Automated Analysis of Alignment in Long-Leg Radiographs by Using a Fully Automated Support System Based on Artificial Intelligence

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade

This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.

Deep-Learning Automation of Preoperative Radiographic Parameters Associated With Early Periprosthetic Femur Fracture After Total Hip Arthroplasty

BACKGROUND

The radiographic assessment of bone morphology impacts implant selection and fixation type in total hip arthroplasty (THA) and is important to minimize the risk of periprosthetic femur fracture (PFF). We utilized a deep-learning algorithm to automate femoral radiographic parameters and determined which automated parameters were associated with early PFF.

METHODS

Radiographs from a publicly available database and from patients undergoing primary cementless THA at a high-volume institution (2016 to 2020) were obtained. A U-Net algorithm was trained to segment femoral landmarks for bone morphology parameter automation. Automated parameters were compared against that of a fellowship-trained surgeon and compared in an independent cohort of 100 patients who underwent THA (50 with early PFF and 50 controls matched by femoral component, age, sex, body mass index, and surgical approach).

RESULTS

On the independent cohort, the algorithm generated 1,710 unique measurements for 95 images (5% lesser trochanter identification failure) in 22 minutes. Medullary canal width, femoral cortex width, canal flare index, morphological cortical index, canal bone ratio, and canal calcar ratio had good-to-excellent correlation with surgeon measurements (Pearson's correlation coefficient: 0.76 to 0.96). Canal calcar ratios (0.43 ± 0.08 versus 0.40 ± 0.07) and canal bone ratios (0.39 ± 0.06 versus 0.36 ± 0.06) were higher (P < .05) in the PFF cohort when comparing the automated parameters.

CONCLUSIONS

Deep-learning automated parameters demonstrated differences in patients who had and did not have early PFF after cementless primary THA. This algorithm has the potential to complement and improve patient-specific PFF risk-prediction tools.

Developing a Computer Vision Model to Automate Quantitative Measurement of Hip-Knee-Ankle Angle in Total Hip and Knee Arthroplasty Patients

BACKGROUND

Increasing deformity of the lower extremities, as measured by the hip-knee-ankle angle (HKAA), is associated with poor patient outcomes after total hip and knee arthroplasty (THA, TKA). Automated calculation of HKAA is imperative to reduce the burden on orthopaedic surgeons. We proposed a detection-based deep learning (DL) model to calculate HKAA in THA and TKA patients and assessed the agreement between DL-derived HKAAs and manual measurement.

METHODS

We retrospectively identified 1,379 long-leg radiographs (LLRs) from patients scheduled for THA or TKA within an academic medical center. There were 1,221 LLRs used to develop the model (randomly split into 70% training, 20% validation, and 10% held-out test sets); 158 LLRs were considered "difficult," as the femoral head was difficult to distinguish from surrounding tissue. There were 2 raters who annotated the HKAA of both lower extremities, and inter-rater reliability was calculated to compare the DL-derived HKAAs with manual measurement within the test set.

RESULTS

The DL model achieved a mean average precision of 0.985 on the test set. The average HKAA of the operative leg was 173.05 ± 4.54°; the nonoperative leg was 175.55 ± 3.56°. The inter-rater reliability between manual and DL-derived HKAA measurements on the operative leg and nonoperative leg indicated excellent reliability (intraclass correlation (2,k) = 0.987 [0.96, 0.99], intraclass correlation (2, k) = 0.987 [0.98, 0.99, respectively]). The standard error of measurement for the DL-derived HKAA for the operative and nonoperative legs was 0.515° and 0.403°, respectively.

CONCLUSIONS

A detection-based DL algorithm can calculate the HKAA in LLRs and is comparable to that calculated by manual measurement. The algorithm can detect the bilateral femoral head, knee, and ankle joints with high precision, even in patients where the femoral head is difficult to visualize.

Development of an automatic surgical planning system for high tibial osteotomy using artificial intelligence

BACKGROUND

This study proposed an automatic surgical planning system for high tibial osteotomy (HTO) using deep learning-based artificial intelligence and validated its accuracy. The system simulates osteotomy and measures lower-limb alignment parameters in pre- and post-osteotomy simulations.

METHODS

A total of 107 whole-leg standing radiographs were obtained from 107 patients who underwent HTO. First, the system detected anatomical landmarks on radiographs. Then, it simulated osteotomy and automatically measured five parameters in pre- and post-osteotomy simulation (hip knee angle [HKA], weight-bearing line ratio [WBL ratio], mechanical lateral distal femoral angle [mLDFA], mechanical medial proximal tibial angle [mMPTA], and mechanical lateral distal tibial angle [mLDTA]). The accuracy of the measured parameters was validated by comparing them with the ground truth (GT) values given by two orthopaedic surgeons.

RESULTS

All absolute errors of the system were within 1.5° or 1.5%. All inter-rater correlation confidence (ICC) values between the system and GT showed good reliability (>0.80). Excellent reliability was observed in the HKA (0.99) and WBL ratios (>0.99) for the pre-osteotomy simulation. The intra-rater difference of the system exhibited excellent reliability with an ICC value of 1.00 for all lower-limb alignment parameters in pre- and post-osteotomy simulations. In addition, the measurement time per radiograph (0.24 s) was considerably shorter than that of an orthopaedic surgeon (118 s).

CONCLUSION

The proposed system is practically applicable because it can measure lower-limb alignment parameters accurately and quickly in pre- and post-osteotomy simulations. The system has potential applications in surgical planning systems.

