![]() Some studies have adopted the classical machine learning technique (i.e., logistic regression) to detect DDH from the clinical features extracted from two- and three-dimensional ultrasounds ( 15, 16). To our knowledge, there have been few attempts to apply machine learning to the detection of DDH using conventional radiography. Using conventional radiography, several studies have shown that machine learning can be helpful for the detection of fractures in skeletal bones and lesions on chest radiography ( 9, 14). Recent studies have shown the potential of deep learning in lesion detection and classification on radiologic images ( 8, 9, 10, 11, 12, 13). Recently, machine learning has made tremendous progress and is considered to be an emerging technique for classification of images ( 7). In particular, the interpreter's experience can significantly affect the diagnostic accuracy of conventional radiography. The diagnostic performance of conventional radiography for the detection of DDH in infants can vary according to several factors such as the patient's age, technical adequacy, and reader's experience ( 6). The anteroposterior (AP) view, frog-leg lateral view, or von Rosen view can be used for the diagnosis of DDH however, the hip AP view is usually sufficient for screening DDH ( 5). Conventional radiography is a useful diagnostic tool as it is readily available at a low cost. Sonography and conventional radiography are the most widely used screening tools. Clinical screening is one of the most widely used screening methods, but the results have low reproducibility ( 4). The recommended diagnostic methods differ according to the patient's age ( 3). For the normal development of the hip joint, articulation of the femoral head and acetabulum is essential thus, early diagnosis and treatment of DDH are important ( 1). The incidence of DDH is approximately 1.5 to 35 in 1000 persons, and the incidence of sonographic screening is 25 to 50 in 1000 persons ( 1, 2). Developmental dysplasia of the hip (DDH) is a spectrum of structural abnormalities ranging from mild dysplasia and subluxation to dislocation of the femoral head ( 1).
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |