Predictive validity of radiographic signs of complete discoid lateral meniscus in children using machine learning techniques

Age and medial compartmental OA were important predictors of the lateral compartmental OA in the discoid lateral meniscus: Analysis using machine learning approach

PURPOSE

The objective of this study was to develop a machine learning model that would predict lateral compartment osteoarthritis (OA) in the discoid lateral meniscus (DLM), from which to then identify factors contributing to lateral compartment OA, with a key focus on the patient's age.

METHODS

Data were collected from 611 patients with symptomatic DLM diagnosed using magnetic resonance imaging between April 2003 and May 2022. Twenty features, including demographic, clinical and radiological data and six algorithms were used to develop the predictive machine learning models. Shapley additive explanation (SHAP) analysis was performed on the best model, in addition to subgroup analyses according to age.

RESULTS

Extreme gradient boosting classifier was identified as the best prediction model, with an area under the receiver operating characteristic curve (AUROC) of 0.968, the highest among all the models, regardless of age (AUROC of 0.977 in young age and AUROC of 0.937 in old age). In the SHAP analysis, the most predictive feature was age, followed by the presence of medial compartment OA. In the subgroup analysis, the most predictive feature was age in young age, whereas the most predictive feature was the presence of medial compartment OA in old age.

CONCLUSION

The machine learning model developed in this study showed a high predictive performance with regard to predicting lateral compartment OA of the DLM. Age was identified as the most important factor, followed by medial compartment OA. In subgroup analysis, medial compartmental OA was found to be the most important factor in the older age group, whereas age remained the most important factor in the younger age group. These findings provide insights that may prove useful for the establishment of strategies for the treatment of patients with symptomatic DLM.

LEVEL OF EVIDENCE

Level III.

Evaluation of the knee joint morphology associated with a complete discoid lateral meniscus, as a function of skeletal maturity, using magnetic resonance imaging

INTRODUCTION

A discoid lateral meniscus (DLM) is associated with increased risk for meniscal tears and progression of knee joint osteoarthritis. Our aim was to differentiate knee joint morphology between patients with and without a DLM, as a function of skeletal maturity, using magnetic (MR) imaging.

MATERIALS AND METHODS

This was a retrospective analysis of MR images of the knee for 110 patients, 6-49 years of age. Of these, 62 were in the open physis group (38 with a DLM) and 48 in the closed physis group (23 with a DLM). The following morphological parameters were measured: anterior obliquity of the lateral tibial plateau (AOLTP), posterior obliquity of the lateral tibial plateau (POLTP), the lowest point of the lateral femoral condyle (LPLFC), and the posterior lateral condylar angle (PLCA).

RESULTS

Regardless of skeletal maturity, a DLM was associated with a greater inclination of the POLTP, lateralization of the LPLFC, and smaller PLCA (p < 0.001 for all compared to that of the control group). In the DLM group, the inclination of the AOLTP and the POLTP were significantly smaller (p < 0.001) and the LPLFC was more lateral (p < 0.001) in the closed physis group than in the open physis group. In the control group, the inclination of the POLTP was larger (p < 0.001) and the PLCA smaller (p = 0.019) in the open than in the closed physis group.

CONCLUSIONS

We identified a characteristic knee morphology among patients with a complete DLM using MR imaging, which was observed before physeal closure and persisted after skeletal maturity was attained. We also noted lateralization of the LPLFC in the presence of a DLM, with an increase in lateralization with skeletal maturation.

LEVEL OF EVIDENCE

Case-control study, III.

The Clinical Application of Machine Learning Models for Risk Analysis of Ramp Lesions in Anterior Cruciate Ligament Injuries

BACKGROUND

Peripheral tears of the posterior horn of the medial meniscus, known as "ramp lesions," are commonly found in anterior cruciate ligament (ACL)-deficient knees but are frequently missed on routine evaluation.

PURPOSE

To predict the presence of ramp lesions in ACL-deficient knees using machine learning methods with associated risk factors.

STUDY DESIGN

Cohort study (Diagnosis); Level of evidence, 2.

