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.

Decreasing Incidence of Partial Meniscectomy, and Increasing Incidence of Meniscus Preservation Surgery from 2010-2020 in the United States.

PURPOSE: The aim of the present study was to characterize the incidence of meniscus surgery from 2010 to 2020 in the United States, using the metrics of age, sex, type of meniscus surgery, and Charlson Comorbidity Index (CCI). METHODS: A retrospective analysis was performed using the PearlDiver national insurance claims database from 2010-2020. Meniscus surgeries were identified using Current Procedural Terminology codes. Patients were stratified by procedure type, age, biological sex, and Charlson Comorbidity Index (CCI) scores. Compound annual growth rate (CAGR) analysis and analysis of variance (ANOVA) were performed to analyze the trends and demographic variables between cohorts. RESULTS: Of 2,053,884 meniscus surgeries, 94.7% were meniscectomies, 0.3% were open repairs, 4.9% were arthroscopic repairs, and 0.1% were meniscal transplantations. CAGR analysis displayed a 4.0% decrease per year in total meniscus surgery. For individual procedure types, the largest decrease was in meniscectomy, and the largest increase was in open repair. Patients undergoing meniscal transplantation were youngest, with the lowest CCI. Meniscectomy patients were oldest, and open repair patients had the highest average CCI. Most procedures were performed on female patients (52.4%), and patients in the 50-59-year age group (30.4%). CONCLUSIONS: There was a sustained decrease in the incidence of total meniscus surgeries from 2010-2020. Meniscectomy was the procedure with the highest incidence, however, it showed the most significant decline in usage over the study period. Conversely, meniscal repair and transplantation procedures increased during the study period.

Failure rate of isolated medial meniscus repair in the stable knee: Systematic review and meta-analysis.

PURPOSE: The present meta-analysis aims to determine the outcomes and failure rates for medial meniscus repairs in patients with stable knees. METHODS: A literature search was conducted using PubMed and Scopus with the terms '(medial meniscus OR medial meniscal) AND (repair)'. The search strategy was based on the PRISMA (Preferred Reporting Items for Systematic Meta-Analyses) protocol and included 93 articles assessed for eligibility. The search criteria were limited to studies reporting outcomes and failure rates. The exclusion criteria included languages other than English, biomechanical studies, letters to editors, non-full text, review articles, meta-analyses and case reports. RESULTS: In total, 10 studies with 595 patients were included. Degenerative tears or studies reporting meniscus repair outcomes on root repairs, revision or primary anterior cruciate ligament reconstruction, discoid menisci or ramp lesions were excluded. All studies included revision surgery and/or clinical symptoms as failure definitions. The overall medial meniscal repair failure rate was 26% with a 95% confidence interval (CI) [15%-37%]. The mean time to failure from isolated medial meniscus repair surgery was 27.7 months with 95% CI [18.5-36.9 months]. The postoperative Lysholm and IKDC scores were reported in three articles. At the final follow-up, the mean postoperative Lysholm and IKDC scores were 92.3 with 95% CI [84.5-100] and 88.6 with 95% CI [83.5-93.8], respectively. CONCLUSION: The current meta-analysis revealed an overall failure rate of 26% in the case of medial meniscus repair in a stable knee. For these reasons, the patient should be aware of the substantial risk of revision surgery (one out of four cases). Medial meniscus repair in a stable knee yielded good clinical results. LEVEL OF EVIDENCE: II.

Achieving high accuracy in meniscus tear detection using advanced deep learning models with a relatively small data set.

PURPOSE: This study aims to evaluate the effectiveness of advanced deep learning models, specifically YOLOv8 and EfficientNetV2, in detecting meniscal tears on magnetic resonance imaging (MRI) using a relatively small data set. METHOD: Our data set consisted of MRI studies from 642 knees-two orthopaedic surgeons labelled and annotated the MR images. The training pipeline included MRI scans of these knees. It was divided into two stages: initially, a deep learning algorithm called YOLO was employed to identify the meniscus location, and subsequently, the EfficientNetV2 deep learning architecture was utilized to detect meniscal tears. A concise report indicating the location and detection of a torn meniscus is provided at the end. RESULT: The YOLOv8 model achieved mean average precision at 50% threshold (mAP@50) scores of 0.98 in the sagittal view and 0.985 in the coronal view. Similarly, the EfficientNetV2 model obtained area under the curve scores of 0.97 and 0.98 in the sagittal and coronal views, respectively. These outstanding results demonstrate exceptional performance in meniscus localization and tear detection. CONCLUSION: Despite a relatively small data set, state-of-the-art models like YOLOv8 and EfficientNetV2 yielded promising results. This artificial intelligence system enhances meniscal injury diagnosis by generating instant structured reports, facilitating faster image interpretation and reducing physician workload. LEVEL OF EVIDENCE: Level III.