Lower Extremity Growth according to AI Automated Femorotibial Length Measurement on Slot-Scanning Radiographs in Pediatric Patients

Background Commonly used pediatric lower extremity growth standards are based on small, dated data sets. Artificial intelligence (AI) enables creation of updated growth standards. Purpose To train an AI model using standing slot-scanning radiographs in a racially diverse data set of pediatric patients to measure lower extremity length and to compare expected growth curves derived using AI measurements to those of the conventional Anderson-Green method. Materials and Methods This retrospective study included pediatric patients aged 0-21 years who underwent at least two slot-scanning radiographs in routine clinical care between August 2015 and February 2022. A Mask Region-based Convolutional Neural Network was trained to segment the femur and tibia on radiographs and measure total leg, femoral, and tibial length; accuracy was assessed with mean absolute error. AI measurements were used to create quantile polynomial regression femoral and tibial growth curves, which were compared with the growth curves of the Anderson-Green method for coverage based on the central 90% of the estimated growth distribution. Results In total, 1874 examinations in 523 patients (mean age, 12.7 years ± 2.8 [SD]; 349 female patients) were included; 40% of patients self-identified as White and not Hispanic or Latino, and the remaining 60% self-identified as belonging to a different racial or ethnic group. The AI measurement training, validation, and internal test sets included 114, 25, and 64 examinations, respectively. The mean absolute errors of AI measurements of the femur, tibia, and lower extremity in the test data set were 0.25, 0.27, and 0.33 cm, respectively. All 1874 examinations were used to generate growth curves. AI growth curves more accurately represented lower extremity growth in an external test set (n = 154 examinations) than the Anderson-Green method (90% coverage probability: 86.7% [95% CI: 82.9, 90.5] for AI model vs 73.4% [95% CI: 68.4, 78.3] for Anderson-Green method; χ2 test, P < .001). Conclusion Lower extremity growth curves derived from AI measurements on standing slot-scanning radiographs from a diverse pediatric data set enabled more accurate prediction of pediatric growth. © RSNA, 2024 Supplemental material is available for this article.

Fully automated assessment of the knee alignment on long leg radiographs following corrective knee osteotomies in patients with valgus or varus deformities

INTRODUCTION

The assessment of the knee alignment on long leg radiographs (LLR) postoperative to corrective knee osteotomies (CKOs) is highly dependent on the reader's expertise. Artificial Intelligence (AI) algorithms may help automate and standardise this process. The study aimed to analyse the reliability of an AI-algorithm for the evaluation of LLRs following CKOs.

MATERIALS AND METHODS

In this study, we analysed a validation cohort of 110 postoperative LLRs from 102 patients. All patients underwent CKO, including distal femoral (DFO), high tibial (HTO) and bilevel osteotomies. The agreement between manual measurements and the AI-algorithm was assessed for the mechanical axis deviation (MAD), hip knee ankle angle (HKA), anatomical-mechanical-axis-angle (AMA), joint line convergence angle (JLCA), mechanical lateral proximal femur angle (mLPFA), mechanical lateral distal femoral angle (mLDFA), mechanical medial proximal tibia angle (mMPTA) and mechanical lateral distal tibia angle (mLDTA), using the intra-class-correlation (ICC) coefficient between the readers, each reader and the AI and the mean of the manual reads and the AI-algorithm and Bland-Altman Plots between the manual reads and the AI software for the MAD, HKA, mLDFA and mMPTA.

RESULTS

In the validation cohort, the AI software showed excellent agreement with the manual reads (ICC: 0.81-0.99). The agreement between the readers (Inter-rater) showed excellent correlations (ICC: 0.95-0. The mean difference in the DFO group for the MAD, HKA, mLDFA and mMPTA were 0.50 mm, - 0.12°, 0.55° and 0.15°. In the HTO group the mean difference for the MAD, HKA, mLDFA and mMPTA were 0.36 mm, - 0.17°, 0.57° and 0.08°, respectively. Reliable outputs were generated in 95.4% of the validation cohort.

CONCLUSION

 he application of AI-algorithms for the assessment of lower limb alignment on LLRs following CKOs shows reliable and accurate results.

LEVEL OF EVIDENCE

Diagnostic Level III.

Full-length radiograph based automatic musculoskeletal modeling using convolutional neural network

Full-length radiographs contain information from which many anatomical parameters of the pelvis, femur, and tibia may be derived, but only a few anatomical parameters are used for musculoskeletal modeling. This study aimed to develop a fully automatic algorithm to extract anatomical parameters from full-length radiograph to generate a musculoskeletal model that is more accurate than linear scaled one. A U-Net convolutional neural network was trained to segment the pelvis, femur, and tibia from the full-length radiograph. Eight anatomic parameters (six for length and width, two for angles) were automatically extracted from the bone segmentation masks and used to generate the musculoskeletal model. Sørensen-Dice coefficient was used to quantify the consistency of automatic bone segmentation masks with manually segmented labels. Maximum distance error, root mean square (RMS) distance error and Jaccard index (JI) were used to evaluate the geometric accuracy of the automatically generated pelvis, femur and tibia models versus CT bone models. Mean Sørensen-Dice coefficients for the pelvis, femur and tibia 2D segmentation masks were 0.9898, 0.9822 and 0.9786, respectively. The algorithm-driven bone models were closer to the 3D CT bone models than the scaled generic models in geometry, with significantly lower maximum distance error (28.3 % average decrease from 24.35 mm) and RMS distance error (28.9 % average decrease from 9.55 mm) and higher JI (17.2 % average increase from 0.46) (P < 0.001). The algorithm-driven musculoskeletal modeling (107.15 ± 10.24 s) was faster than the manual process (870.07 ± 44.79 s) for the same full-length radiograph. This algorithm provides a fully automatic way to generate a musculoskeletal model from full-length radiograph that achieves an approximately 30 % reduction in distance errors, which could enable personalized musculoskeletal simulation based on full-length radiograph for large scale OA populations.