METHODS

This study included 362 patients who underwent ACL reconstruction between June 2010 and March 2019. The exclusion criteria were combined fractures and multiple ligament injuries, except for medial collateral ligament injuries. Patients were grouped according to the presence of ramp lesions on arthroscopic surgery. Binary logistic regression was used to analyze risk factors including age, sex, body mass index, time from injury to surgery (≥3 or <3 months), mechanism of injury (contact or noncontact), side-to-side laxity, pivot-shift grade, medial and lateral tibial/meniscal slope, location of bone contusion, mechanical axis angle, and lateral femoral condyle (LFC) ratio. The receiver operating characteristic curve and area under the curve were also evaluated.

RESULTS

Ramp lesions were identified in 112 patients (30.9%). The risk for ramp lesions increased with steeper medial tibial and meniscal slopes, higher knee laxity, and an increased LFC ratio. Comparing the final performance of all models, the random forest model yielded the best performance (area under the curve: 0.944), although there were no significant differences among the models (P > .05). The cut-off values for the presence of ramp lesions on receiver operating characteristic analysis were as follows: medial tibial slope >5.5° (P < .001), medial meniscal slope >5.0° (P < .001), and LFC ratio >71.3% (P = .033).

CONCLUSION

Steep medial tibial and meniscal slopes, an increased LFC ratio, and higher knee rotatory laxity were observed risk factors for ramp lesions in patients with an ACL injury. The prediction model of this study could be used as a supplementary diagnostic tool for ramp lesions in ACL-injured knees. In general, care should be taken in patients with ramp lesions and its risk factors during ACL reconstruction.

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Artificial intelligence (AI) is playing an ever-increasing role in radiology (more so in the adult world than in pediatrics), to the extent that there are unfounded fears it will completely take over the role of the radiologist. In relation to musculoskeletal applications of AI in pediatric radiology, we are far from the time when AI will replace radiologists; even for the commonest application (bone age assessment), AI is more often employed in an AI-assist mode rather than an AI-replace or AI-extend mode. AI for bone age assessment has been in clinical use for more than a decade and is the area in which most research has been conducted. Most other potential indications in children (such as appendicular and vertebral fracture detection) remain largely in the research domain. This article reviews the areas in which AI is most prominent in relation to the pediatric musculoskeletal system, briefly summarizing the current literature and highlighting areas for future research. Pediatric radiologists are encouraged to participate as members of the research teams conducting pediatric radiology artificial intelligence research.

Deep Learning to Detect Triangular Fibrocartilage Complex Injury in Wrist MRI: Retrospective Study with Internal and External Validation

Objective: To use deep learning to predict the probability of triangular fibrocartilage complex (TFCC) injury in patients’ MRI scans. Methods: We retrospectively studied medical records over 11 years and 2 months (1 January 2009–29 February 2019), collecting 332 contrast-enhanced hand MRI scans showing TFCC injury (143 scans) or not (189 scans) from a general hospital. We employed two convolutional neural networks with the MRNet (Algorithm 1) and ResNet50 (Algorithm 2) framework for deep learning. Explainable artificial intelligence was used for heatmap analysis. We tested deep learning using an external dataset containing the MRI scans of 12 patients with TFCC injuries and 38 healthy subjects. Results: In the internal dataset, Algorithm 1 had an AUC of 0.809 (95% confidence interval—CI: 0.670–0.947) for TFCC injury detection as well as an accuracy, sensitivity, and specificity of 75.6% (95% CI: 0.613–0.858), 66.7% (95% CI: 0.438–0.837), and 81.5% (95% CI: 0.633–0.918), respectively, and an F1 score of 0.686. Algorithm 2 had an AUC of 0.871 (95% CI: 0.747–0.995) for TFCC injury detection and an accuracy, sensitivity, and specificity of 90.7% (95% CI: 0.787–0.962), 88.2% (95% CI: 0.664–0.966), and 92.3% (95% CI: 0.763–0.978), respectively, and an F1 score of 0.882. The accuracy, sensitivity, and specificity for radiologist 1 were 88.9, 94.4 and 85.2%, respectively, and for radiologist 2, they were 71.1, 100 and 51.9%, respectively. Conclusions: A modified MRNet framework enables the detection of TFCC injury and guides accurate diagnosis.