Extracorporeal shockwave therapy for degenerative meniscal tears results in a decreased T2 relaxation time and pain relief: An exploratory randomized clinical trial.

PURPOSE: The optimal management of degenerative meniscal tears remains controversial. Extracorporeal shockwave therapy (ESWT) has been shown to promote tissue repair in both preclinical and clinical studies; however, its effect on degenerative meniscal tears remains unknown. This study aimed to examine whether ESWT improves meniscal degeneration. METHODS: This randomized trial was conducted between 2020 and 2022 and involved patients with degenerative medial meniscal tears. Patients were allocated to receive either focused ESWT (0.25 mJ/mm2, 2000 impulses, 3 sessions with a 1-week interval) or sham treatment. Patients were evaluated using magnetic resonance imaging (MRI) before treatment and at 12 months after treatment. The primary endpoint was improvement in meniscal degeneration, as assessed by the change in T2 relaxation time from baseline on MRI T2 mapping. Knee pain and clinical outcomes were also examined at the same time. RESULTS: Of 29 randomized patients, 27 patients (mean age 63.9 ± 8.7 years; females 37%; ESWT group 14 patients; control group 13 patients) were included in the final analysis. At 12 months postintervention, patients in the ESWT group showed a greater decrease in the T2 relaxation time (ESWT group -2.9 ± 1.7 ms vs. control group 1.0 ± 1.9 ms; p < 0.001) and had less knee pain (p = 0.04). The clinical outcomes at 12 months post-treatment were not statistically significant. No adverse events were reported. CONCLUSION: ESWT decreased the T2 relaxation time in the meniscus at 12 months post-treatment. ESWT also provided pain relief, but no differences were observed in clinical outcomes. LEVEL OF EVIDENCE: Level II.

The Association between the Extent of the Osteoarthritic Meniscus Degeneration and Cigarette Smoking-A Pilot Study.

Background and Objectives: The negative effects of smoking on the musculoskeletal system were presented by many authors, although the relationship between smoking and osteoarthritis remains unclear. The aim of this paper was to investigate the negative effects of smoking on meniscal tissue in osteoarthritic knees by microscopic examination, by adapting the Bonar scoring system and its modifications. Materials and Methods: The study involved 34 patients with varus knees, from whom 65 samples of knee menisci were obtained. The mean age in the studied group was 65.385 years. The smoking status of the patients concluded that there were 13 smokers and 21 nonsmokers. Results: Among smokers, the mean classical Bonar score was 8.42 and the mean modified Bonar score was 6.65, while nonsmokers were characterized by scores of 8.51 and 7.35, respectively. There was a statistically significant negative correlation between the number of cigarettes and the collagen in the medial meniscus (p = 0.0197). Moreover, in the medial meniscus, the modified Bonar score correlated negatively with the number of cigarettes (p = 0.0180). Similarly, such a correlation was observed between the number of cigarettes and the modified Bonar score in the lateral meniscus (p = 0.04571). Furthermore, no correlation was identified between the number of cigarettes and the classical Bonar score in the lateral meniscus. There was a statistically significant difference in the collagen variable value between the smokers and nonsmokers groups (p = 0.04525). Conclusions: The microscopic investigation showed no differences in the menisci of smokers and nonsmokers, except for the collagen, which was more organized in smokers. Moreover, the modified Bonar score was correlated negatively with the number of cigarettes, which supports the role of neovascularization in meniscus pathology under the influence of tobacco smoking.

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.

The value of reducing arthroscopic partial meniscectomy in the treatment of degenerative meniscus tears: a budget impact analysis.