How AI May Transform Musculoskeletal Imaging

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Artificial intelligence-based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility

PURPOSE

The aim of this study was to investigate the performance of an artificial intelligence (AI)-based software for fully automated analysis of leg alignment pre- and postoperatively after high tibial osteotomy (HTO) on long-leg radiographs (LLRs).

METHODS

Long-leg radiographs of 95 patients with varus malalignment that underwent medial open-wedge HTO were analyzed pre- and postoperatively. Three investigators and an AI software using deep learning algorithms (LAMA™, ImageBiopsy Lab, Vienna, Austria) evaluated the hip-knee-ankle angle (HKA), mechanical axis deviation (MAD), joint line convergence angle (JLCA), medial proximal tibial angle (MPTA), and mechanical lateral distal femoral angle (mLDFA). All measurements were performed twice and the performance of the AI software was compared with individual human readers using a Bayesian mixed model. In addition, the inter-observer intraclass correlation coefficient (ICC) for inter-observer reliability was evaluated by comparing measurements from manual readers. The intra-reader variability for manual measurements and the AI-based software was evaluated using the intra-observer ICC.

RESULTS

Initial varus malalignment was corrected to slight valgus alignment after HTO. Measured by the AI algorithm and manually HKA (5.36° ± 3.03° and 5.47° ± 2.90° to - 0.70 ± 2.34 and - 0.54 ± 2.31), MAD (19.38 mm ± 11.39 mm and 20.17 mm ± 10.99 mm to - 2.68 ± 8.75 and - 2.10 ± 8.61) and MPTA (86.29° ± 2.42° and 86.08° ± 2.34° to 91.6 ± 3.0 and 91.81 ± 2.54) changed significantly from pre- to postoperative, while JLCA and mLDFA were not altered. The fully automated AI-based analyses showed no significant differences for all measurements compared with manual reads neither in native preoperative radiographs nor postoperatively after HTO. Mean absolute differences between the AI-based software and mean manual observer measurements were 0.5° or less for all measurements. Inter-observer ICCs for manual measurements were good to excellent for all measurements, except for JLCA, which showed moderate inter-observer ICCs. Intra-observer ICCs for manual measurements were excellent for all measurements, except for JLCA and for MPTA postoperatively. For the AI-aided analyses, repeated measurements showed entirely consistent results for all measurements with an intra-observer ICC of 1.0.

CONCLUSIONS

The AI-based software can provide fully automated analyses of native long-leg radiographs in patients with varus malalignment and after HTO with great accuracy and reproducibility and could support clinical workflows.

LEVEL OF EVIDENCE

Diagnostic study, Level III.

A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images

During clinical evaluation of patients and planning orthopedic treatments, the periodic assessment of lower limb alignment is critical. Currently, physicians use physical tools and radiographs to directly observe limb alignment. However, this process is manual, time consuming, and prone to human error. To this end, a deep-learning (DL)-based system was developed to automatically, rapidly, and accurately detect lower limb alignment by using anteroposterior standing X-ray medical imaging data of lower limbs. For this study, leg radiographs of non-overlapping 770 patients were collected from January 2016 to August 2020. To precisely detect necessary landmarks, a DL model was implemented stepwise. A radiologist compared the final calculated measurements with the observations in terms of the concordance correlation coefficient (CCC), Pearson correlation coefficient (PCC), and intraclass correlation coefficient (ICC). Based on the results and 250 frontal lower limb radiographs obtained from 250 patients, the system measurements for 16 indicators revealed superior reliability (CCC, PCC, and ICC ≤ 0.9; mean absolute error, mean square error, and root mean square error ≥ 0.9) for clinical observations. Furthermore, the average measurement speed was approximately 12 s. In conclusion, the analysis of anteroposterior standing X-ray medical imaging data by the DL-based lower limb alignment diagnostic support system produces measurement results similar to those obtained by radiologists.

Automated correction angle calculation in high tibial osteotomy planning

High tibial osteotomy correction angle calculation is a process that is usually performed manually or in a semi-automated way. The process, according to the Miniaci method, is divided into several stages to find specific points: the center of the femoral head, the edges of the tibial plateau, the Fujisawa point, the center of the ankle joint, and the Hinge point. In this paper, we proposed an end-to-end approach that consists of different techniques for finding each point. We used YOLOv4 to detect regions of interest. To identify the center of the femoral head, we used the YOLOv4 and the Hough transform. For the other points, we used a combined method of YOLOv4 with the ASM/AAM algorithm and YOLOv4 with image processing algorithms. Our fully-automated method achieved a mean error rate of 0.5[Formula: see text] (0[Formula: see text]-2.76[Formula: see text]) ICC 0.99 (0.98-0.99) 95% CI on our own dataset of standing long-leg Anterior Posterior view X-rays. This might be the first method that automatically calculates the correction angle of high tibial osteotomy.

Ceiling Effect of the Combined Norwegian and Danish Knee Ligament Registers Limits Anterior Cruciate Ligament Reconstruction Outcome Prediction

BACKGROUND

Clinical tools based on machine learning analysis now exist for outcome prediction after primary anterior cruciate ligament reconstruction (ACLR). Relying partly on data volume, the general principle is that more data may lead to improved model accuracy.

PURPOSE/HYPOTHESIS

The purpose was to apply machine learning to a combined data set from the Norwegian and Danish knee ligament registers (NKLR and DKRR, respectively), with the aim of producing an algorithm that can predict revision surgery with improved accuracy relative to a previously published model developed using only the NKLR. The hypothesis was that the additional patient data would result in an algorithm that is more accurate.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

Machine learning analysis was performed on combined data from the NKLR and DKRR. The primary outcome was the probability of revision ACLR within 1, 2, and 5 years. Data were split randomly into training sets (75%) and test sets (25%). There were 4 machine learning models examined: Cox lasso, random survival forest, gradient boosting, and super learner. Concordance and calibration were calculated for all 4 models.

RESULTS

The data set included 62,955 patients in which 5% underwent a revision surgical procedure with a mean follow-up of 7.6 ± 4.5 years. The 3 nonparametric models (random survival forest, gradient boosting, and super learner) performed best, demonstrating moderate concordance (0.67 [95% CI, 0.64-0.70]), and were well calibrated at 1 and 2 years. Model performance was similar to that of the previously published model (NKLR-only model: concordance, 0.67-0.69; well calibrated).

CONCLUSION

Machine learning analysis of the combined NKLR and DKRR enabled prediction of the revision ACLR risk with moderate accuracy. However, the resulting algorithms were less user-friendly and did not demonstrate superior accuracy in comparison with the previously developed model based on patients from the NKLR alone, despite the analysis of nearly 63,000 patients. This ceiling effect suggests that simply adding more patients to current national knee ligament registers is unlikely to improve predictive capability and may prompt future changes to increase variable inclusion.

Deep Learning Phenotype Automation and Cohort Analyses of 1,946 Knees Using the Coronal Plane Alignment of the Knee Classification

BACKGROUND

The Coronal Plane Alignment of the Knee (CPAK) classification allows for knee phenotyping which can be used in preoperative planning prior to total knee arthroplasty. We used deep learning (DL) to automate knee phenotyping and analyzed CPAK distributions in a large patient cohort.

METHODS

Patients who had full-limb radiographs from a large arthritis database were retrospectively included. A DL algorithm was developed to automate CPAK knee alignment parameters including the lateral distal femoral, medial proximal tibia, hip-knee-ankle, and joint line obliquity angles. The algorithm was validated against a fellowship-trained arthroplasty surgeon. After applying the algorithm in a large patient cohort (n = 1,946 knees), the distribution of CPAK was compared across patient sex and baseline Kellgren-Lawrence (KL) scores.

RESULTS

There was no significant difference in the CPAK angles (n = 140, P = .66-.98, inter-class correlation coefficient = 0.89-0.91) or phenotype classifications made by the algorithm and surgeon (P = .96). The deep learning algorithm measured the entire cohort (n = 1,946 knees, mean age 61 years [range, 46 to 80 years], 51% women) in < 5 hours. Women had more valgus CPAK phenotypes than men (P < .05). Patients who had higher KL grades at baseline (2 to 4) were more varus using the CPAK classification compared to lower KL grades (0 to 1) (P < .05).

CONCLUSION

We applied an accurate, automated DL algorithm on a large patient cohort to determine knee phenotypes, helping to validate and strengthen the CPAK classification system. Analyses revealed that sex-specific and major bone loss adjustments may need to be accounted for when using this system.

Orthopedic surgeons’ attitudes and expectations toward artificial intelligence: A national survey study

Background/Aim: There is a lack of understanding of artificial intelligence (AI) among orthopedic surgeons regarding how it can be used in their clinical practices. This study aimed to evaluate the attitudes of orthopedic surgeons regarding the application of AI in their practices. Methods: A cross-sectional study was conducted in Turkey among 189 orthopedic surgeons between November 2021 and February 2022. An electronic survey was designed using the SurveyMonkey platform. The questionnaire included six subsections related to AI usefulness in clinical practice and participants’ knowledge about the topic. It also surveyed their acceptance level of learning, concerns about the potential risks of AI, and implementation of this technology into their daily practice Results: A total of 33.9% of the participants indicated that they were familiar with the concept of AI, while 82.5% planned to learn about artificial intelligence in the coming years. Most of the surgeons (68.3%) reported not using AI in their daily practice. The activities of orthopedic associations focused on AI were insufficient according to 77.2% of participants. Orthopedic surgeons expressed concern over AI involvement in the future regarding an insensitive and nonempathic attitude toward the patient (53.5%). A majority of respondents (80.4%) indicated that AI was most feasible in extremity reconstruction. Pelvis fractures were found in the region where the AI system is most needed in the fracture classification (68.7%). Conclusion: Most of the respondents did not use AI in their daily clinical practice; however, almost all surgeons had plans to learn about artificial intelligence in the future. There was a need to improve orthopedic associations’ activities focusing on artificial intelligence. Furthermore, new research including the medical ethics issues of the field will be needed to allay the surgeons’ worries. The classification system of pelvic fractures and sub-branches of orthopedic extremity reconstruction were the most feasible areas for AI systems. We believe that this study will serve as a guide for all branches of orthopedic medicine.

Radiographic findings involved in knee osteoarthritis progression are associated with pain symptom frequency and baseline disease severity: a population-level analysis using deep learning

PURPOSE

To (1) develop a deep-learning (DL) algorithm capable of producing limb-length and knee-alignment measurements, and (2) determine the association between limb-length discrepancy (LLD), coronal-plane alignment, osteoarthritis (OA) severity, and patient-reported knee pain.

METHODS

A multicenter, prospective patient cohort from the Osteoarthritis Initiative between 2004 and 2015 with full-limb standing radiographs at 12 month follow-up was included. A convolutional neural network was developed to automate measurements of the hip-knee-ankle (HKA) angle, femur, and tibia lengths, and LLD. At 12 month follow-up, patients reported their frequency of knee pain since enrollment and current level of knee pain.

RESULTS

A total of 1011 patients (2022 knees, 52.3% female) with an average age of 61.2 ± 9.0 years were included. The algorithm performed 12,312 measurements in 5.4 h. ICC values of HKA and LLD ranged between 0.87 and 1.00 when compared against trained radiologist measurements. Knees producing pain most days of the month were significantly more varus (mean HKA:- 3.9° ± 2.8°) or valgus (mean HKA:2.8° ± 2.3°) compared to knees that did not produce any pain (p < 0.05). In varus knees, those producing pain on most days were part of the shorter limb compared to nonpainful knees (p < 0.05). Baseline Kellgren-Lawrence grade was significantly associated with HKA magnitude, LLD, and pain frequency at 12 month follow-up (p < 0.05 all).

CONCLUSION

A higher frequency of knee pain was associated with more severe coronal plane deformity, with valgus deviation being one degree less than varus on average, suggesting that the knee tolerates less valgus deformation before symptoms become more consistent. Knee pain frequency was also associated with greater LLD and baseline KL grade, suggesting an association between radiographically apparent joint degeneration and pain frequency.

LEVEL OF EVIDENCE

IV case series.

The German Arthroscopy Registry DART: what has happened after 5 years?

PURPOSE

The German Arthroscopy Registry (DART) has been initiated in 2017 with the aim to collect real-life data of patients undergoing knee, shoulder, hip or ankle surgery. The purpose of this study was to present an overview of the current status and the collected data thus far.

METHODS

Data entered between 11/2017 and 01/2022 were analyzed. The number of cases (each case is defined as a single operation with or without concomitant procedures) entered for each joint, follow-up rates and trends between different age groups (18-29 years, 30-44 years, 45-64 years,  ≥ 65 years) and across genders, and quality of life improvement (pre- vs. 1 year postoperative EQ visual analogue scale [EQ-VAS]) for frequently performed procedures (medial meniscus repair [MMR] vs. rotator cuff repair [RCR] vs. microfracturing of the talus [MFX-T]) were investigated.

RESULTS

Overall, 6651 cases were entered into DART, forming three distinct modules classified by joint (5370 knee, 1053 shoulder and 228 ankle cases). The most commonly entered procedures were: knee: partial medial meniscectomy (n = 2089), chondroplasty (n = 1389), anterior cruicate ligament reconstruction with hamstring autograft (n = 880); shoulder: sub acromial decompression (n = 631), bursectomy (n = 385), RCR (n = 359); ankle: partial synovectomy (n = 117), tibial osteophyte resection (n = 72), loose body removal (n = 48). In the knee and shoulder modules, middle-aged patients were the predominant age group, whereas in the ankle module, the youngest age group was the most frequent one. The two oldest age groups had the highest 1-year follow-up rates across all modules. In the knee and shoulder module, 1-year follow-up rates were higher in female patients, whereas follow-up rates were higher in male patients in the ankle module. From pre- to 1-year postoperative, MFX-T (EQ-VAS: 50.0 [25-75% interquartile range: 31.8-71.5] to 75.0 [54.3-84.3]; ∆ + 25.0) led to a comparably larger improvement in quality of life than did MMR (EQ-VAS: 70.0 [50.0-80.0] to 85.0 [70.0-94.0]; ∆ + 15.0) or RCR (EQ-VAS: 67.0 [50.0-80.0] to 85.0 [70.0-95.0]; ∆ + 18.0).

CONCLUSION

DART has been sufficiently established and collects high-quality patient-related data with satisfactory follow-up allowing for a comprehensive analysis of the collected data. The current focus lies on improving patient enrolment and follow-up rates as well as initiating the hip module.

Development and testing of a new application for measuring motion at the cervical spine

Background

Cervical myelopathy is a progressive disease, and early detection and treatment contribute to prognosis. Evaluation of cervical intervertebral instability by simple X-ray is used in clinical setting and the information about instability is important to understand the cause of myelopathy, but evaluation of the intervertebral instability by X-ray is complicated. To reduce the burden of clinicians, a system that automatically measures the range of motion was developed by comparing the flexed and extended positions in the lateral view of a simple X-ray of the cervical spine. The accuracy of the system was verified by comparison with spine surgeons and residents to determine whether the system could withstand actual use.

Methods

An algorithm was created to recognize the four corners of the vertebral bodies in a lateral cervical spine X-ray image, and a system was constructed to automatically measure the range of motion between each vertebra by comparing X-ray images of the cervical spine in extension and flexion. Two experienced spine surgeons and two residents performed the study on the remaining 23 cases. Cervical spine range of motion was measured manually on X-ray images and compared with automatic measurement by this system.

