Search

OBJECTIVE: Deep learning (DL) image reconstruction has the potential to disrupt the current state of MRI by significantly decreasing the time required for MRI examinations. Our goal was to use DL to accelerate MRI to allow a 5-minute comprehensive examination of the knee without compromising image quality or diagnostic accuracy. MATERIALS AND METHODS. A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multisequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. After training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully sampled data acquisition and a 1.88-fold acceleration compared with our standard twofold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of six readers to detect internal derangement of the knee was compared for clinical and DL-accelerated images. RESULTS. We found a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would produce discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence. CONCLUSION. An optimized DL model allowed acceleration of knee images that performed interchangeably with standard images for detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.

OBJECTIVE. Cartilage loss on preoperative knee MRI is a predictor of poor outcomes after arthroscopic partial meniscectomy. The purpose of this study was to compare the ability to predict outcomes after arthroscopic partial meniscectomy with a clinically used modified Outerbridge system versus a semiquantitative MRI Osteoarthritis Knee Score system for grading cartilage loss. MATERIALS AND METHODS. Patients who underwent preoperative knee MRI within 6 months of arthroscopic partial meniscectomy and who had outcomes available from the time of surgery and 1 year later were eligible for inclusion. Cases were evaluated by two radiologists and one radiology fellow with the use of both grading systems. The accuracy of each system in discriminating between surgical success and failure was estimated using the ROC curve (AUC) with 95% CIs. A Wald test was used to assess noninferiority of the clinical grading system. Interreader agreement regarding the accuracy of the grading systems in predicting outcomes was also compared. RESULTS. A total of 78 patients (38 women and 40 men; mean age, 56.6 years) were included in the study. A prediction model using clinical grading (AUC = 0.695; 95% CI, 0.566-0.824) was noninferior (p = 0.047) to a model using MRI Osteoarthritis Knee Score grading (AUC = 0.683; 95% CI, 0.539-0.827). Both MRI prediction models performed better than a model using demographic characteristics only (AUC = 0.667; 95% CI, 0.522-0.812). Inter-reader agreement with clinical grading (80.8%) was higher than that with MRI Osteoarthritis Knee Score grading (65.0%; p = 0.012). CONCLUSION. A clinically used system to grade cartilage loss on MRI is as effective as a semiquantitative system for predicting outcomes after arthroscopic partial meniscectomy, while also offering improved interreader agreement.

The objective of our study was to evaluate the association between anterior tibial translation and injuries on the posterior horn medial meniscus (PHMM) and the integrity of the brake stop mechanism of the PHMM in the anterior cruciate ligament (ACL)-deficient knee.This retrospective study included 85 consecutive patients with an arthroscopically confirmed complete ACL tear. Anterior tibial translation was quantitatively measured using sagittal MRI at the midpoint of the lateral femoral condyle. The "uncovered medial meniscus" sign was considered positive if a vertical line tangent to the posteriormost margin of the medial tibial plateau intersected the PHMM at the midpoint of the medial femoral condyle on sagittal MRI. Concomitant injuries on the structures of the posteromedial and posterolateral corners of the knee, including PHMM tear and meniscal ramp lesion, were recorded. Stratified subgroup analysis and multivariable regression analysis were performed to identify factors associated with anterior tibial translation.The uncovered medial meniscus sign was positive in 21.2% (18/85) of patients and was significantly associated with anterior tibial translation. In the stratified subgroup analysis and multivariable regression analysis, positive uncovered medial meniscus sign consistently showed a significant association with anterior tibial translation and generated an additional 2.8 mm of anterior tibial translation. Other injuries, including PHMM tear and meniscal ramp lesion, were not associated with anterior tibial translation.The uncovered medial meniscus sign showed a statistically significant correlation with anterior tibial translation and could be a useful marker for the lost brake stop mechanism of PHMM in the ACL-deficient knee.

The purpose of this study is to determine the association between polyethylene surface damage and the severity of frondlike hypertrophied synovitis, joint distention, capsular thickness, and osteolysis on MRI compared with other patient factors. Another goal of this study is to ascertain the interobserver reliability in MRI evaluation of synovitis.MR images of 61 patients who had undergone revision total knee arthroplasty (TKA) were retrospectively reviewed. The two MRI reviewers were blinded to clinical and retrieval data. The retrieved polyethylene tibial inserts were graded to determine the severity of surface damage. The association of MRI features with surface damage was assessed using Spearman correlation coefficients and multiple linear regression. Interobserver reliability was assessed using the kappa statistic.Correlations were moderate between the surface damage score and MRI synovitis severity (r = 0.46; p0.001) and joint distention (r = 0.41; p = 0.001). Multiple linear regression showed that the MRI synovitis score (p = 0.045), male sex (p = 0.007), body mass index (p = 0.041), and the time since implantation (p0.0001) predicted the surface damage score. Substantial interobserver agreement was shown for MRI grading of synovitis (κ = 0.72; 95% CI, 0.65-0.80).The magnitude of frondlike hypertrophied synovitis on MRI is significantly associated with polyethylene surface damage in patients who undergo revision TKA. The finding of severe frondlike synovitis on MR images of patients with TKA should raise the possibility of polyethylene surface damage. However, time since implantation is a stronger predictor of surface damage.

