The diagnosis of developmental dysplasia of the hip (DDH) is challenging owing to extensive variation in paediatric pelvic anatomy. Artificial intelligence (AI) may represent an effective diagnostic tool for DDH. Here, we aimed to develop an anteroposterior pelvic radiograph deep learning system for diagnosing DDH in children and analyze the feasibility of its application. In total, 10,219 anteroposterior pelvic radiographs were retrospectively collected from April 2014 to December 2018. Clinicians labelled each radiograph using a uniform standard method. Radiographs were grouped according to age and into ‘dislocation’ (dislocation and subluxation) and ‘non-dislocation’ (normal cases and those with dysplasia of the acetabulum) groups based on clinical diagnosis. The deep learning system was trained and optimized using 9,081 radiographs; 1,138 test radiographs were then used to compare the diagnoses made by deep learning system and clinicians. The accuracy of the deep learning system was determined using a receiver operating characteristic curve, and the consistency of acetabular index measurements was evaluated using Bland-Altman plots.Aims
Methods
In 11 paediatric patients (seven girls and four
boys, from 12 to 15 years old) with unilateral obligatory patellar dislocation
and ligamentous laxity vastus medialis advancement, lateral release,
partial patellar ligament transposition and Galeazzi semitendinosus
tenodesis was undertaken to stabilise the patella. The diagnostic criterion
for ligamentous laxity was based on the Beighton scale. Outcomes
were evaluated radiologically and functionally by measurement of
the range of knee movement and isokinetic testing. The evaluation
also included the Lysholm knee scale. Follow-up studies took place
at a mean of 8.1 years (5 to 15) post-operatively. Normal patellar tracking without any recurrence of dislocation
was obtained in ten out of 11 patients. Pain related to vigorous
activity was reported by nine patients. Compared with the opposite
normal side, the isokinetic tests revealed a statistically significant
decrease in the maximal torque values for the affected quadriceps
muscle (p = 0.003 and p = 0.004), but no difference between the
knee flexors (for angular velocities of 60°/s and 180°/s) (p = 0.858
and p = 0.79). The applied surgical technique generally prevents the recurrence
of the disorder in children with habitual patellar dislocation and
ligamentous laxity. Quadriceps muscle weakness can be expected to
occur post-operatively, Cite this article:
There were 47 patients with congenital muscular torticollis who underwent operative release. After a mean follow-up of 74 months (60 to 90), they were divided into two groups, one aged one to four years (group 1) and the other aged five to 16 years (group 2). The outcomes were assessed by evaluating the following parameters: deficits of lateral flexion and rotation, craniofacial asymmetry, surgical scarring, residual contracture, subjective evaluation and degree of head tilt. The craniofacial asymmetry, residual contracture, subjective evaluation and overall scores were similar in both groups. However, group 2 showed superior results to group 1 in terms of the deficits of movement, surgical scarring and degree of head tilt. It is recommended that operative treatment for congenital muscular torticollis is postponed until the patient can comply successfully with post-operative bracing and an exercise programme.
The bicompartmental acetabulum is one of the morphological changes which may be seen in children with Legg-Calvé-Perthes’ disease. Three-dimensional CT and MRI were used to analyse the detailed morphology of the acetabulum with special reference to its inner surface, in 16 patients with Perthes’ disease and a bicompartmental acetabulum. The bicompartmental appearance was seen on the coronal plane image through the acetabular fossa. The lunate surface was seen to grow laterally resulting in an increased mediolateral thickness of the triradiate cartilage. On the horizontal plane images, the acetabular fossa had deepened and had a distinct prominence at its posterior border. The combination of these morphological changes resulted in a bicompartmental appearance on plain radiography. Acetabular bicompartmentalisation appears to be the result of an imbalance of growth between the cartilage-covered lunate surface and the cartilage-devoid acetabular fossa.