Results

Of a total of 322 cervical vertebrae in 46 images, 313 (97%) were successfully estimated by our learning model. The mean intersection over union value for all the 46-test data was 0.85. The results of measuring the CRoM angle with the proposed cervical spine motion angle measurement system showed that the mean error from the true value was 3.5° and the standard deviation was 2.8°. The average standard deviations for each measurement by specialist and residents are 2.9° and 3.2°.

Conclusions

A system for measuring cervical spine range of motion on X-ray images was constructed and showed accuracy comparable to that of spine surgeons. This system will be effective in reducing the burden on and saving time of orthopedic surgeons by avoiding manually measuring X-ray images.

Trial registration Retrospectively registered with opt-out agreement.

Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks : a deep learning radiological analysis

AIMS

Accurate identification of the ankle joint centre is critical for estimating tibial coronal alignment in total knee arthroplasty (TKA). The purpose of the current study was to leverage artificial intelligence (AI) to determine the accuracy and effect of using different radiological anatomical landmarks to quantify mechanical alignment in relation to a traditionally defined radiological ankle centre.

METHODS

Patients with full-limb radiographs from the Osteoarthritis Initiative were included. A sub-cohort of 250 radiographs were annotated for landmarks relevant to knee alignment and used to train a deep learning (U-Net) workflow for angle calculation on the entire database. The radiological ankle centre was defined as the midpoint of the superior talus edge/tibial plafond. Knee alignment (hip-knee-ankle angle) was compared against 1) midpoint of the most prominent malleoli points, 2) midpoint of the soft-tissue overlying malleoli, and 3) midpoint of the soft-tissue sulcus above the malleoli.

RESULTS

A total of 932 bilateral full-limb radiographs (1,864 knees) were measured at a rate of 20.63 seconds/image. The knee alignment using the radiological ankle centre was accurate against ground truth radiologist measurements (inter-class correlation coefficient (ICC) = 0.99 (0.98 to 0.99)). Compared to the radiological ankle centre, the mean midpoint of the malleoli was 2.3 mm (SD 1.3) lateral and 5.2 mm (SD 2.4) distal, shifting alignment by 0.34^o (SD 2.4^o) valgus, whereas the midpoint of the soft-tissue sulcus was 4.69 mm (SD 3.55) lateral and 32.4 mm (SD 12.4) proximal, shifting alignment by 0.65^o (SD 0.55^o) valgus. On the intermalleolar line, measuring a point at 46% (SD 2%) of the intermalleolar width from the medial malleoli (2.38 mm medial adjustment from midpoint) resulted in knee alignment identical to using the radiological ankle centre.

CONCLUSION

The current study leveraged AI to create a consistent and objective model that can estimate patient-specific adjustments necessary for optimal landmark usage in extramedullary and computer-guided navigation for tibial coronal alignment to match radiological planning.Cite this article: Bone Jt Open 2022;3(10):767-776.

Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images

Background

A deep convolutional neural network (DCNN) system is proposed to measure the lower limb parameters of the mechanical lateral distal femur angle (mLDFA), medial proximal tibial angle (MPTA), lateral distal tibial angle (LDTA), joint line convergence angle (JLCA), and mechanical axis of the lower limbs.

Methods

Standing X-rays of 1000 patients’ lower limbs were examined for the DCNN and assigned to training, validation, and test sets. A coarse-to-fine network was employed to locate 20 key landmarks on both limbs that first recognised the regions of hip, knee, and ankle, and subsequently outputted the key points in each sub-region from a full-length X-ray. Finally, information from these key landmark locations was used to calculate the above five parameters.

Results

The DCNN system showed high consistency (intraclass correlation coefficient > 0.91) for all five lower limb parameters. Additionally, the mean absolute error (MAE) and root mean squared error (RMSE) of all angle predictions were lower than 3° for both the left and right limbs. The MAE of the mechanical axis of the lower limbs was 1.124 mm and 1.416 mm and the RMSE was 1.032 mm and 1.321 mm, for the right and left limbs, respectively. The measurement time of the DCNN system was 1.8 ± 1.3 s, which was significantly shorter than that of experienced radiologists (616.8 ± 48.2 s, t = -180.4, P < 0.001).

Conclusions

The proposed DCNN system can automatically measure mLDFA, MPTA, LDTA, JLCA, and the mechanical axis of the lower limbs, thus helping physicians manage lower limb alignment accurately and efficiently.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12891-022-05818-4.

Artificial Intelligence in Orthopedic Radiography Analysis: A Narrative Review

Artificial intelligence (AI) in medicine is a rapidly growing field. In orthopedics, the clinical implementations of AI have not yet reached their full potential. Deep learning algorithms have shown promising results in computed radiographs for fracture detection, classification of OA, bone age, as well as automated measurements of the lower extremities. Studies investigating the performance of AI compared to trained human readers often show equal or better results, although human validation is indispensable at the current standards. The objective of this narrative review is to give an overview of AI in medicine and summarize the current applications of AI in orthopedic radiography imaging. Due to the different AI software and study design, it is difficult to find a clear structure in this field. To produce more homogeneous studies, open-source access to AI software codes and a consensus on study design should be aimed for.

Artificial intelligence enables reliable and standardized measurements of implant alignment in long leg radiographs with total knee arthroplasties

PURPOSE

The purpose of this study was to evaluate the reliability of a newly developed AI-algorithm for the evaluation of long leg radiographs (LLR) after total knee arthroplasties (TKA).