A radiographic model predicting the status of the anterior cruciate ligament in varus knee with osteoarthritis

Purpose

The study aims to investigate the accuracy of different radiographic signs for predicting functional deficiency of anterior cruciate ligament (ACL) and test whether the prediction model constructed by integrating multiple radiographic signs can improve the predictive ability.

Methods

A total number of 122 patients from January 1, 2018, to September 1, 2021, were enrolled in this study. Among them, 96 patients were classified as the ACL-functional (ACLF) group, while 26 patients as the ACL-deficient (ACLD) group after the assessment of magnetic resonance imaging (MRI) and the Lachman’s test. Radiographic measurements, including the maximum wear point of the proximal tibia% (MWPPT%), tibial spine sign (TSS), coronal tibiofemoral subluxation (CTFS), hip–knee–ankle angle (HKA), mechanical proximal tibial angle (mPTA), mechanical lateral distal femoral angle (mLDFA) and posterior tibial slope (PTS) were measured using X-rays and compared between ACLF and ACLD group using univariate analysis. Significant variables (p < 0.05) in univariate analysis were further analyzed using multiple logistic regression analysis and a logistic regression model was also constructed by multivariable regression with generalized estimating models. Receiver-operating-characteristic (ROC) curve and area under the curve (AUC) were used to determine the cut-off value and the diagnostic accuracy of radiographic measurements and the logistic regression model.

Results

MWPPT% (odds ratio (OR) = 1.383, 95% confidence interval (CI) = 1.193–1.603, p < 0.001), HKA (OR = 1.326, 95%CI = 1.051–1.673, p = 0.017) and PTS (OR = 1.981, 95%CI = 1.207–3.253, p = 0.007) were shown as predictive indicators of ACLD, while age, sex, side, TSS, CTFS, mPTA and mLDFA were not. A predictive model (risk score = -27.147 + [0.342*MWPPT%] + [0.282*HKA] + [0.684*PTS]) of ACLD using the three significant imaging indicators was constructed through multiple logistic regression analysis. The cut-off values of MWPPT%, HKA, PTS and the predictive model were 52.4% (sensitivity:92.3%; specificity:83.3%), 8.5° (sensitivity: 61.5%; specificity: 77.1%), 9.6° (sensitivity: 69.2%; specificity: 78.2%) and 0.1 (sensitivity: 96.2%; specificity: 79.2%) with the AUC (95%CI) values of 0.906 (0.829–0.983), 0.703 (0.574–0.832), 0.740 (0.621–0.860) and 0.949 (0.912–0.986) in the ROC curve.

Conclusion

MWPPT% (> 52.4%), PTS (> 9.6°), and HKA (> 8.5°) were found to be predictive factors for ACLD, and MWPPT% had the highest sensitivity of the three factors. Therefore, MWPPT% can be used as a screening tool, while the model can be used as a diagnostic tool.

Evaluation of knee bone morphology in juvenile patients with complete discoid lateral meniscus using magnetic resonance imaging

PURPOSE

The characteristic two-dimensional bone morphology in patients with a discoid lateral meniscus (DLM) has been described. However, the associated three-dimensional imaging findings have not been characterized. This study was performed to identify differences in the knee bone morphology between juvenile patients with a DLM and those with a normal meniscus using magnetic resonance (MR) imaging.

METHODS

The DLM group comprised 33 consecutive juvenile patients (33 knees) with a complete DLM, and the control group comprised 24 juvenile patients (24 knees) with normal menisci on the basis of MR imaging findings. Each MR image was evaluated to determine the anterior obliquity of the lateral tibial plateau (AOLTP), posterior obliquity of the lateral tibial plateau (POLTP), lowest point of the lateral femoral condyle (LPLFC), posterior lateral condylar angle (PLCA) and posterior medial condylar angle (PMCA). Statistical analyses were performed to determine the differences between the two groups.

