Validity of machine learning algorithms for automatically extract growing rod length on radiographs in children with early-onset scoliosis.

The magnetically controlled growing rod technique is an effective surgical treatment for children who have early-onset scoliosis. The length of the instrumented growing rods is adjusted regularly to compensate for the normal growth of these patients. Manual measurement of rod length on posteroanterior spine radiographs is subjective and time-consuming. A machine learning (ML) system using a deep learning approach was developed to automatically measure the adjusted rod length. Three ML models-rod model, 58 mm model, and head-piece model-were developed to extract the rod length from radiographs. Three-hundred and eighty-seven radiographs were used for model development, and 60 radiographs with 118 rods were separated for final testing. The average precision (AP), the mean absolute difference (MAD) ± standard deviation (SD), and the inter-method correlation coefficient (ICC[2,1]) between the manual and artificial intelligence (AI) adjustment measurements were used to evaluate the developed method. The AP of the 3 models were 67.6%, 94.8%, and 86.3%, respectively. The MAD ± SD of the rod length change was 0.98 ± 0.88 mm, and the ICC[2,1] was 0.90. The average time to output a single rod measurement was 6.1 s. The developed AI provided an accurate and reliable method to detect the rod length automatically.

Automated Method for Growing Rod Length Measurement on Ultrasound Images in Children With Early Onset Scoliosis.

OBJECTIVE: To develop and validate machine learning algorithms to automatically extract the rod length of the magnetically controlled growing rod from ultrasound images (US) in a pilot study. METHODS: Two machine-learning (ML) models, called the "Boundary model" and "Rod model," were developed to identify specific rod segments on ultrasound images. The models were developed utilizing Mask Regional Convolutional Neural Networks (Mask RCNN). Ninety US images were acquired from 23 participants who had early onset scoliosis (EOS) surgeries; among those, 70 were used for model development, including training and validation, and 20 were used for testing by comparing the AI-based vs. manual measurements. RESULTS: The average precision (AP) of the ML models was 88.5% and 60.2%, respectively. The inter-method correlation coefficient (ICC) was 0.98, and the mean absolute difference ± standard deviation (MAD ± SD) between AI and manual measurements was 0.86 ± 1.0 mm. The Bland-Altman analysis showed no bias, and 90% of the data were within the 95% confidence interval. The automated method was reliable, accurate, and fast. Measurements were displayed in 4.6 seconds after the US image was inputted. CONCLUSION: This was the first AI-based method to measure the MCGR rod length on US images automatically.

Reliability and accuracy of scoliotic parameters on using a wireless handheld 3D ultrasound for children with adolescent idiopathic scoliosis: a pilot study.

PURPOSE: To report the accuracy and reliability of Cobb angle (CA), axial vertebral rotation (AVR), kyphotic and lordotic angles (KA and LA) measurements on using a new 3D ultrasound (US) system. METHODS: Forty participants (34 F, 6 M, aged 14.0 ± 2.3 years) were recruited. The first 20 participants were scanned by the validated US system and the new US system. The other 20 participants were scanned with the new US system only. Two raters (R1 and R2) performed the measurements: R1 has 10 years of experience in radiology but is new in ultrasound scoliosis, while R2 has 30 years of scoliosis experience. All US images were measured twice by R1, and once by R2. Forty posteroanterior and 30 lateral standing radiographs were obtained and measured once by R1. Statistical analysis consisted of mean absolute difference (MAD), intraclass correlation coefficient (ICC (2,1)), and Bland-Altman plots. RESULTS: R1 showed excellent intra-rater and inter-rater reliability for US measurements with ICCs(2,1) ≥ 0.91. The inter-method reliability was good between the two US systems for all parameters with ICCs(2,1) ≥ 0.85 and maximum MAD of 3.4°. The new US showed good reliability and accuracy compared to radiographs for CA, AVR and KA with ICCs(2,1) ≥ 0.81 and maximum MAD of 5.8°, but poor results for LA with ICCs(2,1) of 0.27-0.35 and MADs of 14.0°-15.4°. CONCLUSION: The new 3D US system showed good reliability and accuracy for CA, AVR and KA measurements, but a large measurement discrepancy on LA. A new measurement method for US LA may need to investigate.

Validation of an artificial intelligence-based method to automate Cobb angle measurement on spinal radiographs of children with adolescent idiopathic scoliosis.