METHODS

In the validation cohort 200 calibrated LLRs of eight different common unconstrained and constrained knee systems were analysed. Accuracy and reproducibility of the AI-algorithm were compared to manual reads regarding the hip-knee-ankle (HKA) as well as femoral (FCA) and tibial component (TCA) angles. In the evaluation cohort all institutional LLRs with TKAs in 2018 (n = 1312) were evaluated to assess the algorithms' ability of handling large data sets. Intraclass correlation (ICC) coefficient and mean absolute deviation (sMAD) were calculated to assess conformity between the AI software and manual reads.

RESULTS

Validation cohort: The AI-software was reproducible on 96% and reliable on 92.1% of LLRs with an output and showed excellent reliability in all measured angles (ICC > 0.97) compared to manual measurements. Excellent results were found for primary unconstrained TKAs. In constrained TKAs landmark setting on the femoral and tibial component failed in 12.5% of LLRs (n = 9). Evaluation cohort: Mean measurements for all postoperative TKAs (n = 1240) were 0.2° varus ± 2.5° (HKA), 89.3° ± 1.9° (FCA), and 89.1° ± 1.6° (TCA). Mean measurements on preoperative revision TKAs (n = 74) were 1.6 varus ± 6.4° (HKA), 90.5° ± 3.1° (FCA), and 88.9° ± 4.1° (TCA).

CONCLUSIONS

AI-powered applications are reliable for automated analysis of lower limb alignment on LLRs with TKAs. They are capable of handling large data sets and could, therefore, lead to more standardized and efficient postoperative quality controls.

LEVEL OF EVIDENCE

Diagnostic Level III.

Artificial Intelligence System for Automatic Quantitative Analysis and Radiology Reporting of Leg Length Radiographs

Leg length discrepancies are common orthopedic problems with the potential for poor functional outcomes. These are frequently assessed using bilateral leg length radiographs. The objective was to determine whether an artificial intelligence (AI)-based image analysis system can accurately interpret long leg length radiographic images. We built an end-to-end system to analyze leg length radiographs and generate reports like radiologists, which involves measurement of lengths (femur, tibia, entire leg) and angles (mechanical axis and pelvic tilt), describes presence and location of orthopedic hardware, and reports laterality discrepancies. After IRB approval, a dataset of 1,726 extremities (863 images) from consecutive examinations at a tertiary referral center was retrospectively acquired and partitioned into train/validation and test sets. The training set was annotated and used to train a fasterRCNN-ResNet101 object detection convolutional neural network. A second-stage classifier using a EfficientNet-D0 model was trained to recognize the presence or absence of hardware within extracted joint image patches. The system was deployed in a custom web application that generated a preliminary radiology report. Performance of the system was evaluated using a holdout 220 image test set, annotated by 3 musculoskeletal fellowship trained radiologists. At the object detection level, the system demonstrated a recall of 0.98 and precision of 0.96 in detecting anatomic landmarks. Correlation coefficients between radiologist and AI-generated measurements for femur, tibia, and whole-leg lengths were > 0.99, with mean error of < 1%. Correlation coefficients for mechanical axis angle and pelvic tilt were 0.98 and 0.86, respectively, with mean absolute error of < 1°. AI hardware detection demonstrated an accuracy of 99.8%. Automatic quantitative and qualitative analysis of leg length radiographs using deep learning is feasible and holds potential in improving radiologist workflow.

Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study

OBJECTIVES

Accurate assessment of knee alignment and leg length discrepancy is currently measured manually from standing long-leg radiographs (LLR), a process that is both time consuming and poorly reproducible. The aim was to assess the performance of a commercial available AI software by comparing its outputs with manually performed measurements.

MATERIALS AND METHODS

The AI was trained on over 15,000 radiographs to measure various clinical angles and lengths from LLRs. We performed a retrospective single-center analysis on 295 LLRs obtained between 2015 and 2020 from male and female patients over 18 years. AI and expert measurements were performed independently. Kellgren-Lawrence score and reading time were assessed. All measurements were compared and non-inferiority, mean-absolute-deviation (sMAD), and intra-class-correlation (ICC) were calculated.

RESULTS

A total of 295 LLRs from 284 patients (mean age, 65 years (18; 90); 97 (34.2%) men) were analyzed. The AI model produces outputs on 98.0% of the LLRs. Manually annotations were considered as 100% accurate. For each measurement, its divergence was calculated, resulting in an overall accuracy of 89.2% when comparing the AI outputs to the manually measured. AI vs. mean observer revealed an sMAD between 0.39 and 2.19° for angles and 1.45-5.00 mm for lengths. AI showed good reliability in all lengths and angles (ICC ≥ 0.87). Non-inferiority comparing AI to the mean observer revealed an equivalence-index (γ) between 0.54 and 3.03° for angles and - 0.70-1.95 mm for lengths. On average, AI was 130 s faster than clinicians.

CONCLUSION

Automated measurements of knee alignment and length measurements produced with an AI tool result in reproducible, accurate measures with a time savings compared to manually acquired measurements.

A deep learning approach to automatically quantify lower extremity alignment in children

OBJECTIVE

To develop and validate a convolutional neural network (CNN) capable of predicting the anatomical landmarks used to calculate the hip-knee-ankle angles (HKAAs) from radiographs and thereby quantify lower extremity alignments in children.

