Artificial intelligence applied to magnetic resonance imaging reliably detects the presence, but not the location, of meniscus tears: a systematic review and meta-analysis.

OBJECTIVES: To review and compare the accuracy of convolutional neural networks (CNN) for the diagnosis of meniscal tears in the current literature and analyze the decision-making processes utilized by these CNN algorithms. MATERIALS AND METHODS: PubMed, MEDLINE, EMBASE, and Cochrane databases up to December 2022 were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) statement. Risk of analysis was used for all identified articles. Predictive performance values, including sensitivity and specificity, were extracted for quantitative analysis. The meta-analysis was divided between AI prediction models identifying the presence of meniscus tears and the location of meniscus tears. RESULTS: Eleven articles were included in the final review, with a total of 13,467 patients and 57,551 images. Heterogeneity was statistically significantly large for the sensitivity of the tear identification analysis (I2 = 79%). A higher level of accuracy was observed in identifying the presence of a meniscal tear over locating tears in specific regions of the meniscus (AUC, 0.939 vs 0.905). Pooled sensitivity and specificity were 0.87 (95% confidence interval (CI) 0.80-0.91) and 0.89 (95% CI 0.83-0.93) for meniscus tear identification and 0.88 (95% CI 0.82-0.91) and 0.84 (95% CI 0.81-0.85) for locating the tears. CONCLUSIONS: AI prediction models achieved favorable performance in the diagnosis, but not location, of meniscus tears. Further studies on the clinical utilities of deep learning should include standardized reporting, external validation, and full reports of the predictive performances of these models, with a view to localizing tears more accurately. CLINICAL RELEVANCE STATEMENT: Meniscus tears are hard to diagnose in the knee magnetic resonance images. AI prediction models may play an important role in improving the diagnostic accuracy of clinicians and radiologists. KEY POINTS: • Artificial intelligence (AI) provides great potential in improving the diagnosis of meniscus tears. • The pooled diagnostic performance for artificial intelligence (AI) in identifying meniscus tears was better (sensitivity 87%, specificity 89%) than locating the tears (sensitivity 88%, specificity 84%). • AI is good at confirming the diagnosis of meniscus tears, but future work is required to guide the management of the disease.

Evaluation of the usefulness of non-weight-bearing tunnel view using X-ray in the short term after medial meniscus posterior root tear onset: a retrospective study.

BACKGROUND: This study aimed to examine whether the non-weight-bearing tunnel view X-ray is effective for short-term evaluation of medial meniscus posterior root tear (MMPRT) by assessing the X-ray characteristics at the initial and follow-up visits. METHODS: This was a retrospective longitudinal study of 26 enrolled knees diagnosed with MMPRT on magnetic resonance imaging. The distance between the medial tibial eminence and medial femoral condyle (MTE-MFC distance) and medial tibiofemoral joint (MTFJ) width were measured by obtaining non-weight-bearing tunnel view and frontal view X-ray radiographs. The initial and follow-up values at a median interval of 17 days were compared. Additionally, the correlations between the MTE-MFC distance increase rate and body mass index (BMI), age, femorotibial angle (FTA), and posterior tibial slope (PTS) were evaluated using linear regression analysis. RESULTS: The tunnel view images of the initial and follow-up X-rays showed a significant increase in the MTE-MFC distance and a significant decrease in the MTFJ width. Furthermore, a moderate correlation was observed between the change in the MTE-MFC distance and the time interval between X-rays. However, no substantial correlation was observed for the change in the MTFJ width over time. Moreover, no significant correlation was observed between the change in the MTE-MFC distance in the non-weight-bearing tunnel view and BMI, age, FTA, and PTS. CONCLUSIONS: The non-weight-bearing tunnel view is highly beneficial for evaluating MMPRT progression in the short term.

Quantitative evaluation of meniscus injury using synthetic magnetic resonance imaging.