AIMS: Numerous studies have shown that arthroscopic partial meniscectomy (APM) is not (cost-) effective in patients with symptoms attributed to a degenerative meniscus tear. We aimed to assess the budget impact of reducing APM in routine clinical practice in this population. MATERIALS AND METHODS: A patient-level state transition model was developed to simulate patients recently diagnosed with a degenerative meniscus tear. Three strategies were compared: "current guideline" (i.e., postpone surgery to at least 3 months after diagnosis), "APM at any time" (i.e., APM available directly after diagnosis), and "nonsurgical" (i.e., APM no longer performed). Total societal costs over 5 years were calculated to determine the budget impact. Probabilistic and deterministic sensitivity analyses were conducted to address uncertainty. RESULTS: The average cost per patient over 5 years were EUR 5,077, EUR 4,577, and EUR 4,218, for the "APM at any time," "current guideline," and "nonsurgical" strategy, respectively. Removing APM from the treatment mix (i.e., 30,000 patients per year) in the Netherlands, resulted in a reduction in health care expenditures of EUR 54 million (95 percent confidence interval [CI] EUR 38 million-EUR 70 million) compared to the "current guideline strategy" and EUR 129 million (95 percent CI EUR 102 million-EUR 156 million) compared to the "APM at any time" strategy. Sensitivity analyses showed that uncertainty did not alter our conclusions. CONCLUSIONS: Substantial costs can be saved when APM is no longer performed to treat symptoms attributed to degenerative meniscus tears in the Netherlands. It is therefore recommended to further reduce the use of APM to treat degenerative meniscus tears.

Delayed multiligament PCL reconstruction is associated with a higher prevalence of intraarticular injury and may influence treatment.

BACKGROUND: The aim of this study was to investigate differences in concomitant injury patterns and their treatment in patients undergoing early (≤ 12 weeks) and delayed (> 12 weeks) primary multiligament posterior cruciate ligament (PCL) reconstruction (PCL-R). METHODS: This study was a retrospective chart review of patients undergoing primary multiligament PCL-R at a single institution between 2008 and 2020. Multiligament PCL-R was defined as PCL-R and concurrent surgical treatment of one or more additional knee ligament(s). Exclusion criteria included isolated PCL-R, PCL repair, and missing data for any variable. Patients were dichotomized into early (≤ 12 weeks) and delayed (> 12 weeks) PCL-R groups based on the time elapsed between injury and surgery. Between-group comparison of variables were conducted with the Chi-square, Fisher's exact, and independent samples t-tests. RESULTS: A total of 148 patients were eligible for analysis, with 57 (38.5%) patients in the early and 91 (61.1%) patients in the delayed multiligament PCL-R groups. Concomitant LCL/PLC reconstruction (LCL-R/PLC-R) was performed in 55 (60%) of delayed multiligament PCL-Rs and 23 (40%) of early PCL-Rs (p = 0.02). Despite similar rates of meniscus injury, concomitant meniscus surgery was significantly more prevalent in the early (n = 25, 44%) versus delayed (n = 19, 21%) multiligament PCL-R group (p = 0.003), with a significantly greater proportion of medial meniscus surgeries performed in the early (n = 16, 28%) compared to delayed (n = 13, 14%) PCL-R group (p = 0.04). The prevalence of knee cartilage injury was significantly different between the early (n = 12, 24%) and delayed (n = 41, 46%) multiligament PCL-R groups (p = 0.01), with more frequent involvement of the lateral (n = 17, 19% vs. n = 3, 5%, respectively; p = 0.04) and medial (n = 31, 34% vs. n = 6, 11%, respectively; p = 0.005) femoral condyles in the delayed compared to the early PCL-R group. CONCLUSIONS: Given higher rates of chondral pathology and medial meniscus surgery seen in delayed multiligament PCL-R, early management of PCL-based multiligament knee injury is recommended to restore knee stability and potentially prevent the development of further intraarticular injury. LEVEL OF EVIDENCE: Level III.

Arthroscopic repair of degenerative medial meniscus tears in patients aged over 45 years resulted in favorable clinical outcomes and low clinical failure rates at a minimum 2-year follow-up.