BACKGROUND: Accurately measuring the Cobb angle on radiographs is crucial for diagnosis and treatment decisions for adolescent idiopathic scoliosis (AIS). However, manual Cobb angle measurement is time-consuming and subject to measurement variation, especially for inexperienced clinicians. AIM: This study aimed to validate a novel artificial-intelligence-based (AI) algorithm that automatically measures the Cobb angle on radiographs. DESIGN: This is a retrospective cross-sectional study. SETTING: The population of patients attended the Stollery Children's Hospital in Alberta, Canada. POPULATION: Children who: 1) were diagnosed with AIS, 2) were aged between 10 and 18 years old, 3) had no prior surgery, and 4) had a radiograph out of brace, were enrolled. METHODS: A total of 330 spinal radiographs were used. Among those, 130 were used for AI model development and 200 were used for measurement validation. Automatic Cobb angle measurements were validated by comparing them with manual ones measured by a rater with 20+ years of experience. Analysis was performed using the standard error of measurement (SEM), inter-method intraclass correlation coefficient (ICC2,1), and percentage of measurements within clinical acceptance (≤5°). Subgroup analysis was conducted by severity, region, and X-ray system to identify any systematic biases. RESULTS: The AI method detected 346 of 352 manually measured curves (mean±standard deviation: 24.7±9.5°), achieving 91% (316/346) of measurements within clinical acceptance. Excellent reliability was obtained with 0.92 ICC and 0.79° SEM. Comparable performance was found throughout all subgroups, and no systematic biases in performance affecting any subgroup were discovered. The algorithm measured each radiograph approximately 18s on average which is slightly faster than the estimated measurement time of an experienced rater. Radiographs taken by the EOS X-ray system were measured more quickly on average than those taken by a conventional digital X-ray system (10s vs. 26s). CONCLUSIONS: An AI-based algorithm was developed to measure the Cobb angle automatically on radiographs and yielded reliable measurements quickly. The algorithm provides detailed images on how the angles were measured, providing interpretability that can give clinicians confidence in the measurements. CLINICAL REHABILITATION IMPACT: Employing the algorithm in practice could streamline clinical workflow and optimize measurement accuracy and speed in order to inform AIS treatment decisions.

Reliability of measurements of a reflection coefficient index to indicate spinal bone strength on adolescents with idiopathic scoliosis (AIS): a pilot study.

PURPOSE: To investigate the test-retest, intra- and inter-rater reliabilities of an ultrasound (US) reflection coefficient (RC) index measured in a lumbar vertebra to reflect bone strength on children with AIS. METHODS: Fifty-eight participants (47F; 11M) were scanned by an US imager in standing position. Twenty-four were scanned twice for a test-retest study. The RC index measures the US signal reflected from L5 to indicate bone strength. Five measurements were obtained using three different methods: (i) the maximum RC (MRC) values on the left and right sides, (ii) the average RC (ARC) values on left and right sides, and (iii) the combined average RC (CARC) from both sides. Only rater 1 measured the 24 repeated US scans once. Raters 1 and 2 measured the RC index twice on all 58 images in 1 week apart. The intraclass correlation coefficient ICC [3, 1] for test-retest and ICC [2, 1] for intra- and inter-rater reliabilities as well as the standard error of measurements (SEM) were reported. RESULTS: The means of scan 1 versus scan 2 were 0.16 ± 0.08 versus 0.16 ± 0.07 for left-MRC, 0.17 ± 0.11 versus 0.18 ± 0.11 for right-MRC, 0.08 ± 0.04 versus 0.09 ± 0.04 for left-ARC, 0.09 ± 0.04 versus 0.09 ± 0.05 for right-ARC and 0.08 ± 0.04 versus 0.09 ± 0.03 for CARC and all ICC[3, 1] ≥ 0.77. Among these 5 approaches, the CARC provided the best intra-rater and inter-rater reliabilities with ICC [2, 1] ≥ 0.84 and SEM ≤ 0.01. CONCLUSIONS: The RC index could be measured repeatably and reliably. The high RC value may reduce the risk of progression of scoliosis.

Health-related quality of life with long-term retention of the PROSthesis of Antibiotic Loaded Acrylic Cement system following infection resolution in low demand patients.

BACKGROUND: The study purpose was to (1) evaluate health-related quality of life (HRQL) with the PROSthesis of Antibiotic Loaded Acrylic Cement (PROSTALAC) in situ for infected total hip arthroplasty (THA), (2) determine infection resolution, and (3) compare subjects who underwent second stage surgery with those who retained the PROSTALAC on a longer term basis. METHODS: Demographics, physical demand level, and comorbidities were recorded prospectively in 29 subjects followed to at least 24 months after initial PROSTALAC insertion. HRQL was evaluated using the Western Ontario McMaster Osteoarthritis Index (WOMAC) and RAND 36-Item Health Survey. Infection resolution was determined using a pre-specified clinical definition. RESULTS: Twenty-five of 29 (86%) subjects' infections resolved. Three subjects died, of whom two had resolved infections. For survivors, 22/26 (85%) completed HRQL evaluations. After PROSTALAC insertion, pain and function improved within 3-6 months and was retained at 24 months. Of those followed to 24 months, 7/22 (32%) subjects underwent second stage surgery. They were higher physical demand subjects ( p = 0.03) than those not undergoing second stage surgery. We found no difference in WOMAC scores at 24 months between those who underwent second stage surgery and those who retained the PROSTALAC ( p > 0.32). DISCUSSION: The PROSTALAC system for THA appears to allow acceptable HRQL while in situ for at least 2 years in low physical demand patients. Subjects with higher physical demand levels are more likely to undergo second stage surgery. CONCLUSION: Further evaluation is required to determine whether longer term PROSTALAC retention may be appropriate for specific patient groups.