Search

Background and purpose: Trauma to the knee is one of the most common injuries in people, especially young people, and delay in the diagnosis of knee fractures and soft tissue injuries in the knee causes limitation of movement, instability, and constant knee pain. In this research can show the correlation between the initial symptoms of the patients and the need for further procedures. To be able to identify traumatic knee injuries that are not clear in the simple knee radiography and to evaluate the findings of the patients for further procedure. Materials and methods: This research is an observational study in which all patients who presented with knee trauma during the course of the study were included in the study. All the information of these patients in a form including age, age group and sex, admission and discharge information such as visit date, discharge date, duration of hospitalization, mechanism of trauma, underlying disease, knee pain, limitation of range of motion, hemarthrosis, associate injury, skin abrasion, Inability to walk, history of knee trauma, radiography findings, knee CT findings, MRI findings, arthroscopy findings, Lysholm and Tegner knee score, probable diagnosis in the emergency room, type of treatment the emergency room, duration of hospitalization in the emergency room, discharge from the emergency room, in The hospitalization form of the performed procedures, the time of hospitalization in the ward and the definitive diagnosis were collected, and then 4 weeks after discharge, they were followed up by phone call with referral to the orthopedic clinic, and other diagnostic and therapeutic measures were reviewed in these patients. The information was provided by the project manager without interfering in the patient care process. Quantitative data were expressed as mean and standard deviation and qualitative data were expressed as frequency and percentage. Independent student t-tests were used to evaluate quantitative variables in two groups, and the Chi-Square test and Fisher's exact test were used to evaluate qualitative variables. Results: During the study period, 177 people were studied. The average age of the patients was 24.21±13.08, of which 138 (76.7%) were men. Most of the injury was caused by traffic accidents. The initial diagnosis in the emergency department had a significant relationship with the definite diagnosis. A statistically significant relationship was seen between MRI findings with knee movement limitation and non-weight bearing. There was a statistically significant relationship between the existence of definitive injury in the knee, limitation of knee movement, lacerations and scratches on the knee, and non-weight bearing. The mechanism of knee injury and laceration, the inability to weight bearing, and the positive findings of X-ray and MRI in the patients who underwent invasive procedures were significantly different from those who received conservative treatment. Conclusion: Injury mechanisms in patients and clinical symptoms such as knee range of motion limitation and non-weigh bearing and abrasion or laceration of the skin on the knee, despite the lack of findings in the initial investigations in the emergency department, is a high chance of injury to the knee joint and they need further evaluation and follow-up.

Background and purpose: Trauma to the knee is one of the most common injuries in people, especially young people, and delay in the diagnosis of knee fractures and soft tissue injuries in the knee causes limitation of movement, instability, and constant knee pain. In this research can show the correlation between the initial symptoms of the patients and the need for further procedures. To be able to identify traumatic knee injuries that are not clear in the simple knee radiography and to evaluate the findings of the patients for further procedure. Materials and methods: This research is an observational study in which all patients who presented with knee trauma during the course of the study were included in the study. All the information of these patients in a form including age, age group and sex, admission and discharge information such as visit date, discharge date, duration of hospitalization, mechanism of trauma, underlying disease, knee pain, limitation of range of motion, hemarthrosis, associate injury, skin abrasion, Inability to walk, history of knee trauma, radiography findings, knee CT findings, MRI findings, arthroscopy findings, Lysholm and Tegner knee score, probable diagnosis in the emergency room, type of treatment the emergency room, duration of hospitalization in the emergency room, discharge from the emergency room, in The hospitalization form of the performed procedures, the time of hospitalization in the ward and the definitive diagnosis were collected, and then 4 weeks after discharge, they were followed up by phone call with referral to the orthopedic clinic, and other diagnostic and therapeutic measures were reviewed in these patients. The information was provided by the project manager without interfering in the patient care process. Quantitative data were expressed as mean and standard deviation and qualitative data were expressed as frequency and percentage. Independent student t-tests were used to evaluate quantitative variables in two groups, and the Chi-Square test and Fisher's exact test were used to evaluate qualitative variables. Results: During the study period, 177 people were studied. The average age of the patients was 24.21±13.08, of which 138 (76.7%) were men. Most of the injury was caused by traffic accidents. The initial diagnosis in the emergency department had a significant relationship with the definite diagnosis. A statistically significant relationship was seen between MRI findings with knee movement limitation and non-weight bearing. There was a statistically significant relationship between the existence of definitive injury in the knee, limitation of knee movement, lacerations and scratches on the knee, and non-weight bearing. The mechanism of knee injury and laceration, the inability to weight bearing, and the positive findings of X-ray and MRI in the patients who underwent invasive procedures were significantly different from those who received conservative treatment. Conclusion: Injury mechanisms in patients and clinical symptoms such as knee range of motion limitation and non-weigh bearing and abrasion or laceration of the skin on the knee, despite the lack of findings in the initial investigations in the emergency department, is a high chance of injury to the knee joint and they need further evaluation and follow-up. [ABSTRACT FROM AUTHOR]