RESULTS

The POLTP was significantly larger, the LPLFC was significantly more lateral, and the PLCA was significantly smaller in the DLM group than in the control group (p < 0.001, p < 0.001 and p < 0.001 respectively). However, there was no statistically significant difference in the AOLTP or PMCA between the two groups (p = 0.429 and p = 0.148, respectively).

CONCLUSIONS

Hypoplasia of the lateral femoral condyle and posterior lateral tibial plateau is recognized in juvenile patients with a complete DLM on coronal and axial MRI images.

LEVEL OF EVIDENCE

Diagnostic study, Level III.

Application of deep-learning-based artificial intelligence in acetabular index measurement

OBJECTIVE

To construct an artificial intelligence system to measure acetabular index and evaluate its accuracy in clinical application.

METHODS

A total of 10,219 standard anteroposterior pelvic radiographs were collected retrospectively from April 2014 to December 2018 in our hospital. Of these, 9,219 radiographs were randomly selected to train and verify the system. The remaining 1,000 radiographs were used to compare the system's and the clinicians' measurement results. All plain pelvic films were labeled by an expert committee through PACS system based on a uniform standard to measure acetabular index. Subsequently, eight other clinicians independently measured the acetabular index from 200 randomly selected radiographs from the test radiographs. Bland-Altman test was used for consistency analysis between the system and clinician measurements.

RESULTS

The test set included 1,000 cases (2,000 hips). Compared with the expert committee measurement, the 95% limits of agreement (95% LOA) of the system was -4.02° to 3.45° (bias = -0.27°, P < 0.05). The acetabular index measured by the system within all age groups, including normal and abnormal groups, also showed good credibility according to the Bland-Altman principle. Comparison of the measurement evaluations by the system and eight clinicians vs. that of, the expert committee, the 95% LOA of the clinician with the smallest measurement error was -2.76° to 2.56° (bias = -0.10°, P = 0.126). The 95% LOA of the system was -0.93° to 2.86° (bias = -0.03°, P = 0.647). The 95% LOA of the clinician with the largest measurement error was -3.41° to 4.25° (bias = 0.42°, P < 0.05). The measurement error of the system was only greater than that of a senior clinician.

CONCLUSION

The newly constructed artificial intelligence system could quickly and accurately measure the acetabular index of standard anteroposterior pelvic radiographs. There is good data consistency between the system in measuring standard anteroposterior pelvic radiographs. The accuracy of the system is closer to that of senior clinicians.

Diagnostic Value of Ultrasound in Children with Discoid Lateral Meniscus Using Either an Intracavitary Convex Array Probe or a Linear Array Probe

This prospective study aimed to assess the usefulness of an intracavitary convex array probe (ICAP) in visualizing the lateral meniscus (LM) and improving the diagnostic utility of ultrasound (US) when diagnosing or screening for discoid lateral meniscus (DLM) in children. We included 105 knees (66 patients) that had symptomatic or asymptomatic DLM. We extracted and retrospectively reviewed data regarding patient demographics, medical records, magnetic resonance imaging (MRI), ultrasonographic features and arthroscopic findings. The inner edge of the LM visualized using an ICAP was significantly clearer than that visualized using a linear array probe, and the difference was significant (p < 0.01). The edges were better visualized in patients aged <8 y than in those aged >8 y, and the difference was significant (p < 0.001). The average widths of the LM body using an ICAP and MRI were 19.85 ± 3.63 and 24.46 ± 4.94 mm, respectively, and the wider the meniscal width, the greater was the deviation between the US and MRI measurements, which were positively correlated (r = 0.612, p < 0.001). With the use of MRI measurements and an ICAP, meniscal widths in poorly visualized LMs were greater than those in clearly visualized LMs, but this difference was not significant (p = 0.161). US scans using an ICAP and MRI were highly consistent in assessing the shape of the menisci (κ = 0.849, p < 0.001). US scan using an ICAP is a non-invasive, convenient and low-cost modality for diagnosing or screening for DLM in the pediatric population, especially in children aged <8 y.