The purpose of this study is to retrospectively investigate the frequency of a focal defect at the lateral patellar retinaculum on knee MRI and to determine the variables that are significantly associated with the defect.Two radiologists independently reviewed 99 knee MR images for the presence of a focal defect at the lateral patellar retinaculum and categorized patients with concordant results into two groups: a group with the defect (≥ 3 mm; group 1) and a group without the defect (3 mm; group 2). Clinical and radiologic variables, including the Kellgren-Lawrence radiographic grade, subcutaneous fat thickness, infrapatellar fat pad area, and the amount of joint effusion, were evaluated. The size and location of the defect were measured in group 1. To correlate MRI and histologic findings, MRI was performed for 11 cadavers, and three histologic specimens were obtained.Of the 99 knee MR images, concordant results between two reviewers were obtained for a total of 96 knees (97%): 25 knees (26%) in group 1 and 71 knees (74%) in group 2. A statistically significant difference between groups (p = 0.033) was noted for the infrapatellar fat pad area only. In all three cadaveric specimens, the lateral patellar retinaculum was more loose and sparse than the medial patellar retinaculum, and this site corresponded to the location of the defect on MRI.A focal defect of the lateral patellar retinaculum was not found to be a rare finding on knee MRI (frequency, 26%), and it may be a normal variant rather than a pathologic change. In addition, we suspect that a focal defect can be a route of infrapatellar fat herniation and a route of superficial extension of the infrapatellar fat pad lesion without a lateral patellar retinaculum tear or invasion.

BACKGROUND. Potential approaches for abbreviated knee MRI, including prospective acceleration with deep learning, have achieved limited clinical implementation. OBJECTIVE. The objective of this study was to evaluate the interreader agreement between conventional knee MRI and a 5-minute 3D quantitative double-echo steady-state (qDESS) sequence with automatic T2 mapping and deep learning super-resolutionaugmentation and to compare the diagnostic performance of the two methods regarding findings from arthroscopic surgery. METHODS. Fifty-one patients with knee pain underwent knee MRI that included an additional 3D qDESS sequence with automatic T2 mapping. Fourier interpolation was followed by prospective deep learning super resolution to enhance qDESS slice resolution twofold. A musculoskeletal radiologist and a radiology resident performed independent retrospective evaluations of articular cartilage, menisci, ligaments, bones, extensor mechanism, and synovium using conventional MRI. Following a 2-month washout period, readers reviewed qDESS images alone followed by qDESS with the automatic T2 maps. Interreader agreement between conventional MRI and qDESS was computed using percentage agreement and Cohen kappa. The sensitivity and specificity of conventional MRI, qDESS alone, and qDESS plus T2 mapping were compared with arthroscopic findings using exact McNemar tests. RESULTS. Conventional MRI and qDESS showed 92% agreement in evaluating all tissues. Kappa was 0.79 (95% CI, 0.76–0.81) across all imaging findings. In 43 patients who underwent arthroscopy, sensitivity and specificity were not significantly different (p = .23 to > .99) between conventional MRI (sensitivity, 58–93%; specificity, 27–87%) and qDESS alone (sensitivity, 54–90%; specificity, 23–91%) for cartilage, menisci, ligaments, and synovium. For grade 1 cartilage lesions, sensitivity and specificity were 33% and 56%, respectively, for conventional MRI; 23% and 53% for qDESS (p = .81); and 46% and 39% for qDESS with T2 mapping (p = .80). For grade 2A lesions, values were 27% and 53% for conventional MRI, 26% and 52% for qDESS (p = .02), and 58% and 40% for qDESS with T2 mapping (p < .001). CONCLUSION. The qDESS method prospectively augmented with deep learning showed strong interreader agreement with conventional knee MRI and near-equivalent diagnostic performance regarding arthroscopy. The ability of qDESS to automatically generate T2 maps increases sensitivity for cartilage abnormalities. CLINICAL IMPACT. Using prospective artificial intelligence to enhance qDESS image quality may facilitate an abbreviated knee MRI protocol while generating quantitative T2 maps.

