Primary anterior cruciate ligament repair: magnetic resonance imaging characterisation of reparable lesions and correlation with arthroscopy

Lightweight Attentive Graph Neural Network with Conditional Random Field for Diagnosis of Anterior Cruciate Ligament Tear

Anterior cruciate ligament (ACL) tears are prevalent orthopedic sports injuries and are difficult to precisely classify. Previous works have demonstrated the ability of deep learning (DL) to provide support for clinicians in ACL tear classification scenarios, but it requires a large quantity of labeled samples and incurs a high computational expense. This study aims to overcome the challenges brought by small and imbalanced data and achieve fast and accurate ACL tear classification based on magnetic resonance imaging (MRI) of the knee. We propose a lightweight attentive graph neural network (GNN) with a conditional random field (CRF), named the ACGNN, to classify ACL ruptures in knee MR images. A metric-based meta-learning strategy is introduced to conduct independent testing through multiple node classification tasks. We design a lightweight feature embedding network using a feature-based knowledge distillation method to extract features from the given images. Then, GNN layers are used to find the dependencies between samples and complete the classification process. The CRF is incorporated into each GNN layer to refine the affinities. To mitigate oversmoothing and overfitting issues, we apply self-boosting attention, node attention, and memory attention for graph initialization, node updating, and correlation across graph layers, respectively. Experiments demonstrated that our model provided excellent performance on both oblique coronal data and sagittal data with accuracies of 92.94% and 91.92%, respectively. Notably, our proposed method exhibited comparable performance to that of orthopedic surgeons during an internal clinical validation. This work shows the potential of our method to advance ACL diagnosis and facilitates the development of computer-aided diagnosis methods for use in clinical practice.

Approaching expert-level accuracy for differentiating ACL tear types on MRI with deep learning

Treatment for anterior cruciate ligament (ACL) tears depends on the condition of the ligament. We aimed to identify different tear statuses from preoperative MRI using deep learning-based radiomics with sex and age. We reviewed 862 patients with preoperative MRI scans reflecting ACL status from Hunan Provincial People's Hospital. Based on sagittal proton density-weighted images, a fully automated approach was developed that consisted of a deep learning model for segmenting ACL tissue (ACL-DNet) and a deep learning-based recognizer for ligament status classification (ACL-SNet). The efficacy of the proposed approach was evaluated by using the sensitivity, specificity and area under the receiver operating characteristic curve (AUC) and compared with that of a group of three orthopedists in the holdout test set. The ACL-DNet model yielded a Dice coefficient of 98% ± 6% on the MRI datasets. Our proposed classification model yielded a sensitivity of 97% and a specificity of 97%. In comparison, the sensitivity of alternative models ranged from 84 to 90%, while the specificity was between 86 and 92%. The AUC of the ACL-SNet model was 99%, demonstrating high overall diagnostic accuracy. The diagnostic performance of the clinical experts as reflected in the AUC was 96%, 92% and 88%, respectively. The fully automated model shows potential as a highly reliable and reproducible tool that allows orthopedists to noninvasively identify the ACL status and may aid in optimizing different techniques, such as ACL remnant preservation, for ACL reconstruction.

Spontaneous healing of acute ACL ruptures: rate, prognostic factors and short-term outcome

INTRODUCTION

Anterior cruciate ligament (ACL) reconstruction is considered the first line treatment in ACL rupture. However, some patients return to high intensity sport activities and show a normal knee function without ACL reconstruction. Therefore, aim of this study was to evaluate the rate and prognostic factors of spontaneous healing in patients with ACL rupture and the short-term functional outcome.

METHODS

The rate, prognostic factors and short-term functional results of spontaneous healing in patients with ACL rupture were evaluated in 381 patients. Morphology of ACL rupture and extent of posterior tibial slope (PTS) were classified by MR- and x-ray imaging. In patients with normal knee stability in anesthesia examination and healed ACL during the arthroscopy 6 weeks after trauma ACL reconstruction was canceled. IKDC -, Tegner Activity Score, KT 1000 testing and radiological characteristics were collected 12 months postoperatively in these patients.

RESULTS

14.17% of the patients with ACL rupture showed a spontaneous healing after 6 weeks. Femoral ACL-rupture (p < 0.02) with integrity of ligament stump > 50% (p < 0.001), without bundle separation (p < 0.001) and decreased PTS (p < 0.001) was found significantly more often in patients with a spontaneous healed ACL. The average IKDC score was high at 84,63 in patients with healed ACL at 1 year follow-up, but KT 1000 testing was inferior compared to non-injured side.