PURPOSE: This study aimed to investigate clinical and radiological results of arthroscopic repair for isolated medial degenerative meniscus tears (DMTs) in patients over 45 years old at a minimum 2-year follow-up. METHODS: From 2013 to 2017, patients aged over 45 years with isolated medial DMT refractory to conservative management or with true mechanical symptoms who had undergone arthroscopic repair were retrospectively reviewed. Arthroscopic meniscus repair was performed using all-inside or all-inside and inside-out technique in combination with bone marrow venting procedure. Tear patterns were classified according to arthroscopic findings. Magnetic resonance imaging (MRI) and outcome evaluations, including Lysholm score, Tegner activity score, and International Knee Documentation Committee (IKDC) score, were evaluated preoperatively and at the final follow-up. International Cartilage Repair Society grades of the medial compartments and MRI signal at tear sites were assessed preoperatively and at the final follow-up. A grade 0 to 2 signal at the repair site suggested a healed meniscus, whereas a grade 3 signal suggested an unhealed meniscus. Clinical failure was determined according to Barrett criteria. RESULTS: Twenty-seven patients (mean age, 57.7 ± 7.4 years) were enrolled. The mean follow-up was 52.0 ± 15.6 months. Among tear patterns, 48% were complex tears, 30% were horizontal tears, and 22% were other patterns. The mean Lysholm score and IKDC score significantly improved from 53 ± 25 to 89 ± 15 (p < 0.001) and 34 ± 24 to 72 ± 15 (p < 0.001) at the final follow-up, respectively. The median Tegner activity score significantly improved from 1 (range 1-4) to 4 (range 2-7, p < 0.001). Three (11%) patients were considered clinical failures, and five patients (19%) had cartilage lesion progression. At the final follow-up, MRI showed grade 0 in one (4%) patient, grade 1 in nine (33%) patients, grade 2 in six (22%) patients, and grade 3 in eleven (41%) patients. CONCLUSION: Arthroscopic repair of isolated medial DMT refractory to conservative management or with true mechanical symptoms in patients aged over 45 years had good to excellent clinical outcomes with low clinical failure rates, despite unhealed menisci being observed on MRI in 41% of patients at a mean 4.3-year follow-up. Arthroscopic repair could be a treatment option for these patients. LEVEL OF EVIDENCE: IV.

No risk of iatrogenic peroneal nerve injury in all-inside lateral meniscal repair with either 14- or 18-mm needles through the popliteus tendon in the standard arthroscopic knee conditions.

PURPOSE: The objectives of this prospective study were to evaluate the risk of peroneal nerve (PN) injury in simulated all-inside lateral meniscal repair with sutures placed through the popliteus tendon (PT) and to determine the optimal needle length. METHODS: Twenty-nine axial magnetic resonance images (MRI) of postoperative knees with infused intra-articular fluid and in a figure-of-four position were used. The cross-sectional length of the PT was divided into four equal parts with measurements performed at the 25%, 50% and 75% points according to their anteroposterior arrangement. Simulated repairs were performed with 14-mm and 18-mm straight needles via the anteromedial (AM) and anterolateral (AL) portals. Distances from the needle tip following full insertion through the PT to the PN and from the anterior PT border to the posterior knee capsule were measured to determine PN injury risk and ideal needle insertion depths at the different landmarks. RESULTS: Simulated repairs on the 29 knee MRI images resulted in no incidences of PN injury. The average distances from the needle tip to the PN of the 14-mm needle were significantly greater than the 18-mm needle in all the simulated repairs (P < 0.02), except at the 25% point in the AM approach. When using the 14-mm needle, capsule underpenetration was found in three knees (10.3%) at the 25% point during the AM approach, in one knee (3.4%) at the 50% and 75% points in the AM approach, and in all repairs from the AL portal. The average distances from the anterior PT border to the capsule at the 25%, 50%, and 75% division points on the PT in the AM approach were 7.7 ± 2.7 mm, 7.9 ± 2.5 mm and 7.6 ± 2.8 mm, respectively, whilst in the AL approach were 8.4 ± 2.9 mm, 8.1 ± 2.8 mm and 7.6 ± 2.7 mm. CONCLUSION: Simulated all-inside lateral meniscal repair with suture placement through the PT with 14-mm and 18-mm needles was safe. The measurements in this study can be used to determine potential PN injury risk in relation to the PT and the appropriate needle length for safe lateral meniscal repairs.

Health-economic evaluation of meniscus tear treatments: a systematic review.