OBJECTIVE. Patients who undergo knee MRI for presumed musculoskeletal disease can have unexpected vascular findings or pathology in the imaged field. Some vascular processes are limb threatening and affect treatment planning and patient outcome. CONCLUSION. Unexpected vascular findings on knee MRI can range from incidental to symptomatic and can include such processes as variant anatomy, aneurysm, traumatic injury, and neoplasm. The assessment for vascular pathology should be a key component of every radiologist's search pattern when evaluating knee MRI.

The purpose of this article is to evaluate the quality of reports of knee MRI examinations in form, content, and diagnosis and to assess the effect of three different quality improvement measures.Reports of 500 knee MRI examinations (first round, or baseline) were reviewed retrospectively by five musculoskeletal radiologists. Fifteen different criteria were assessed for formal and content-related quality of reports. Diagnostic discrepancies were categorized using a 5-point scale, as follows: I, no deviation; II, undetected finding, clinically irrelevant; III, wrong interpretation of finding, clinically irrelevant; IV, undetected finding, clinically relevant; and V, wrong interpretation of finding, clinically relevant. Then three different quality improvement measures were applied prospectively to a total of 510 consecutive reports: a quiet work environment, double reading, and the use of a structured report template. These 510 knee MRI reports (second round) were evaluated using the same criteria.A statistically significant improvement in 13 of 15 criteria was found in the second-round reports: orthographic errors improved from 32.4% to 22.0% (p0.001) of reports and digital speech recognition errors improved from 8.4% to 7.6% (p = 0.660). Missing anatomic structures decreased from 6.3% to 0.4%. Diagnostic discrepancies were less frequently found (12.9% vs 20.8%; p = 0.001), along with the following changes in categorization (first-round results are in parentheses): I, 87.1% (79.2%); II, 9.2% (16.8%); III, 2.3% (1.0%); IV, 1.0% (2.6%); and V, 0.4% (0.4%). Quality improvement was found in all three measure groups, without statistical significance among the groups, except for the orthographic errors (p0.001), which were most common in the template group.All three quality improvement measures significantly improved the quality of the knee MRI reports, but no measure was clearly superior to the others.

The purpose of this study was to characterize meniscal ossicles and their association with meniscal root tears.A two-center retrospective assessment of 65 knee MRI studies with meniscal ossicles was performed. The relationship of the ossicle to the meniscal root and horn was assessed along with other findings of internal derangement of the knee.Meniscal ossicles were identified in patients ranging from 23 to 80 years old. The ossicles were located within the posterior horn and root of the medial meniscus in 57 of 65 (88%) examinations. Associated meniscal tears were seen at the site or adjacent to the ossicle in all but one examination (98%). Meniscal extrusion was present in 52% (34/65) of examinations. Associated findings included articular cartilage loss, which was severe in 51% (33/65) of examinations. Anterior cruciate ligament injury or prior anterior cruciate ligament reconstruction surgery was also identified in 58% (38/65) of examinations.Our findings show that the vast majority of meniscal ossicles are associated with posterior horn or meniscal root tears and a high incidence of focal articular cartilage loss as well as anterior cruciate ligament tears.

Radiographs are often obtained before MRI in the evaluation of pediatric knee pain, but the value of these radiographs is undefined. The purpose of this study was to determine the marginal value of knee radiographs in the interpretation of knee MR images requested by pediatric sports medicine and orthopedic subspecialists.Knee MRI examinations of 194 pediatric patients (mean age, 14 [SD, 3.1] years; range 4-18 years) performed over a 3-year period were reviewed retrospectively. Patients were separated into groups based on MRI findings: normal, ligamentous injury, osteochondral injury, or both ligamentous and osteochondral injury. Two pediatric radiologists blinded to the MRI findings reviewed the knee radiographs in consensus and categorized the findings into the same groups. Radiographic and MRI findings were compared, and the influence of radiographic findings on MRI interpretation was designated as noncontributory if radiographic findings did not aid MRI interpretation, erroneous for false-negative and false-positive radiographic findings, or helpful if radiographs aided MRI interpretation.Radiographic findings were normal in 166 of 194 cases (86%). Among the 166, MRI findings were normal in 73 (44%) cases and abnormal in 93 (56%). Twenty-five of 28 patients (89%) with abnormal radiographic findings had abnormal MRI findings. Radiographs were deemed helpful in 14 of the 25 cases (56%) and noncontributory in 11 (44%). Overall, radiographs were helpful in 14 of 194 cases (7%), noncontributory in 84 (43%), and erroneous in 96 (50%).In the interpretation of knee MRI studies requested by pediatric sports medicine and orthopedic subspecialists for knee pain, radiographs provide limited marginal value. Reliable clinical predictors are needed to identify which subset of pediatric patients with knee pain referred for MRI will benefit from the acquisition of knee radiographs.