Imaging of meniscus and ligament injuries of the knee

Identification and diagnosis of meniscus tear by magnetic resonance imaging using a deep learning model

Objective

Meniscus tear is a common problem in sports trauma, and its imaging diagnosis mainly relies on MRI. To improve the diagnostic accuracy and efficiency, a deep learning model was employed in this study and the identification efficiency was evaluated.

Methods

Standard knee MRI images from 924 individual patients were used to complete the training, validation and testing processes. Mask regional convolutional neural network (R–CNN) was used to build the deep learning network structure, and ResNet50 was adopted to develop the backbone network. The deep learning model was trained and validated with a dataset containing 504 and 220 patients, respectively. Internal testing was performed based on a dataset of 200 patients, and 180 patients from 8 hospitals were regarded as an external dataset for model validation. Additionally, 40 patients who were diagnosed by the arthroscopic surgery were enrolled as the final test dataset.

Results

After training and validation, the deep learning model effectively recognized healthy and injured menisci. Average precision for the three types of menisci (healthy, torn and degenerated menisci) ranged from 68% to 80%. Diagnostic accuracy for healthy, torn and degenerated menisci was 87.50%, 86.96%, and 84.78%, respectively. Validation results from external dataset demonstrated that the accuracy of diagnosing torn and intact meniscus tear through 3.0T MRI images was higher than 80%, while the accuracy verified by arthroscopic surgery was 87.50%.

Conclusion

Mask R–CNN effectively identified and diagnosed meniscal injuries, especially for tears that occurred in different parts of the meniscus. The recognition ability was admirable, and the diagnostic accuracy could be further improved with increased training sample size. Therefore, this deep learning model showed great potential in diagnosing meniscus injuries.

Translational potential of this article

Deep learning model exerted unique effect in terms of reducing doctors’ workload and improving diagnostic accuracy. Injured and healthy menisci could be more accurately identified and classified based on training and learning datasets. This model could also distinguish torn from degenerated menisci, making it an effective tool for MRI-assisted diagnosis of meniscus injuries in clinical practice.

Imaging of the Posttraumatic Knee in Pediatric Patients

Owing to its continuous transformation, the musculoskeletal system of pediatric patients presents some unique features with respect to both anatomy and physiology. The lesional pattern of the knee in pediatric patients is both similar to and in many aspects different from the lesional pattern in adults with knee injuries. In the case of pediatric patients, meniscal, tendinous and ligamentous lesions occur most frequently as a consequence of traumatic episodes. The purpose of the present study is to emphasize the importance of MRI examinations in pediatric patients exhibiting symptoms of knee joint injury. The imaging assessment of the extent of the lesions, which can be either simple or complex alterations, can directly influence the clinical management of these cases by appreciating the growth potential of the specific segment of immature skeleton involved.

The ring-shaped meniscus: a case series demonstrating the variation of imaging appearances on MRI

The ring-shaped meniscus (RSM) is a rare meniscal variant in which there is an intermeniscal bridge between the anterior and posterior horns of the meniscus, thus forming a complete ring. The lateral meniscus is more commonly involved than the medial meniscus. Distinguishing an RSM from a bucket handle tear (BHT) with a displaced fragment in the intercondylar notch is challenging and there are reports of negative arthroscopies for suspected BHTs. There are many reports of symptomatic and asymptomatic lateral RSMs diagnosed on MRI in the literature. We report a series of RSMs in six patients, which includes MRI descriptions of two cases of medial RSM and a case of bilateral lateral RSM, which were diagnosed on MRI and have never previously been reported. This study will also describe the various imaging features of a RSM that distinguish it from a displaced BHT. We will also discuss associated rare malformations encountered in our study, such as hypoplastic anterior cruciate ligament and the anomalous insertion of the popliteus tendon onto the posterior horn of a lateral RSM.