Background Developmental dysplasia of the hip (DDH) is the most common hip abnormality in children. Closed or open reduction and cast immobilization are the most commonly used treatments for patients aged 6 to 18 months with dislocation; they are also used in children younger than 6 months when brace treatment is not effective.
Purpose
An automatic evaluation technology based on artificial intelligence and three‐dimensional ultrasonography (3D US) is proposed for hip US inspection plane selection. This study aimed to evaluate the consistency of the α angle as measured using 3D US to select the section plane and two‐dimensional ultrasonography (2D US) to manually select the Graf image, as well as to explore the feasibility of diagnosing developmental dysplasia of the hip (DDH) using 3D US and reconstruction technology.
Methods
A total of 216 infant hips were included and assessed by doctors using 3D US layer‐by‐layer. The researchers used a computer to identify the coronal images that met the Graf standard and then compared the αX values obtained with the αG values measured artificially by 2D US.
Results
Compared with 2D US, 3D US more clearly showed the relative positions of the ilium, ischia, and pubis. The measured α value of the optimal section obtained by 3D US showed good agreement with the measured α value of the standard Graf section.
Conclusion
The artificial intelligence and 3D US‐based automatic evaluation technology for section selection and inspection for DDH showed good agreement with the Graf method based on standard sections.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.