Evaluation of Ultrasound Imaging in Developmental Hip Dysplasia with Artificial Intelligence

Authors : Hacı Ali Olçar, Ahmet Sertol Köksal, Onur Altıntaş, Bülent Turan, Göker Yurdakul, Satuk Buğrahan Yinanç, Gürol Göksungur, Burak Çakar, Murat Korkmaz

Pages : 78-87

Doi:10.52827/hititmedj.1472551

View : 39 | Download : 21

Publication Date : 2025-02-25

Article Type : Research Paper

Abstract :Objective: Developmental hip dysplasia is a common condition that starts in infancy. With the introduction of machine learning (artificial intelligence, AI) into medicine, the early diagnosis of disease and the success of treatment have increased significantly. This study aims to determine the accuracy of ultrasound images from ultrasound videos used in the developmental hip dysplasia screening program using machine learning techniques. Material and Method: The study involved the extraction of ultrasound image features using the Local Binary Pattern (LBP) method. The ultrasound image dataset was then prepared to evaluate the effectiveness of various machine learning approaches, including Decision Tree (DT), Random Forest (RF), K-Nearest Neighbour (KNN), Gradient Boosting (GB), Support Vector Machines (SVM), Naïve Bayes (NB), Logistic Regression (LR), and Multilayer Perceptron (MLP). Results: RF algorithm performed very well, recording the highest correct image rate. The study was generally considered successful and it is believed that the resulting model will be useful in the early diagnosis of developmental hip dysplasia. Conclusion: RF algorithm recorded the highest correct image rate, performing very well at 87.62% compared to other tested algorithms. The study was generally considered successful and the resulting model is believed to be useful in the early diagnosis of developmental hip dysplasia.
Keywords : makine öğrenimi (yapay zeka), gelişimsel kalça displazisi, görüntü sınıflandırma, lokal ikili model tekniği, kalça ultrasonografisi

ORIGINAL ARTICLE URL