MATERIALS AND METHODS

A search of the image archive at a large children's hospital was conducted to identify full-length lower extremity radiographs performed in children (≤ 18 years old) for the indication of lower extremity alignment (7/2019-10/2019). A radiologist manually labeled each radiograph's six requisite anatomical landmarks used to measure HKAAs (bilateral centers of the femoral head, tibial spine, and tibial plafond) and defined the resultant labels as ground truth. A 2D heatmap was generated for each ground truth landmark to encode the pseudo-probability of a landmark being at a particular location. A CNN was developed for indirect landmark localization by regressing across a collection of these heatmaps. The landmarks predicted from this model were used to calculate the HKAAs. Absolute prediction error and intraclass correlation were used to assess the accuracy of the HKAA estimates.

RESULTS

The study cohort consisted of 528 radiographs from 517 patients (mean age = 10.8 years, SD = 4.2 years). Evaluation of this CNN showed few HKAA prediction outliers (12/1056 [1.1%]), defined as having an absolute prediction error of > 10°. Excluding these outliers, the study cohort's mean absolute prediction error for the HKAA was 0.94° ± 0.84°, and the intraclass correlation between the ground truth and prediction was 0.974.

CONCLUSION

The proposed CNN generated promising results and offers potential for using this model as a computer-aided diagnostic tool.

Artificial intelligence and machine learning: an introduction for orthopaedic surgeons

The application of artificial intelligence (AI) and machine learning to the field of orthopaedic surgery is rapidly increasing. While this represents an important step in the advancement of our specialty, the concept of AI is rich with statistical jargon and techniques unfamiliar to many clinicians. This knowledge gap may limit the impact and potential of these novel techniques. We aim to narrow this gap in a way that is accessible for all orthopaedic surgeons. With this manuscript, we introduce the concept of AI and machine learning and give examples of how it can impact clinical practice and patient care.Level of evidence VI.

Machine learning algorithm to predict anterior cruciate ligament revision demonstrates external validity

PURPOSE

External validation of machine learning predictive models is achieved through evaluation of model performance on different groups of patients than were used for algorithm development. This important step is uncommonly performed, inhibiting clinical translation of newly developed models. Machine learning analysis of the Norwegian Knee Ligament Register (NKLR) recently led to the development of a tool capable of estimating the risk of anterior cruciate ligament (ACL) revision ( https://swastvedt.shinyapps.io/calculator_rev/ ). The purpose of this study was to determine the external validity of the NKLR model by assessing algorithm performance when applied to patients from the Danish Knee Ligament Registry (DKLR).

METHODS

The primary outcome measure of the NKLR model was probability of revision ACL reconstruction within 1, 2, and/or 5 years. For external validation, all DKLR patients with complete data for the five variables required for NKLR prediction were included. The five variables included graft choice, femur fixation device, KOOS QOL score at surgery, years from injury to surgery, and age at surgery. Predicted revision probabilities were calculated for all DKLR patients. The model performance was assessed using the same metrics as the NKLR study: concordance and calibration.

RESULTS

In total, 10,922 DKLR patients were included for analysis. Average follow-up time or time-to-revision was 8.4 (± 4.3) years and overall revision rate was 6.9%. Surgical technique trends (i.e., graft choice and fixation devices) and injury characteristics (i.e., concomitant meniscus and cartilage pathology) were dissimilar between registries. The model produced similar concordance when applied to the DKLR population compared to the original NKLR test data (DKLR: 0.68; NKLR: 0.68-0.69). Calibration was poorer for the DKLR population at one and five years post primary surgery but similar to the NKLR at two years.

CONCLUSION

The NKLR machine learning algorithm demonstrated similar performance when applied to patients from the DKLR, suggesting that it is valid for application outside of the initial patient population. This represents the first machine learning model for predicting revision ACL reconstruction that has been externally validated. Clinicians can use this in-clinic calculator to estimate revision risk at a patient specific level when discussing outcome expectations pre-operatively. While encouraging, it should be noted that the performance of the model on patients undergoing ACL reconstruction outside of Scandinavia remains unknown.

LEVEL OF EVIDENCE

III.

Deep Learning-Based Post-Processing of Real-Time MRI to Assess and Quantify Dynamic Wrist Movement in Health and Disease

While morphologic magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of ligamentous wrist injuries, it is merely static and incapable of diagnosing dynamic wrist instability. Based on real-time MRI and algorithm-based image post-processing in terms of convolutional neural networks (CNNs), this study aims to develop and validate an automatic technique to quantify wrist movement. A total of 56 bilateral wrists (28 healthy volunteers) were imaged during continuous and alternating maximum ulnar and radial abduction. Following CNN-based automatic segmentations of carpal bone contours, scapholunate and lunotriquetral gap widths were quantified based on dedicated algorithms and as a function of wrist position. Automatic segmentations were in excellent agreement with manual reference segmentations performed by two radiologists as indicated by Dice similarity coefficients of 0.96 ± 0.02 and consistent and unskewed Bland–Altman plots. Clinical applicability of the framework was assessed in a patient with diagnosed scapholunate ligament injury. Considerable increases in scapholunate gap widths across the range-of-motion were found. In conclusion, the combination of real-time wrist MRI and the present framework provides a powerful diagnostic tool for dynamic assessment of wrist function and, if confirmed in clinical trials, dynamic carpal instability that may elude static assessment using clinical-standard imaging modalities.