Ultrasound Imaging of Hip Displacement in Children With Cerebral Palsy.

OBJECTIVE: An approach to estimation of hip displacement on ultrasound (US) images is described. Its accuracy is validated through numerical simulation, an in vitro study with 3-D-printed hip phantoms and pilot in vivo data. METHODS: A diagnostic index, migration percentage (MP), is defined by the ratio of acetabulum-femoral head distance to femoral head width. The acetabulum-femoral head distance could be measured directly on hip US images, while the femoral head width was estimated from the diameter of a best-fit circle. Simulation was performed to evaluate the accuracy of circle fitting with noiseless and noisy data. Surface roughness was also considered. Nine hip phantoms (three different sizes of femur head × three MP values) and 10 US hip images were used in this study. RESULTS: The maximum diameter error was 16.1 ± 8.5% when the roughness and noise were 20% of the original radius and 20% of the wavelet peak, respectively. In the phantom study, the percentage errors of MPs between the 3-D-design US and X-ray US were 0.3%-6.6% and 0.0%-5.7%, respectively. From the pilot clinical trial, the mean absolute difference between the X-ray-US MPs was 3.5 ± 2.8% (1%-9%). CONCLUSION: This study indicates that the US method can be used to evaluate hip displacement in children.

Investigation of ultrasonic soft tissue-bone reflection coefficients correlating with curve severity in children with adolescent idiopathic scoliosis.

Adolescent idiopathic scoliosis (AIS) is a three-dimensional curvature of spine. Children with AIS and low bone quality have higher chance to get curve progression leading to bigger spinal curvature. In addition, bone quality affects acoustic impedance of bone, thus influencing the reflection coefficient of ultrasound signal from the soft tissue-bone interface. This study aimed to estimate the bone quality of AIS patients based on the reflection coefficients to determine the correlation of the bone quality with curve severity. A simple bone model was used to develop an equation to calculate the reflection coefficient value. Experiments were conducted on five different phantoms. Acrylic was used to design a vertebral shape to study the effect of surface roughness and inclination, including: smooth flat surface (SFS), smooth curved surface (SCS), rough curved surface (RCS), and the rough curved inclined surface (RCIS). A clinical study with 37 AIS patients were recruited. The estimated reflection coefficient values of plate phantoms agreed well with the predicted values and the maximum error was 6.7%. The reflection coefficients measured from the acrylic-water interface for the SFS, SCS, RCS, RCIS (3° and 5°) were 0.37, 0.33, 0.28, (0.23 and 0.12), respectively. The surface roughness and inclination increased the reflection loss. From the clinical data, the average reflection coefficients for children with AIS were 0.11 and 0.07 for the mild curve group and the moderate curve group, respectively. A moderate linear correlation was found between the reflection coefficients and curve severity (r2 = 0.3). Patients with lower bone quality have observed to have larger spinal curvature.

2D Ultrasound Validation to Assess the Accuracy of Hip Displacement Measurement: A Phantom Study.

Hip displacement is a common orthopedic abnormality in children with cerebral palsy and is assessed on anteroposterior pelvic radiographs during surveillance. Repeated exposure to ionizing radiation is a major concern of cancer risks for children. Ultrasound (US) has been proposed to image the hips. The severity of hip displacement is measured by the Reimers' migration percentage (MP), which is calculated by the ratio of the femoral head distance from the acetabulum to the width of the femoral head. Methods have been published to estimate MP from the US hip images in literature; however, validation for accuracy has not been reported. This study aimed to determine the accuracy of the 2D ultrasound techniques using two 3D printed hip phantoms with known MP values. The MPs estimated from the US images were compared with those measured from the X-ray images. Based on the experimental results, the US measurements had a maximum absolute discrepancy of 2.2% as compared to 9.8% from the X-ray measurements for the MP. The study on phantoms has showed the proposed US approach is promising with better accuracy and without ionizing radiation.Clinical Relevance - If the accuracy is proved to be at least as good as the current X-ray gold standard, the proposed US method will provide a modality of choice to pediatric patients for hip displacement diagnostics and hip surveillance, especially those with cerebral palsy. The method will be free of ionizing radiation and therefore significantly improve the pediatric patient care.

Assessment of hip displacement in children with cerebral palsy using machine learning approach.

Manual measurements of migration percentage (MP) on pelvis radiographs for assessing hip displacement are subjective and time consuming. A deep learning approach using convolution neural networks (CNNs) to automatically measure the MP was proposed. The pre-trained Inception ResNet v2 was fine tuned to detect locations of the eight reference landmarks used for MP measurements. A second network, fine-tuned MobileNetV2, was trained on the regions of interest to obtain more precise landmarks' coordinates. The MP was calculated from the final estimated landmarks' locations. A total of 122 radiographs were divided into 57 for training, 10 for validation, and 55 for testing. The mean absolute difference (MAD) and intra-class correlation coefficient (ICC [2,1]) of the comparison for the MP on 110 measurements (left and right hips) were 4.5 [Formula: see text] 4.3% (95% CI, 3.7-5.3%) and 0.91, respectively. Sensitivity and specificity were 87.8% and 93.4% for the classification of hip displacement (MP-threshold of 30%), and 63.2% and 94.5% for the classification of surgery-needed hips (MP-threshold of 40%). The prediction results were returned within 5 s. The developed fine-tuned CNNs detected the landmarks and provided automatic MP measurements with high accuracy and excellent reliability, which can assist clinicians to diagnose hip displacement in children with CP.