Patella dislocation: an overview

YOLOv8 algorithm-aided detection of patellar instability or dislocation on knee joint MRI images

BackgroundPatellar instability (PI) or patellar dislocation (PD) is challenging to diagnose accurately based on medical history and clinical manifestations alone. While X-ray, computed tomography (CT), and magnetic resonance imaging (MRI) are commonly employed for detecting PI or PD, computer vision has not yet been widely utilized for this purpose.PurposeTo explore the feasibility of computer vision, specifically the You Only Look Once (YOLO) algorithm, in identifying patellar instability or dislocation.Material and MethodsA total of 550 patients (190 diagnosed with patellar instability or dislocation) were divided into a training set (n = 360), validation set (n = 90), and external test set (n = 100). Four indicators were measured on transverse knee MRI scans to determine the presence of patellar instability, and 450 images were labeled using Labelme software. YOLO version 8 (YOLOv8) was refined using these labeled images and validated on 100 unlabeled images. The diagnostic accuracy of YOLOv8 was compared with that of a junior radiologist.ResultsThe sensitivity, specificity, and accuracy of the refined YOLO model and the junior radiologist were 62%, 97%, and 83%, and 62%, 82%, and 74%, respectively. Although the YOLO model demonstrated slightly higher accuracy, the difference did not reach statistical significance (P = 0.093). The YOLO model required approximately 14.01 ± 10.34 ms to interpret each image, significantly shorter than the 9.55 ± 2.39 s required by the radiologist (P < 0.001).ConclusionThe refined YOLOv8 model is not inferior to junior radiologists in identifying patellar instability or dislocation and offers a significantly faster interpretation time.

The impact of patellofemoral joint diseases on functional outcomes and prosthesis survival in patients undergoing unicompartmental knee arthroplasty: a systematic review and meta-analysis

BACKGROUND

Patellofemoral joint (PFJ) diseases are chronic degenerative conditions that contribute to knee joint symptoms. Unicompartmental knee arthroplasty (UKA) is widely regarded as an effective treatment for knee osteoarthritis (KOA); however, its specific indications remain a subject of debate.

HYPOTHESIS

Patients with PFJ disease are expected to experience outcomes post-UKA comparable to those of patients without PFJ disease.

METHODS

We conducted this meta-analysis following the guidelines outlined by the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA). A comprehensive search of PubMed, Embase, and Web of Science databases was conducted for studies examining the association between PFJ disease and UKA, including publications up to September 2024. Extracted data encompassed author, publication year, country, disease type, prosthesis type, sample size, mean patient age, gender distribution, follow-up duration, PFJ disease prevalence at surgery, diagnostic methods, and whether PFJ disease was considered a contraindication for UKA. To maintain objectivity, only studies in which PFJ diseases were visually identifiable were included in the meta-analysis. Statistical analyses were performed using Stata 15.0 and Review Manager 5.4.1. A random-effects meta-analysis was conducted to evaluate the Oxford Knee Score (OKS), Knee Society Score (KSS), flexion range of motion (ROM), Forgotten Joint Score (FJS), Tegner activity score, and prosthesis survival rate, with outcomes stratified by PFJ disease type (PFJ degeneration or patella cartilage injury). Mean differences, confidence intervals, and P values were calculated for comparisons between the PFJ disease and non-PFJ disease groups. The Methodological Index for Non-Randomized Studies (MINORS) criteria and the Newcastle-Ottawa Scale (NOS) were applied to evaluate the risk of bias. To address heterogeneity, sensitivity analyses were performed, and publication bias was assessed using funnel plots and Egger's test.

RESULTS

A total of 14,866 knees from 48 relevant studies were included in this systematic review. Methodological quality was assessed using the MINORS criteria, with case series scoring 11.0/16 and cohort studies scoring 18.2/24. PFJ degeneration emerged as the most studied condition, followed by patella cartilage injury. Clinical outcomes assessments indicated that medial PFJ degeneration, anterior knee pain, patella cartilage damage, and patella baja did not significantly impact UKA outcomes or prosthesis survival. However, severe lateral PFJ degeneration, lateral patellar subluxation, lateral trochlear osteophytes, and patellar bone marrow edema did influence results. Fifteen high-quality studies were included in the meta-analysis, involving 6080 patients-1338 in the PFJ disease group and 4,742 in the non-PFJ disease group. With an average NOS score of 7.2, the studies were generally of high quality. Meta-analysis results showed no significant differences between groups in final follow-up OKS, FJS, Tegner activity score, or prosthesis survival rate. However, the PFJ disease group had lower KSS and reduced flexion ROM compared to the non-PFJ disease group. Subgroup analysis further revealed that the PFJ degeneration group scored lower than the patella cartilage injury group on OKS, KSS, and flexion ROM following UKA.

CONCLUSION

In summary, PFJ disease was found to have limited impact on UKA outcomes; however, caution is recommended for cases involving severe lateral PFJ degeneration due to potential restrictions in postoperative knee function, particularly affecting flexion ROM in UKA patients.

Predicting two-year return-to-sport failure after medial patellofemoral ligament reconstruction in patellar dislocation patients with bone abnormalities

PURPOSE

To develop a comprehensive and validated personalized scoring system based on anatomical characteristics to predict the probability of failure to return to sport after medial patellofemoral ligament reconstruction in patients with patellar dislocation.

METHODS

312 patients with medial patellofemoral ligament reconstruction in our hospital from 2013 to 2023 were included. Demographic and anatomical characteristics were collected retrospectively. A backward stepwise approach was used to identify independent predictors, and a nomogram was constructed to predict the probability of recurrence. The predictive performance was evaluated by receiver operating characteristic curves, calibration diagram and decision curve analysis.

RESULTS

Multivariate analysis showed that increased tibial tubercle-trochlear groove (TT-TG) distance, trochlear dysplasia, increased femoral anteversion angle, and patellar alta were independent risk factors for failure of return to sport after medial patellofemoral ligament reconstruction. Validation of this column graph in the training cohort and validation cohort showed strong predictive power, with areas under the curve of 0.850 and 0.844, respectively. The nomogram has good calibration and good clinical practicability.

CONCLUSION

The study developed a personalized predictive nomogram with 4 predictors (increased TT-TG distance, trochlear dysplasia, increased femoral anteversion angle, and patellar alta) that allowed surgeons to stratify the risk of failure to return to sport after medial patellofemoral ligament reconstruction and recommend skeletal surgery for patients with these factors.

LEVEL OF EVIDENCE

Level III.

Differences in Outcomes between Patellar Dislocations Managed in Emergent versus Non-Emergent Care Settings

Patellar dislocations occur at a much higher rate in military than civilian populations. Past population-level studies have shown that surgical management is as good as or superior to conservative care and may reduce future reoccurrences. Although in acute cases and in civilian clinics, patellar dislocations are usually managed first in an emergent care setting, previous work suggests this can lead to increased costs. This study compared differences in downstream care type and intensity of services based on whether initial care occurred in emergent or non-emergent care settings. In our sample of 1,523 Military Health System (MHS) beneficiaries with patellar dislocation and 2-year follow-up, we found non-significant differences in costs, intensity of services, and rates of surgical repair regardless of whether the patient was initially seen in an emergent versus non-emergent care setting. Although we found significant increases in the use of imaging, patellar dislocation-related medical visits, and frequency of closed treatment approaches in emergent care settings, these values were very small and likely not clinically significant. These findings, which included all the patellar dislocations reported across the entire MHS in a 24-month period, suggest that neither emergent nor non-emergent care settings are likely to influence the long-term care received by the individual.