PURPOSE: To evaluate the overall evidence of published health-economic evaluation studies on meniscus tear treatment. METHODS: Our systematic review focuses on health-economic evaluation studies of meniscus tear treatment interventions found in PubMed and Embase databases. A qualitative, descriptive approach was used to analyze the studies' results and systematically report them following PRISMA guidelines. The health-economic evaluation method for each included study was categorized following one of the four approaches: partial economic evaluation (PEE), cost-effectiveness analysis (CEA), cost-benefit analysis (CBA), or cost-utility analysis (CUA). The quality of each included study was assessed using the Consensus on Health Economic Criteria (CHEC) list. Comparisons of input variables and outcomes were made, if applicable. RESULTS: Sixteen studies were included; of these, six studies performed PEE, seven studies CUA, two studies CEA, and one study combined CBA, CUA, and CEA. The following economic comparisons were analyzed and showed the respective comparative outcomes: (1) meniscus repair was more cost-effective than arthroscopic partial meniscectomy (meniscectomy) for reparable meniscus tear; (2) non-operative treatment or physical therapy was less costly than meniscectomy for degenerative meniscus tear; (3) physical therapy with delayed meniscectomy was more cost-effective than early meniscectomy for meniscus tear with knee osteoarthritis; (4) meniscectomy without physical therapy was less costly than meniscectomy with physical therapy; (5) meniscectomy was more cost-effective than either meniscus allograft transplantation or meniscus scaffold procedure; (6) the conventional arthroscopic instrument cost was lower than laser-assisted arthroscopy in meniscectomy procedures. CONCLUSION: Results from this review suggest that meniscus repair is the most cost-effective intervention for reparable meniscus tears. Physical therapy followed by delayed meniscectomy is the most cost-effective intervention for degenerative meniscus tears. Meniscus scaffold should be avoided, especially when implemented on a large scale. LEVEL OF EVIDENCE: Systematic review of level IV studies.

Ipsilateral chondral lesions worsen the long-term prognosis following arthroscopic partial medial meniscectomy.

PURPOSE: The effect of knee cartilage defects that are detected during partial meniscectomy remains controversial in terms of the long-term prognosis on knee function. This study aimed to investigate the effect of concurrent medial compartment focal cartilage lesions on the long-term prognosis of knee function in patients who underwent arthroscopic partial medial meniscectomy for traumatic medial meniscal tears. METHODS: This retrospective study analyzed 46 patients who underwent arthroscopic partial medial meniscectomy between 1991 and 2008 by a single surgeon. Twenty-one patients who underwent arthroscopic partial medial meniscectomy due to traumatic meniscal tear had focal chondral lesions only at the medial compartment, and these patients were assigned to group A. Twenty-five patients who had no cartilage lesions in any compartments were assigned to group B. The age, sex, body mass index (BMI), follow-up time, age at the time of surgery, clinical and radiological scores, and perioperative arthroscopy findings were analyzed. RESULTS: The mean follow-up time was 20 ± 3.7 years. No significant difference was found in the demographic data, and the average age of the patients at the time of operation was 35 ± 9.5 years. Both groups had improved Lysholm score at the last follow-up. Although no difference was found between the groups during the preoperative period, group B had a higher Lysholm score at the last follow-up than group A. The mean International Knee Documentation Committee (IKDC) and Knee injury and Osteoarthritis Outcome Score (KOOS) scores at the last follow-up were significantly higher in group B. The mean Kellgren-Lawrence grades in the operated knees of group A were higher than those of group B. In group A, a negative correlation was found between the BMI and postoperative Lysholm (r = - 0.461, p = 0.03) IKDC (r = - 0.433, p = 0.05) and KOOS (r = - 0.565, p = 0.008) scores. In group B, no correlation was found between BMI and any score. CONCLUSION: Among patients who underwent arthroscopic partial medial meniscectomy with an average follow-up of 20 years, those with concurrent focal cartilage defect in the medial compartment had clinically and radiologically worse outcomes than patients without any cartilage defect. Therefore, orthopedic surgeons should be meticulous before performing any arthroscopic partial medial meniscectomy in case of concurrent cartilage lesion. LEVEL OF EVIDENCE: Level III.

Coronal extrusion of the lateral meniscus does not increase after pullout repair of the posterior root of the lateral meniscus at short-term follow-up.

PURPOSE: Posterior lateral meniscus root (PLMR) tears are injuries that commonly occur together with anterior cruciate ligament (ACL) tears. The aim of this study was to evaluate the clinical and radiological outcome of PLMR repair accompanying ACL reconstruction. Specifically, PLMR healing rates, meniscal extrusion behavior and their influence on patient-reported outcome measures (PROMs) were analyzed. It was hypothesized that PLMR repair shows satisfactory healing rates and coronal meniscal extrusion does not increase significantly following PLMR repair. METHODS: Patients that underwent PLMR repair between 2014 and 2019 were evaluated at least 12 months postoperatively. At follow-up, magnetic resonance imaging (MRI) was performed in order to evaluate the PLMR healing behavior (complete vs. partial vs. no healing) as well as the coronal and sagittal meniscal extrusion in comparison with the preoperative MRI. Additionally, patient-reported outcome measures (PROMs; Lysholm score, International Knee Documentation Committee subjective knee form [IKDC]) were compiled. Pre- and postoperative meniscal extrusion were tested for statistical significance using the paired t test. The Kruskal-Wallis test was used to compare extrusion values and PROMs in relation to different healing states. A correlation analysis was conducted using the Pearson correlation coefficient between differences in meniscal extrusion and PROMs. RESULTS: Out of 25 patients, 18 patients (72.0%; 11 male and seven female) were available for final assessment at a mean follow-up of 40.8 ± SD 17.5 months. One revision PLMR repair was performed five months after the initial repair. In 14 cases (77.8%), healing of the lateral meniscus was observed (6 × complete, 8 × partial). Coronal extrusion of the lateral meniscus did not increase significantly following PLMR repair (2.0 ± 1.5 mm vs. 2.1 ± 1.3 mm; p = 0.645). Sagittal extrusion increased significantly (25.7 ± 2.4 mm vs. 27.0 ± 1.4 mm; p < 0.001). The healing status of the PLMR showed no significant association with meniscal extrusion or PROMs (p > 0.05). But a higher increase in coronal meniscal extrusion negatively affected PROMs (Lysholm score: p = 0.046, r = - 0.475; IKDC: p = 0.003, r = - 0.651). CONCLUSION: High healing rates of the PLMR and no significant increase in coronal extrusion may be expected following combined PLMR repair and ACL reconstruction. But a greater increase in postoperative coronal meniscal extrusion correlates with less favorable clinical results. A greater increase in sagittal extrusion was observed, but this did not influence the clinical outcome. LEVEL OF EVIDENCE: Retrospective Case Series; IV.

Do associated proximal fibula fractures help predict the severity of tibial plateau fractures?

PURPOSE: Proximal fibula fractures are often associated with tibial plateau fractures, but their relationship is poorly characterized. The purpose of this study was to better define the relationship between tibial plateau injury severity and presence of associated soft tissue injuries. METHODS: A retrospective review was performed on all operatively treated tibial plateau fractures at a Level 1 trauma center over a 5-year period. Patient demographics, injury radiographs, CT scans, operative reports and follow-up were reviewed. RESULTS: Queried tibial plateau fractures from 2014 to 2019 totaled 217 fractures in 215 patients. Fifty-two percent were classified as AO/OTA 41B and 48% were AO/OTA 41C. Thirty-nine percent had an associated proximal fibula fracture. The presence of a proximal fibula fracture had significant correlation with AO/OTA 41C fractures, as compared with AO/OTA 41B fractures (chi-square, p < 0.001). Of the patients with a lateral split depression type tibial plateau fracture, the presence of a proximal fibula fracture was associated with more articular comminution, measured by number of articular fragments (mean = 4.0 vs. 2.9 articular fragments, p = 0.004). There was also a higher rate of meniscal injury in patients with proximal fibula fractures (37% vs. 20%, p = 0.003). CONCLUSIONS: There was a significant relationship between the higher energy tibial plateau fracture type (AO/OTA 41C) and the presence of an associated proximal fibula fracture. The presence of a proximal fibula fracture with a tibial plateau fracture is an indicator of a higher energy injury and a higher likelihood of meniscal injury.

Development of convolutional neural network model for diagnosing meniscus tear using magnetic resonance image.

BACKGROUND: Deep learning (DL) is an advanced machine learning approach used in diverse areas, such as image analysis, bioinformatics, and natural language processing. A convolutional neural network (CNN) is a representative DL model that is advantageous for image recognition and classification. In this study, we aimed to develop a CNN to detect meniscal tears and classify tear types using coronal and sagittal magnetic resonance (MR) images of each patient. METHODS: We retrospectively collected 599 cases (medial meniscus tear = 384, lateral meniscus tear = 167, and medial and lateral meniscus tear = 48) of knee MR images from patients with meniscal tears and 449 cases of knee MR images from patients without meniscal tears. To develop the DL model for evaluating the presence of meniscal tears, all the collected knee MR images of 1048 cases were used. To develop the DL model for evaluating the type of meniscal tear, 538 cases with meniscal tears (horizontal tear = 268, complex tear = 147, radial tear = 48, and longitudinal tear = 75) and 449 cases without meniscal tears were used. Additionally, a CNN algorithm was used. To measure the model's performance, 70% of the included data were randomly assigned to the training set, and the remaining 30% were assigned to the test set. RESULTS: The area under the curves (AUCs) of our model were 0.889, 0.817, and 0.924 for medial meniscal tears, lateral meniscal tears, and medial and lateral meniscal tears, respectively. The AUCs of the horizontal, complex, radial, and longitudinal tears were 0.761, 0.850, 0.601, and 0.858, respectively. CONCLUSION: Our study showed that the CNN model has the potential to be used in diagnosing the presence of meniscal tears and differentiating the types of meniscal tears.

A bone bruise at the lateral and medial tibial plateau with an anterior cruciate ligament injury is associated with a meniscus tear.

PURPOSE: Bone bruises with anterior cruciate ligament (ACL) injury are well studied, but the association between bone bruises and multiple factors is unclear. The main objective of this study was to investigate the association between bone bruising and ACL injury and concomitant injury as well as clinical and functional scores. The second objective was to investigate the presence and distribution patterns of bone bruises. METHOD: A total of 176 patients who underwent ACL reconstruction for primary ACL injury were included. The demographic characteristics and responses to clinical and functional assessments (the Visual Analog Scale for activities of daily living and sports, the Cincinnati Knee Rating System, the Lysholm score, the Knee Osteoarthritis Outcome Score and side-to-side difference in anterior laxity) were recorded at the initial visit. Concomitant injuries were evaluated by intraoperative assessment. RESULTS: Bone bruises were detected in 141 patients (80.1%). The lateral femoral condyle (LFC) was the most common site in 116 patients (65.9%), followed by the lateral tibial plateau (LTP) in 82 patients (46.6%), medial tibial plateau (MTP) in 47 patients (26.7%) and medial femoral condyle (MFC) in 29 patients (16.5%). Regarding the distribution patterns, bone bruising at only the LFC, which was the most common pattern, was detected in 38 patients (27.0%). Bone bruising at the LTP or MTP was significantly associated with lateral (LM) and medial meniscus (MM) tears (odds ratios 4.0, 3.0, 4.3 and 40.5, 95% confidence intervals 1.5-11.6, 1.2-15.1, 1.2-17.3 and 8.6-283.0, respectively). No marked differences in the functional or clinical scores were noted. The severity of bone bruising at the MTP was significantly associated with MM tears and that at the LTP was significantly associated with LM tears. (p < 0.01). CONCLUSION: This study showed association between bone bruising at LTP and LM tears or at MTP and MM tears. Additionally, it provided detailed information on the presence and distribution patterns of bone bruises at each anatomic site. These findings are clinically relevant and will aid in preoperatively diagnosing meniscus tears in cases of ACL injury. LEVEL OF EVIDENCE: Level III.

Treatment of post-meniscectomy knee symptoms with medial meniscus replacement results in greater pain reduction and functional improvement than non-surgical care.

PURPOSE: Partial meniscectomy is a common orthopedic procedure intended to improve knee pain and function in patients with irreparable meniscal tears. However, 6-25% of partial meniscectomy patients experience persistent knee pain after surgery. In this randomized controlled trial (RCT) involving subjects with knee pain following partial meniscectomy, it was hypothesized that treatment with a synthetic medial meniscus replacement (MMR) implant provides significantly greater improvements in knee pain and function compared to non-surgical care alone. METHODS: In this prospective, multicenter RCT, subjects with persistent knee pain following one or more previous partial meniscectomies were randomized to receive either MMR or non-surgical care. This analysis evaluated the 1-year outcomes of this 2-year clinical trial. Patient-reported knee pain, function, and quality of life were measured using nine separate patient-reported outcomes. The primary outcomes were the pain subscale of the Knee injury and Osteoarthritis Outcome Score (KOOS) and the average of all five KOOS subscales (KOOS Overall). Treatment cessation was defined as permanent device removal in the MMR group and any surgical procedure to the index knee in the non-surgical care group. RESULTS: Treated subjects had a median age of 52 years old (range 30-69 years) and one or more previous partial meniscectomies at a median of 34 months (range 5-430 months) before trial entry. Among 127 subjects treated with either MMR (n = 61) or non-surgical care (n = 66), 11 withdrew from the trial or were lost to follow-up (MMR, n = 0; non-surgical care, n = 11). The magnitude of improvement from baseline to 1 year was significantly greater in subjects who received MMR in both primary outcomes of KOOS Pain (P = 0.013) and KOOS Overall (P = 0.027). Treatment cessation was reported in 14.5% of non-surgical care subjects and only 4.9% of MMR subjects (n.s.). CONCLUSION: Treatment with the synthetic MMR implant resulted in significantly greater improvements in knee pain, function, and quality of life at 1 year of follow-up compared to treatment with non-surgical care alone. LEVEL OF EVIDENCE: I.

Clinical and radiographic results after arthroscopic repair of lateral meniscus tear in lateral-depression tibial plateau fracture.

INTRODUCTION: To evaluate the clinical and radiographic results of AR/IF and meniscus repair for treating lateral meniscus (LM) tears associated with lateral tibial plateau fractures and to identify the factors associated with LM tear. MATERIALS AND METHODS: Forty-two patients with lateral plateau fractures (Schatzker types II and III) treated by AR/IF were included retrospectively. Radiographic evaluations using the Rasmussen system and computerized tomography (CT) were performed. Clinical evaluations were also conducted at final follow-up. Second-look arthroscopy was applied during metal removal. RESULTS: All fractures were healed after 46.3 months of follow-up. The mean Tegner activity level was not decreased significantly, going from 7.1 ± 2.1 pre-injury to 6.6 ± 2.3 at final follow-up (p = 0.301). However, the amount of depression noted on CT imaging was significantly decreased from 8.9 mm ± 4.4 to 1.2 mm ± 1.3 (p = 0.000). The mean Rasmussen radiologic score at final follow-up was 14.5 ± 5.3 points. Osteoarthritis was progressed in six patients (14.3%). Twenty-five patients had concomitant LM tear, with 18 cases treated by repair and the remaining ones treated by partial meniscectomy. Preoperative joint depression (> 11 mm) was significantly associated with the risk of LM tear (p = 0.024; odds ratio (OR): 9.0, 95% confidence interval (CI): 1.018-79.545) and most of those lesions could be repaired (p = 0.001). Postoperatively, 16 repaired patients were evaluated by second-look arthroscopy; 15 had healed completely and one had healed partially. CONCLUSION: LM tears are frequently combined with lateral tibial plateau fracture, especially in correlation with more than 11 mm of joint depression, though most of those lesions can be repaired at the time of fracture fixation. AR/IF with arthroscopic meniscus repair could achieve good clinical and radiographic outcomes when treating Schatzker types II and III tibial plateau fractures. STUDY DESIGN: Level IV retrospective cohort study.

A rare double-delta sign in a bucket handle tear of lateral meniscus: A case report.

The two most common causes of a meniscus tear are trauma and degenerative processes. Meniscus tears clinically present with pain, swelling and limited mobility of the knee joint. Bucket handle tear (BHT) is a full-thickness tear of the meniscus usually involving the inner portion of the medial meniscus. It is three times more likely to occur in the medial meniscus than in the lateral meniscus. Various signs such as the double anterior cruciate ligament (ACL) sign, double posterior cruciate ligament (PCL) sign, and triple PCL sign have helped radiologists diagnose this tear on magnetic resonance imaging (MRI). This case report is about a BHT of the less commonly involved lateral meniscus identified with a double-delta sign on MRI which has rarely been reported. A comparison of various radiological signs reported in the literature has been made, which will aid radiologists in diagnosis and have importance for the medical literature.