 55(6) : 1725-36.
Appleby RB,Basran PS .2022 .Artificial intelligence in veterinary medicine. J Am Vet Med Assoc, 260(8) : 819-24.
Bouchemla F,Akchurin SV,Akchurina IV .2023 .Artificial intelligence feasibility in veterinary medicine: A systematic review. Vet World, 16(10) : 2143-149.
Boufenar C,Logovi TEMN,Samir D .2023 .Computer-aided diagnosis of canine hip dysplasia using deep learning in a novel Xray dataset. Comput Methods Biomech Biomed Eng Imaging Vis, 11(7) : .
Comhaire FH,Schoonjans FA .2011 .Canine hip dysplasia: significance of the Norberg angle for healthy breeding. J Small Anim Pract, 52 : 536-42.
Den H,Ito J,Kokaze A .2023 .Diagnostic accuracy of a deep learning model using YOLOv5 for detecting developmental dysplasia of the hip on radiographs. Sci Rep, 13(1) : 6693.
Fitzke M,Stack C,Dourson A .2021 .global deployment of radiology AI for veterinary teleradiology. arXiv 2111, : .
Franco-Gonçalo P,Leite P,Alves-Pimenta S .2025 .A Computer-Aided Approach to Canine Hip Dysplasia Assessment: Measuring Femoral Head-Acetabulum Distance with Deep Learning. Appl Sci, 15(9) : 5087.
Ginja M,Gaspar A,Ginja C .2015 .Emerging insights into the genetic basis of canine hip dysplasia. Vet Med Res Rep, 6 : 193-202.
Gomes D,Alves-Pimenta S,Ginja M .2021 .Predicting canine hip dysplasia in X-ray images using deep learning. In: Optimization, Learning Algorithms and Applications, : 393-400.
Hansen GC,Yao Y,Fischetti AJ .2025 .Next-generation machine learning model to measure the Norberg angle on canine hip radiographs increases accuracy and time to completion. Am J Vet Res, 25(9) : .
Hennessey E,DiFazio M,Hennessey R .2022 .Artificial intelligence in veterinary diagnostic imaging: A literature review. Vet Radiol Ultrasound, 63 : 851-70.
Jacob N,Kumar BAAS,Padodara RJ .2022 .A glimpse into artificial intelligence in animal physiology and allied sciences. Anim Reprod Update, 2(1) : 72-81.
Joslyn S and Alexander K .2022 .Evaluating artificial intelligence algorithms for use in veterinary radiology. Vet Radiol Ultrasound, 63(S1) : 871-79.
Kim E,Fischetti AJ,Sreetharan PS .2022 .Comparison of artificial intelligence to the veterinary radiologist's diagnosis of canine cardiogenic pulmonary edema. Vet Radiol Ultrasound, 63(3) : 292-97.
Klever J,Brühschwein A,Wagner S .2020 .Comparison of Norberg angle and distraction index for hip laxity in dogs. Vet Comp Orthop Traumatol, 33(4) : 274-78.
Lassalle L,Regnard NE,Durteste M .2025 .Validation of AI-driven measurements for hip morphology assessment. Eur J Radiol, 183 : 111911.
LeCun Y,Bengio Y,Hinton G .2015 .Deep learning. Nature, 521(7553) : 436-44.
Liu C,Wang W,Lian J .2025 .Lesion classification and diabetic retinopathy grading via vision transformer. Front Public Health, 12 : 1442114.
Loureiro C,Gonçalves L,Leite P .2024 .Deep learning-based automated assessment of canine hip dysplasia. Multimed Tools Appl, 1 : .
McEvoy F and Amigo J .2013 .Using machine learning to classify image features from canine pelvic radiographs. Vet Radiol Ultrasound, 54(2) : 122-26.
McEvoy F,Proschowsky H,Müller A .2021 .Deep transfer learning for hip joint detection and dysplasia classification in pelvis radiographs. Vet Radiol Ultrasound, 62(4) : 387-93.
Mikkola L,Holopainen S,Pessa-Morikawa T .2019 .Genetic dissection of canine hip dysplasia phenotypes and osteoarthritis reveals three novel loci. BMC Genomics, 20 : 1027.
Pesapane F,Gnocchi G,Quarrella C .2024 .Errors in radiology: a standard review. J Clin Med, 13(15) : 4306.
Pinna S,Tassani C,Antonino A .2022 .Prevalence of primary radiographic signs of hip dysplasia in dogs. Animals, 12(20) : 2788.
Ragap MG,Abdulkadır SJ,Muneer A,Comprehensive Systematic A .2023 .Review of YOLO for Medical Object Detection (. IEEE Access, 12 : 57815-57836.
Santana A,Alves-Pimenta S,Martins J .2021 .Imaging diagnosis of canine hip dysplasia without human exposure to ionizing radiation. Vet J, 276 : 105745.
Lopez Schachner E,M, Schachner E .2015 .Diagnosis, prevention, and management of canine hip dysplasia: A review. Vet Med Res Rep, 6 : 181-192.
Sezer A,Sezer HB .2020 .Deep CNN-based automatic classification of neonatal hip ultrasound images with speckle noise reduction. Ultrasound Med Biol, 46(3) : 735-49.
Sha J,Huang L,Chen Y .2023 .Clinical thought-based software for diagnosing developmental dysplasia of the hip in pediatric radiographs. Front Pediatr, 11 : 1080194.
Vinicki K,Ferrari P,Belic M .1803 .Using CNNs to determine reticulocyte percentage in cats. Clin Orthop Relat Res arXiv, 04873 : .
Zakareya S,Izadkhah H,Karimpour J .1944 .A new deep-learning model for breast cancer diagnosis from medical images. Diagnostics, 13(11) : .
0

Citations

0

Downloads

22

Views