BACKGROUND: Magnetic resonance imaging (MRI) can diagnose meniscal lesions anatomically, while quantitative MRI can reflect the changes of meniscal histology and biochemical structure. Our study aims to explore the association between the measurement values obtained from synthetic magnetic resonance imaging (SyMRI) and Stoller grades. Additionally, we aim to assess the diagnostic accuracy of SyMRI in determining the extent of meniscus injury. This potential accuracy could contribute to minimizing unnecessary invasive examinations and providing guidance for clinical treatment. METHODS: Total of 60 (n=60) patients requiring knee arthroscopic surgery and 20 (n=20) healthy subjects were collected from July 2022 to November 2022. All subjects underwent conventional MRI and SyMRI. Manual measurements of the T1, T2 and proton density (PD) values were conducted for both normal menisci and the most severely affected position of injured menisci. These measurements corresponded to the Stoller grade of meniscus injuries observed in the conventional MRI. All patients and healthy subjects were divided into normal group, degeneration group and torn group according to the Stoller grade on conventional MRI. One-way analysis of variance (ANOVA) was employed to compare the T1, T2 and PD values of the meniscus among 3 groups. The accuracy of SyMRI in diagnosing meniscus injury was assessed by comparing the findings with arthroscopic observations. The diagnostic efficiency of meniscus degeneration and tear between conventional MRI and SyMRI were analyzed using McNemar test. Furthermore, a receiver operating characteristic curve (ROC curve) was constructed and the area under the curve (AUC) was utilized for evaluation. RESULTS: According to the measurements of SyMRI, there was no statistical difference of T1 value or PD value measured by SyMRI among the normal group, degeneration group and torn group, while the difference of T2 value was statistically significant among 3 groups (P=0.001). The arthroscopic findings showed that 11 patients were meniscal degeneration and 49 patients were meniscal tears. The arthroscopic findings were used as the gold standard, and the difference of T1 and PD values among the 3 groups was not statistically significant, while the difference of T2 values (32.81±2.51 of normal group, 44.85±3.98 of degeneration group and 54.42±3.82 of torn group) was statistically significant (P=0.001). When the threshold of T2 value was 51.67 (ms), the maximum Yoden index was 0.787 and the AUC value was 0.934. CONCLUSIONS: The measurement values derived from SyMRI could reflect the Stoller grade, illustrating that SyMRI has good consistency with conventional MRI. Moreover, the notable consistency observed between SyMRI and arthroscopy suggests a potential role for SyMRI in guiding clinical diagnoses.

Predicting incident radiographic knee osteoarthritis through quantitative meniscal lesion parameters: data from the osteoarthritis initiative.

BACKGROUND: This study investigates the potential of novel meniscal parameters as predictive factors for incident radiographic knee osteoarthritis (ROA) over a span of four years, as part of the Osteoarthritis Initiative (OAI) study. OBJECTIVES: Quantitative measurements of meniscal parameters alteration could serve as predictors of OA's occurrence and progression. METHODS AND MATERIALS: A nested matched case-control study design was used to select participants from OAI study. Case knees (n = 178) were defined as those with incident ROA (Kellgren Lawrence Grade (KLG) 0 or 1 at baseline (BL), evolving into KLG 2 or above by year 4). Control knees were matched one-to-one by sex, age and radiographic status with case knees. The mean distance from medial-to-lateral meniscal lesions [Mean(MLD)], mean value of tibial plateau width [Mean(TPW)] and the mean of the relative percentage of the medial-to-lateral meniscal lesions distance [Mean(RMLD)] were evaluated through coronal T2-weighted turbo spin echo (TSE) MRI at P-0 (visit when incident ROA was found on radiograph), P-1(one year prior to P-0) and baseline, respectively. Using the imaging data of one patient, the mechanism was investigated by finite element analysis. RESULTS: Participants were on average 60.22 years old, predominantly female (66.7%) and overweight (mean BMI: 28.15). Mean(MLD) and Mean(RMLD) were significantly greater for incident knees compared to no incident knees at baseline, P-1 and P-0. [Mean(MLD), Mean(RMLD); (42.56-49.73) mean ± (7.70-9.52) mm SD vs. (38.14-40.78) mean ± (5.51-7.05)mm SD; (58.61-68.95) mean ± (8.52-11.40) mm SD vs. (52.52-56.35) mean ± (6.53-7.85)mm SD, respectively]. Baseline Mean(MLD) and Mean(RMLD), [Adjusted OR, 95%CI: 1.11(1.07 to 1.16) and 1.13(1.09 to 1.17), respectively], were associated with incident ROA during 4 years, However, Mean(TPW) [Adjusted OR, 95%CI: 0.98(0.94 to 1.02)] was not associated with incident ROA during 4 years. While Mean(TPW) at P-1 and P-0 was not associated with the risk of incident ROA, Mean(MLD) and Mean(RMLD) at P-1 and P-0 were significantly positively associated with the risk of incident ROA. CONCLUSIONS: The meniscal parameters alteration could be an important imaging biomarker to predict the occurrence of ROA.

A larger radius of the medial femoral posterior condyle is a risk factor for medial meniscus posterior root tears.

BACKGROUND: Studies have shown an association between medial meniscus posterior root tears (MMPRT) and morphologic characteristics of the bone. However, the association between distal femoral bone morphology and MMPRT, particularly the medial femoral posterior condyle, is poorly understood. Our study aimed to determine the association between the morphologic characteristics of the medial posterior femoral condyle and MMPRT. METHODS: A retrospective case-control study was performed from January 2021 to January 2022. After screening based on the inclusion and exclusion criteria, two matched groups were analyzed: the MMPRT group and the isolated lateral meniscus tears group. The hip-knee-ankle angle (HKA) and Kellgren-Lawrence grade (KLG) were measured on radiographs; the medial tibial slope angle (MTSA), medial tibial plateau depth (MTPD), and radius of the medial femoral posterior condyle (RMFPC) were measured on magnetic resonance imaging (MRI) in both groups. The area under the curve (AUC) and the best cutoff value for predicting MMPRT were calculated by using receiver operating characteristic (ROC) curve analysis. RESULTS: The final analysis included a total of 174 patients (87 MMPRT patients and 87 controls). Significant differences were shown in the RMFPC (17.6 ± 1.0 vs. 16.2 ± 1.0, p < 0.01) and MTSA (6.4 ± 2.0 vs. 4.0 ± 1.3, p < 0.01), which were larger than those of the control group. The MTPD (1.8 ± 0.6 vs. 2.9 ± 0.7, p < 0.01) and HKA (175.4 ± 2.2 vs. 179.0 ± 2.7, p < 0.01) of the injury group were significantly different from the control group, and both were lower than the control group. However, between the MMPRT and control groups on the KLG (2.3 ± 0.6 vs. 2.2 ± 0.6, p = 0.209), there was no statistically significant difference. Among them, the RMFPC cutoff value was calculated to be 16.8 mm by ROC curve analysis, and the sensitivity and specificity were both 81.61%. CONCLUSIONS: This study demonstrated that larger RMFPC, MTSA, smaller MTPD, and HKA were all associated with MMPRT, and RMFPC ≥ 16.8 mm was considered as a significant risk factor for MMPRT.

Single-bundle ACL combined with ALL reconstruction yields comparable outcomes in patients with varied anatomical risk factors for ACL graft failure.

BACKGROUND: Anterior cruciate ligament (ACL) graft failure is influenced by factors such as meniscal tears and tibial plateau slope. Combined anterior cruciate ligament (ACL) and anterolateral ligament (ALL) reconstruction has reduced failure rates; however, its efficacy in high-risk patients remains unclear. This study hypothesized that combined ACL and ALL reconstruction would yield similar clinical outcomes in patients with varying risks of ACL failure. PATIENTS AND METHODS: A total of 76 patients who underwent primary single-bundle ACL reconstruction combined with ALL reconstruction between June 2018 and June 2021 were included. The medial tibial slope (MTS), lateral tibial slope (LTS), and anterior tibial translation (ATT) were measured using magnetic resonance imaging and plain radiography of the knee joint. The meniscal lesions were assessed during surgery. Preoperative clinical assessments and final follow-up were conducted using patient-reported outcome measurements (PROMs), including the International Knee Documentation Committee (IKDC) evaluation, Lysholm knee scoring scale, and Tegner Activity scale. PROMs were collected at least two years postoperatively. RESULTS: The average follow-up was 32.5 ± 7.4 months. There were no significant differences in postoperative IKDC score, Lysholm score, or Tegner activity score between patients with or without medial meniscus injury (p = 0.155, 0.914, and 0.042, respectively), with or without lateral meniscus injury (p = 0.737, 0.569, and 0.942, respectively), medial tibial slope > 12° or ≤ 12° (p = 0.290, 0.496, and 0.988, respectively), or lateral tibial slope > 7.4° or ≤ 7.4° (p = 0.213, 0.625, and 0.922, respectively). No significant correlations were found between anterior tibial translation and postoperative IKDC (R = -0.058, p = 0.365), Lysholm (R = -0.017, p = 0.459), or Tegner activity scores (R = -0.147, p = 0.189). CONCLUSION: Our study demonstrates that single-bundle ACL reconstruction combined with ALL reconstruction provides reliable and comparable clinical outcomes in patients with high-risk factors for ACL graft failure, such as increased tibial slope or meniscal injury. Our results suggest that the indications for ALL reconstruction may be expanded to include patients with a high tibial slope or meniscal injury, because these factors have been shown to contribute to increased rotational instability and high rates of ACL graft failure. Future prospective randomized controlled trials with large patient cohorts and long follow-up periods are needed to validate these findings and establish clear guidelines for patient selection and surgical decision-making. LEVEL OF EVIDENCE: Level 3.

"Ring-shaped" meniscus and accompanying intermeniscal bridge meniscus: a rare combined variant resembling a bucket-handle tear.

Many anatomical variations have been described in the menisci, especially in the lateral meniscus. Among these, discoid meniscus is the most common variation. Others are described in the literature as double-layered meniscus, accessory meniscus, ring-shaped meniscus, and hypoplastic meniscus. Also, combined variations associated with ring-shaped meniscus have been described, and they can be confused with fragmented complex tears and cause unnecessary surgery. Increasing awareness of the imaging features of these accompanying combined variations may aid in the recognition and differentiation of this entity from meniscus tears. We report the case of a ring-shaped meniscus and accompanying intermeniscal bridge meniscus, which has not been described before in the literature, highlighting the MRI and arthroscopic imaging findings of it.

Diagnostic Accuracy of MRI in Knee Meniscus Tear and ACL Injury.

Objective: Knee injuries are very common and may lead to other secondary injuries if effective treatment is lacking. In addition to standardized physical examination, magnetic resonance imaging (MRI) is sometimes considered an aid in the diagnosis of knee trauma. In order to have a more accurate diagnosis of knee injuries, we compared MRI with arthroscopic findings in this study to evaluate the diagnostic accuracy of MRI for meniscal tears and anterior cruciate ligament injuries of the knee. Methods: One hundred and ten patients with suspected meniscal tears and anterior cruciate ligament injuries of the knee who were admitted to our hospital from June 2020 to June 2022 were selected as study subjects, and the clinical data of the patients were retrospectively analyzed. All patients underwent MRI for preoperative diagnosis, and the sensitivity, specificity, MRI findings, and confirmation of diagnosis were compared and analyzed, and the accuracy of MRI in diagnosing meniscal tears and ACL injuries of the knee was analyzed. Results: The mean ACL angle was (98.0 ± 5.4) in the MRI group and (118.0 ± 6.8) in the arthroscopic group, the difference between the two groups was statistically significant P < .05. The mean L/H value of the ACL was (2.12 ± 0.38) in the MRI group and (1.81 ± 0.19) in the arthroscopic group, which was statistically different between the two groups (P < .05). Among the patients, 68 meniscal injuries were found in the MRI examination, including 45 cases of knee meniscal tears and 23 cases of anterior cruciate ligament injuries. The sensitivity, specificity, positive and negative predictive values, agreement rate, kappa value, and Youden index of MRI in diagnosing meniscal tears and ACL injuries were all high. Conclusions: In terms of sensitivity and accuracy, MRI is an excellent imaging technique for the diagnosis of meniscal tears and anterior cruciate ligament injuries of the knee.

Meniscal ramp lesion classification systems: A systematic review.

PURPOSE: To describe the proposed classification systems for meniscal ramp lesions (RLs) in the literature and evaluate their accuracy and reliability. METHODS: A systematic search was conducted according to the Preferred Reporting Items for Systematic reviews and Meta-analyses guidelines utilising PubMed, Embase and Cochrane Library databases. Level I-IV studies referencing RLs along with either an arthroscopic- or magnetic resonance imaging (MRI)-based classification system used to describe RL subtypes were included. RESULTS: In total, 21 clinical studies were included. Twenty-seven (79%) of the included studies were published in 2020 or later. There were four main classification systems proposed within the literature (two arthroscopic-, two MRI-based), describing tear patterns, mediolateral extent, associated ligament disruption and stability of the lesion. The first classification was proposed in 2015 by Thaunat et al. and is referenced in 22 (64.7%) of the included studies. The application of the Thaunat et al. criteria to MRI showed variable sensitivity (31.70%-93.8%) and interobserver agreement (k = 0.55-0.80). The Greif et al. modification to the Thaunat et al. system was referenced in 32.4% of the included studies and had a substantial interobserver agreement (k = 0.8). Stability to probing and specific tear location were each used to classify RLs in 28.6% and 23.8% of the included clinical studies, respectively. CONCLUSION: Although there has been a recent increase in the recognition and treatment of meniscal RLs, there is limited consistency in descriptive classifications used for this pathology. Current RL classification systems based on preoperative MRI have variable reliability, and arthroscopic examination remains the gold standard for diagnosis and classification. LEVEL OF EVIDENCE: Level IV.

Meniscal extrusion consensus statement: A collaborative survey within the Meniscus International Network (MenIN) Study Group.

PURPOSE: The purpose of the present study was to perform a survey administered to members of the Meniscus International Network (MenIN) Study Group, seeking to delineate the most contentious aspects of meniscal extrusion classification and provide a foundation for new, more comprehensive definitions and treatments for these pathologies. METHODS: MenIN Study Group is a group of international experts treating and performing research on meniscus pathology and treatment. All MenIN Study Group members were asked to complete a survey aimed at establishing criteria for the optimal classification system for meniscal extrusion. Data obtained from the completed questionnaires were transferred into a spreadsheet and then analysed. All responses are presented as counts, percentages or means. RESULTS: Forty-seven (85.5%) MenIN Study Group members completed the survey and were included in this analysis. Key aspects recommended for inclusion in a comprehensive classification system for meniscal extrusion included laterality (93.6%), anatomical location (76.6%), patient age (76.6%), body mass index (BMI) (68.1%) and aetiology (68.1%). For classifying meniscal extrusion, 53.2% considered the distance in millimetres from the tibial plateau's outer margin as the most reliable measurement technique on imaging. Preferences for imaging modalities varied, with 44.7% favouring weight-bearing magnetic resonance imaging (MRI) and 36.2% opting for weight-bearing ultrasound due to its greater availability. Respondents advocated for a classification system addressing stability or progression of meniscal extrusion (66%), reducibility (53.2%), potential progression of knee osteoarthritis (OA) (83%), influencing treatment approaches (83%), a gradation system (83%), consideration of dynamic factors (66%), association with clinical outcomes and prognosis (76.6%) and investigation around centralization procedures (57.4%). CONCLUSIONS: In conclusion, the findings of this survey shed light on the global perspectives regarding meniscal extrusion classification. It was generally felt that a new classification of extrusion measured on MRI scans at the mid-tibial plateau should be developed, which considers factors such as laterality, anatomical location, age, BMI and aetiology. Additionally, the results support the integration of dynamic factors and clinical outcomes in MRI-based classifications to inform treatment approaches. LEVEL OF EVIDENCE: Level IV.

The presence of a deep lateral femoral notch sign in ACL-injured patients is associated with a 2.7° steeper posterior tibial slope and a 19% higher frequency of lateral meniscal injuries.

PURPOSE: The purpose of this study was to study the relationship between the presence of a deep lateral femoral notch sign (DLFNS) in anterior cruciate ligament (ACL)-injured patients and a higher posterior lateral tibial slope (LPTS), a reduced meniscal bone angle (MBA), a higher LPTS/MBA ratio and a higher incidence of concomitant injuries in primary ACL tears. METHODS: A retrospective case-control study was performed in patients submitted to primary ACL reconstruction with an available preoperative magnetic resonance imaging (MRI) scan. Patients with ACL tears and a femoral impactation with a depth ≥2 mm were assorted to the DLFNS group and patients with ACL tear and without a DLFNS to the control group. LPTS and MBA were measured in MRI. The presence of concomitant injuries (meniscal, posterior cruciate ligament, medial collateral ligament, lateral collateral ligament and bone injuries) was assessed in MRI. Quantitative data are presented in the median ± interquartile range (IQR). RESULTS: There were 206 patients included in the study, with 46 patients assorted to the DLFNS group and 160 patients to the control group. In the DLFNS group, the median LPTS was 6.7° (IQR: 4.0-8.2) versus 4.0° in the control group (IQR: 2.2-6.5) (p = 0.003). The LPTS/MBA ratio was significantly higher in the DLFNS group, with a median of 0.32 (IQR: 0.19-0.44), in comparison to the control group, with a median of 0.19 (IQR: 0.11-0.31) (p < 0.001). The multivariable logistic regression analysis showed that the LPTS is an independent risk factor to having a DLFNS (odds ratio [OR] = 1.161; 95% confidence interval [CI]: 1.042-1.293, p = 0.007). There was a higher incidence of concomitant lateral meniscal injuries in the DLFNS group (67% vs. 48%, p = 0.017). CONCLUSIONS: In patients with ACL tears, the presence of a DLFNS is associated with a steeper lateral posterior tibial slope, as well as a higher incidence of concomitant lateral meniscal injuries. LEVEL OF EVIDENCE: Level III.

Magnetic Resonance Imaging Indirect Signs for Anterior Instability of the Lateral Meniscus in Pediatric and Adolescent Patients.

BACKGROUND: Anterior instability (AI) of the LM is potentially debilitating in young patients. The use of magnetic resonance imaging (MRI) to diagnose AI is limited due to the lack of reliable and accurate MRI findings. The ability to identify AI preoperatively would potentially improve the diagnosis and treatment of this pathology. This study presents a novel MRI finding ("phantom sign") for the detection of AI of the LM and demonstrates its reliability and accuracy. METHODS: Three independent blinded reviewers performed retrospective review of preoperative MRI for all patients who underwent LM repair between July 1, 2019, and March 31, 2022, at a single center. Positive phantom sign was defined as abnormal signal intensity on MRI of the anterior horn of the LM on the coronal sequence at the anterior tibial insertion of the anterior cruciate ligament (ACL). Preoperative MRI was also evaluated for other signs of LM anterior instability. Intrarater and inter-rater reliability was assessed for rater scoring of presence of pathology on MRI. Predictive ability of each imaging finding with at least good (ICC 0.6 or above) reliability was also evaluated based on documented intraoperative findings. RESULTS: Fifty-five preoperative MRIs of arthroscopically treated LM tears were reviewed. Median age was 15 years (range 6 to 20), and 21 patients (38.2%) were female. Twenty-seven patients (49.1%) had a discoid meniscus. LM AI was present on arthroscopy for 25 knees (45.45%), and among these, 21 had discoid morphology. Interrater reliability was substantial for phantom sign (ICC 0.71, 97.5% CI: 0.55-0.82), posterior displacement (ICC 0.71, 97.5% CI: 0.55-0.82), and posterior "megahorn" (ICC 0.76, 97.5% CI: 0.62-0.85). On predictive analysis, phantom signs were 98% sensitive and 76.7% specific for LM AI. Posterior displacement and posterior megahorn were specific for AI (both 93.34%), though with limited sensitivity (32% and 28.6%, respectively). CONCLUSIONS: Phantom sign is a reliable and sensitive MRI finding for anterior instability, even in the absence of frank displacement on preoperative MRI. A positive finding should prompt a thorough arthroscopic evaluation of the anterior horn of the LM. LEVEL OF EVIDENCE: Level III-case control study.

Meniscus root tears: state of the art.

BACKGROUND: Meniscus root tears represent significant pathology that, historically, has been underdiagnosed and undertreated. However, the recognition of their clinical and functional significance has recently surged, mainly due to their frequent association with anterior cruciate ligament injuries. AIM: This comprehensive review discusses various aspects of meniscal root tears, including their epidemiology, biomechanics, etiology, clinical and radiological findings, classification, management and surgical techniques.

The relevance of knee arthroscopy photographs in medicolegal proceedings.

PURPOSE: Whether photographs included in the operative report of knee arthroscopies can make the surgeon liable in the event of a legal investigation remains unknown. The main objective of this study was to establish inter-observer reliability in determining the presence or absence of lesions of the cartilage, meniscus and anterior cruciate ligament (ACL). Secondary objective was to assess the inter-observer reliability in classifying lesions. METHOD: A retrospective observational study was conducted in a continuous serie of 60 patients who underwent knee arthroscopy from the same operator. The photographs of each patient's operative report were presented separately to three experts, blinded to each other. Each expert had to decide on the presence or absence of injuries to the following structures: meniscal, cartilage and ACL and then, classify it. Primary and secondary endpoints were evaluated using the Fleiss' kappa index. RESULTS: Inter-observer reliability for lesion detection was between 0.4 and 0.61 for all structures with three exceptions: for cartilage, it was low (0.15) at the lateral tibial plateau and poor (-0.01) at the external condyle. On the contrary, the concordance was almost perfect (0.8) for the ACL. For classifying cartilaginous and meniscal lesions, inter-observer reliability was poor (from 0.03 to 0.14), except for at the lateral meniscus (0.65). CONCLUSION: Inter-observer reliability of arthroscopic knee diagnoses is poor when photographs alone are used. In the event of a legal investigation following knee arthroscopy, the photographs included in the operative report should not be used alone to hold the surgeon liable.

Ultrasonographic diagnosis of medial meniscus posterior root tear in early knee osteoarthritis: a comparative study.

INTRODUCTION: This study aimed to detect medial meniscal posterior root tear (MMPRT) diagnostic methods with high sensitivity and specificity using dynamic ultrasonographic evaluation in patients with early knee osteoarthritis (OA) and demonstrate the usefulness of dynamic ultrasonographic medial meniscal extrusion (MME) evaluation in MMPRT diagnosis using a cutoff value. MATERIALS AND METHODS: Between 2018 and 2020, a total of 120 patients were diagnosed with early knee OA using clinical and radiographic findings. Dynamic ultrasonographic evaluations and magnetic resonance imaging were performed in all patients, and 47 patients who had and 73 patients who did not have MMPRT were classified into the MMPRT and non-MMPRT groups, respectively. Age, sex, femorotibial angle, MME of knee extension and flexion, and MME at weight-bearing were compared between the two groups. Additionally, the sensitivity and specificity of significant ultrasonographic findings were calculated using a receiver operating characteristic (ROC) curve. RESULTS: The MMEs under knee extension-flexion and weight-loading in the MMPRT group were significantly larger than those in the non-MMPRT group. ROC curve analysis for each ultrasonographic evaluation condition to diagnose MMPRT indicated that the sensitivity was 72-88% and the specificity was 66-85% when the cutoff values of MME under knee flexion at 0°, 90°, and weight-loading were set at 2.55 mm, 2.00 mm, and 3.55 mm, respectively. The highest sensitivity (88%) and specificity (85%) were exhibited upon > 2 mm MME at a knee flexion of 90° and were the most useful indicators for MME diagnosis. CONCLUSIONS: Ultrasonographic MME evaluations for MMPRT diagnosis showed relatively high sensitivity and specificity in patients with early knee OA. Dynamic ultrasonographic MME evaluation may lead to appropriate additional examinations, early diagnosis, and intervention for MMPRT in patients with early knee OA.

Automatic Detection of Meniscus Tears Using Backbone Convolutional Neural Networks on Knee MRI.

BACKGROUND: Timely diagnosis of meniscus injuries is key for preventing knee joint dysfunction and improving patient outcomes because it decreases morbidity and facilitates treatment planning. PURPOSE: To train and evaluate a deep learning model for automated detection of meniscus tears on knee magnetic resonance imaging (MRI). STUDY TYPE: Bicentric retrospective study. SUBJECTS: In total, 584 knee MRI studies, divided among training (n = 234), testing (n = 200), and external validation (n = 150) data sets, were used in this study. The public data set MRNet was used as a second external validation data set to evaluate the performance of the model. SEQUENCE: A 3 T, coronal, and sagittal images from T1-weighted proton density (PD) fast spin-echo (FSE) with fat saturation and T2-weighted FSE with fat saturation sequences. ASSESSMENT: The detection system for meniscus tear was based on the improved YOLOv4 model with Darknet-53 as the backbone. The performance of the model was also compared with that of three radiologists of varying levels of experience. The determination of the presence of a meniscus tear from surgery reports was used as the ground truth for the images. STATISTICAL TESTS: Sensitivity, specificity, prevalence, positive predictive value, negative predictive value, accuracy, and receiver operating characteristic curve were used to evaluate the performance of the detection model. Two-way analysis of variance, Wilcoxon signed-rank test, and Tukey's multiple tests were used to evaluate differences in performance between the model and radiologists. RESULTS: The overall accuracies for detecting meniscus tears using our model on the internal testing, internal validation, and external validation data sets were 95.4%, 95.8%, and 78.8%, respectively. One radiologist had significantly lower performance than our model in detecting meniscal tears (accuracy: 0.9025 ± 0.093 vs. 0.9580 ± 0.025). DATA CONCLUSION: The proposed model had high sensitivity, specificity, and accuracy for detecting meniscus tears on knee MRIs. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Medial meniscal posterior horn tears and ramp lesions in pediatric patients: lessons learned.

Meniscal injuries are increasingly reported in pediatric patients due to early sports participation and are commonly encountered during anterior cruciate ligament reconstruction. Preoperative identification of meniscal tears is crucial, particularly when involving the posteromedial meniscocapsular junction (ramp lesion). MRI plays an important role in detecting this particular type of meniscal injury. Consequently, pediatric radiologists should be aware of particular MRI findings related to ramp lesions including the presence of a medial meniscal tear, peripheral meniscal irregularity, meniscocapsular junctional fluid-like signal intensity, and capsular ligament tears. Thus, we illustrate the lessons we have learned from our institutional multidisciplinary arthroscopic-MR correlation conference for retrospectively identified posterior horn medial meniscal tears and ramp lesions.

Reprint of: Outcomes of Arthroscopic All-Inside Repair Are Improved Compared to Transtibial Pull-Out Repair of Medial Meniscus Posterior Root Tears.

PURPOSE: The purpose of the present study was to compare the clinical outcomes of patients who underwent an all-inside repair (with a bony trough) versus transtibial pull-out repair in medial meniscus posterior root tears (MMPRTs). METHODS: We retrospectively investigated consecutive patients who underwent MMPRT repairs in nonacute tears in age over 40 from November 2015 to June 2019. All patients were divided into a transtibial pull-out repair group and an all-inside repair group. Different surgical techniques were used during different time frames. All patients were followed-up for a minimum of 2 years. The data collected included the International Knee Documentation Committee (IKDC) Subjective, Lysholm, and Tegner activity scores. Magnetic resonance imaging (MRI) was performed at the 1-year follow-up to assess meniscus extrusion, signal intensity, and healing. RESULTS: The final cohort consisted of 28 patients in the all-inside repair group and 16 in the transtibial pull-out repair group. In the all-inside repair group, the IKDC Subjective, Lysholm, and Tegner scores improved significantly at the 2-year follow-up. In the transtibial pull-out repair group, the IKDC Subjective, Lysholm, and Tegner scores did not improve significantly at the 2-year follow-up. Postoperative extrusion ratio increased in both groups, and patient-reported outcomes at follow-up did not differ between the two groups The change in the extrusion ratio was significantly less in the all-inside repair group (P = .009), as was the postoperative meniscus signal (P = .011). Postoperative MRI revealed significantly better healing in the all-inside group (P = .041). CONCLUSION: All-inside repair improved the functional outcome scores. Radiologically, all-inside repair was better than transtibial pull-out repair. All-inside repair may be a viable MMPRT treatment option. LEVEL OF EVIDENCE: III, retrospective cohort study.

Isolated Posterior Lateral Meniscofemoral Ligament Tears Show Greater Meniscal Extrusion in Knee Extension, and Isolated Posterior Lateral Meniscal Root Tears Show Greater Meniscal Extrusion at 30° Using Ultrasound: A Cadaveric Study.

PURPOSE: To quantify the effects that posterior meniscofemoral ligament (pMFL) lesions have on lateral meniscal extrusion (ME) both with and without concomitant posterior lateral meniscal root (PLMR) tears and describe how lateral ME varied along the length of the lateral meniscus. METHODS: Ultrasonography was used to measure ME of human cadaveric knees (n = 10) under the following conditions: control, isolated pMFL sectioning, isolated PLMR sectioning, pMFL+PLMR sectioning, and PLMR repair. ME was measured anterior to the fibular collateral ligament (FCL), at the FCL, and posterior to the FCL in both unloaded and axially loaded states at 0° and 30° of flexion. RESULTS: Isolated and combined pMFL and PLMR sectioning consistently demonstrated significantly greater ME when measured posterior to the FCL compared with other image locations. Isolated pMFL tears demonstrated greater ME at 0° compared with 30° of flexion (P < .05), whereas isolated PLMR tears demonstrated greater ME at 30° compared with 0° of flexion (P < .001). All specimens with isolated PLMR deficiencies demonstrated greater than 2 mm of ME at 30° flexion, whereas only 20% of specimens did so at 0°. When the pMFL was sectioned following an isolated PLMR tear, there was a significant increase in ME at 0° (P < .001). PLMR repair after combined sectioning restored ME to levels similar to that of controls in all specimens when measured at and posterior to the FCL (P < .001). CONCLUSIONS: The pMFL protects against ME primarily in full extension, whereas the presence of ME in the setting of PLMR injuries may be better appreciated in knee flexion. With combined tears, isolated repair of the PLMR can restore near-native meniscus position. CLINICAL RELEVANCE: The stabilizing properties of intact pMFL may mask the presentation of PLMR tears and delay appropriate management. Additionally, the MFL is not routinely assessed during arthroscopy due to difficult visualization and access. Understanding the ME pattern of these pathologies in isolation and combination may improve detection rates so that the source of patients' symptoms can be addressed to satisfaction.

Medial Meniscal Extrusion of Greater Than 3 Millimeters on Ultrasound Suggests Combined Medial Meniscotibial Ligament and Posterior Medial Meniscal Root Tears: A Cadaveric Analysis.

PURPOSE: To evaluate how the meniscotibial ligament (MTL) affects meniscal extrusion (ME) with or without concomitant posterior medial meniscal root (PMMR) tears and to describe how ME varied along the length of meniscus. METHODS: ME was measured using ultrasonography in 10 human cadaveric knees in conditions: (1) control, either (2a) isolated MTL sectioning, or (2b) isolated PMMR tear, (3) combined PMMR+MTL sectioning, and (4) PMMR repair. Measurements were obtained 1 cm anterior to the MCL (anterior), over the MCL (middle), and 1 cm posterior to the MCL (posterior) with or without 1,000 N axial loads in 0° and 30° flexion. RESULTS: At 0°, MTL sectioning demonstrated greater middle than anterior (P < .001) and posterior (P < .001) ME, whereas PMMR (P = .0042) and PMMR+MTL (P < .001) sectioning demonstrated greater posterior than anterior ME. At 30°, PMMR (P < .001) and PMMR+MTL (P < .001) sectioning demonstrated greater posterior than anterior ME, and PMMR (P = .0012) and PMMR+MTL (P = .0058) sectioning demonstrated greater posterior than anterior ME. PMMR+MTL sectioning demonstrated greater posterior ME at 30° compared with 0° (P = .0320). MTL sectioning always resulted in greater middle ME (P < .001), in contrast with no middle ME changes following PMMR sectioning. At 0°, PMMR sectioning resulted in greater posterior ME (P < .001), but at 30°, both PMMR and MTL sectioning resulted in greater posterior ME (P < .001). Total ME surpassed 3 mm only when both the MTL and PMMR were sectioned. CONCLUSIONS: The MTL and PMMR contribute most to ME when measured posterior to the MCL at 30° of flexion. ME greater than 3 mm is suggestive of combined PMMR + MTL lesions. CLINICAL RELEVANCE: Overlooked MTL pathology may contribute to persistent ME following PMMR repair. We found isolated MTL tears able to cause 2 to 2.99 mm of ME, but the clinical significance of these magnitudes of extrusion is unclear. The use of ME measurement guidelines with ultrasound may allow for practical MTL and PMMR pathology screening and pre-operative planning.