CONCLUSION

Spontaneous healing of a ruptured ACL happened in 14% of the patients. Especially in low-demand patients with femoral single bundle lesions without increased posterior tibial slope delayed ACL surgery should be considered to await the possibility for potential spontaneous ACL healing.

Positional MR imaging of normal and injured knees

OBJECTIVES

This study uses a practical positional MRI protocol to evaluate tibiofemoral translation and rotation in normal and injured knees.

METHODS

Following ethics approval, positional knee MRI of both knees was performed at 35° flexion, extension, and hyperextension in 34 normal subjects (mean age 31.1 ± 10 years) and 51 knee injury patients (mean age 36.4 ± 11.5 years, ACL tear n = 23, non-ACL injury n = 28). At each position, tibiofemoral translation and rotation were measured.

RESULTS

Normal knees showed 8.1 ± 3.3° external tibial rotation (i.e., compatible with physiological screw home mechanism) in hyperextension. The unaffected knee of ACL tear patients showed increased tibial anterior translation laterally (p = 0.005) and decreased external rotation (p = 0.002) in hyperextension compared to normal knees. ACL-tear knees had increased tibial anterior translation laterally (p < 0.001) and decreased external rotation (p < 0.001) compared to normal knees. Applying normal thresholds, fifteen (65%) of 23 ACL knees had excessive tibial anterior translation laterally while 17 (74%) had limited external rotation. None (0%) of 28 non-ACL-injured knees had excessive tibial anterior translation laterally while 13 (46%) had limited external rotation. Multidirectional malalignment was much more common in ACL-tear knees.

CONCLUSIONS

Positional MRI shows (a) physiological tibiofemoral movement in normal knees, (b) aberrant tibiofemoral alignment in the unaffected knee of ACL tear patients, and (c) a high frequency of abnormal tibiofemoral malalignment in injured knees which was more frequent, more pronounced, more multidirectional, and of a different pattern in ACL-tear knees than non-ACL-injured knees.

KEY POINTS

• Positional MRI shows physiological tibiofemoral translation and rotation in normal knees. • Positional MRI shows a different pattern of tibiofemoral alignment in the unaffected knee of ACL tear patients compared to normal control knees. • Positional MRI shows a high prevalence of abnormal tibiofemoral alignment in injured knees, which is more frequent and pronounced in ACL-tear knees than in ACL-intact injured knees.

A deep learning approach for anterior cruciate ligament rupture localization on knee MR images

Purpose: To develop and evaluate a deep learning-based method to localize and classify anterior cruciate ligament (ACL) ruptures on knee MR images by using arthroscopy as the reference standard.

Methods: We proposed a fully automated ACL rupture localization system to localize and classify ACL ruptures. The classification of ACL ruptures was based on the projection coordinates of the ACL rupture point on the line connecting the center coordinates of the femoral and tibial footprints. The line was divided into three equal parts and the position of the projection coordinates indicated the classification of the ACL ruptures (femoral side, middle and tibial side). In total, 85 patients (mean age: 27; male: 56) who underwent ACL reconstruction surgery under arthroscopy were included. Three clinical readers evaluated the datasets separately and their diagnostic performances were compared with those of the model. The performance metrics included the accuracy, error rate, sensitivity, specificity, precision, and F1-score. A one-way ANOVA was used to evaluate the performance of the convolutional neural networks (CNNs) and clinical readers. Intraclass correlation coefficients (ICC) were used to assess interobserver agreement between the clinical readers.

Results: The accuracy of ACL localization was 3.77 ± 2.74 and 4.68 ± 3.92 (mm) for three-dimensional (3D) and two-dimensional (2D) CNNs, respectively. There was no significant difference in the ACL rupture location performance between the 3D and 2D CNNs or among the clinical readers (Accuracy, p < 0.01). The 3D CNNs performed best among the five evaluators in classifying the femoral side (sensitivity of 0.86 and specificity of 0.79), middle side (sensitivity of 0.71 and specificity of 0.84) and tibial side ACL rupture (sensitivity of 0.71 and specificity of 0.99), and the overall accuracy for sides classifying of ACL rupture achieved 0.79.

Conclusion: The proposed deep learning-based model achieved high diagnostic performances in locating and classifying ACL fractures on knee MR images.