Objective: Chondromalacia patella (CP) describes the softening of the patellar cartilage, and magnetic resonance imaging (MRI) is more useful in diagnosis than other imaging methods. The aim of study is to determine the frequency of other knee MRI fndings and their relationship with chondromalacia stages in patients evaluated for reasons other than trauma and found to have patellar chondromalacia. Methods: This retrospective study included patients who underwent knee MRI examination in the radiology departments of Cukurova University Faculty of Medicine and Health Sciences University Adana Faculty of Medicine for reasons other than trauma between January 2016 and January 2022. Magnetic resonance imaging was used to evaluate the presence and stage of CP, and the outerbridge system was used for staging. As additional fndings, the presence of osteoarthritis, cruciate ligament, meniscus, collateral ligament, and patellar tendon pathologies were evaluated. Results: A total of 278 patients, 168 women and 110 men, with an average age of 59.4 ± 9.8 years, were included in our study. Forty-six patients had stage 1, 64 had stage 2, 66 had stage 3, and 102 had stage 4 CP. A statistically signifcant correlation was found between increasing chondromalacia stage and the presence and stage of osteoarthritis (P < .001), the incidence of anterior cruciate ligament pathology (P < .001), the incidence of tears of the medial meniscus (anterior horn P < .002, posterior horn P < .039), and advanced age (P < .001). Conclusion: It has been determined that there is a relationship between the stage of CP and some additional knee pathologies and advanced age. [ABSTRACT FROM AUTHOR]

Manual anatomical landmarking for morphometric knee bone characterization in orthopedics is highly time-consuming and shows high operator variability. Therefore, automation could be a substantial improvement for diagnostics and personalized treatments relying on landmark-based methods. Applications include implant sizing and planning, meniscal allograft sizing, and morphological risk factor assessment. For twenty MRI-based 3D bone and cartilage models, anatomical landmarks were manually applied by three experts, and morphometric measurements for 3D characterization of the distal femur and proximal tibia were calculated from all observations. One expert performed the landmark annotations three times. Intra- and inter-observer variations were assessed for landmark position and measurements. The mean of the three expert annotations served as the ground truth. Next, automated landmark annotation was performed by elastic deformation of a template shape, followed by landmark optimization at extreme positions (highest/lowest/most medial/lateral point). The results of our automated annotation method were compared with ground truth, and percentages of landmarks and measurements adhering to different tolerances were calculated. Reliability was evaluated by the intraclass correlation coefficient (ICC). For the manual annotations, the inter-observer absolute difference was 1.53 ± 1.22 mm (mean ± SD) for the landmark positions and 0.56 ± 0.55 mm (mean ± SD) for the morphometric measurements. Automated versus manual landmark extraction differed by an average of 2.05 mm. The automated measurements demonstrated an absolute difference of 0.78 ± 0.60 mm (mean ± SD) from their manual counterparts. Overall, 92% of the automated landmarks were within 4 mm of the expert mean position, and 95% of all morphometric measurements were within 2 mm of the expert mean measurements. The ICC (manual versus automated) for automated morphometric measurements was between 0.926 and 1. Manual annotations required on average 18 min of operator interaction time, while automated annotations only needed 7 min of operator-independent computing time. Considering the time consumption and variability among observers, there is a clear need for a more efficient, standardized, and operator-independent algorithm. Our automated method demonstrated excellent accuracy and reliability for landmark positioning and morphometric measurements. Above all, this automated method will lead to a faster, scalable, and operator-independent morphometric analysis of the knee. [ABSTRACT FROM AUTHOR]

Objective: Peripatellar fat pads are extrasynovial intracapsular fat tissues. Suprapatellar, perifemoral, and infrapatellar (Hoffa fat pad) fat pads are included in the peripatellar fat pad. This study aimed to describe the magnetic resonance imaging (MRI) signs of suprapatellar fat pad impingement syndrome, describe their prevalence and pattern, and look into the relationship between their MRI and clinical signs. Methods: Two radiologists retrospectively analyzed 5,700 patients’ knee MRI data between December 2010 and December 2015. We documented the MRI findings that were associated with suprapatellar fad pad impingement syndrome. The correlations between age, osteoarthritis, chondromalacia, and the patellofemoral joint were evaluated using Pearson’s correlations. Results: In our study group, the prevalence of suprapatellar fat pad impingement was 5.3%. Of the patients 52% were men and 48% were women. Patients who were admitted to the clinic complained of non-specific pain in 80.3% of patients. Twenty-seven patients (8.9%) presented with isolated suprapatellar impingement syndrome; 185 (60.9%) showed an increase in intra-articular fluid; 4 (1.3%) had synovitis findings; 17 (5.6%) had medial collateral ligament tears; 107 (35.2%) had quadriceps femoris tendinitis; 8 (2.6%) had patellar tendinitis; 80 (26.3%) had a medial meniscus tear; 23 (7.6%) had Baker’s cyst; and 30 (9.9%) had soft-tissue edema. Medial meniscus degeneration was observed in 51 (16.8%) patients, Hoffa edema was observed in 31 (10.2%) patients, and anterior cruciate ligament tears in 3 (1%) patients. There were positive correlations between age and osteoarthritis (r=0.4660, p

Copyright of Bezmialem Science is the property of Galenos Yayinevi Tic. LTD. STI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Manual anatomical landmarking for morphometric knee bone characterization in orthopedics is highly time-consuming and shows high operator variability. Therefore, automation could be a substantial improvement for diagnostics and personalized treatments relying on landmark-based methods. Applications include implant sizing and planning, meniscal allograft sizing, and morphological risk factor assessment. For twenty MRI-based 3D bone and cartilage models, anatomical landmarks were manually applied by three experts, and morphometric measurements for 3D characterization of the distal femur and proximal tibia were calculated from all observations. One expert performed the landmark annotations three times. Intra- and inter-observer variations were assessed for landmark position and measurements. The mean of the three expert annotations served as the ground truth. Next, automated landmark annotation was performed by elastic deformation of a template shape, followed by landmark optimization at extreme positions (highest/lowest/most medial/lateral point). The results of our automated annotation method were compared with ground truth, and percentages of landmarks and measurements adhering to different tolerances were calculated. Reliability was evaluated by the intraclass correlation coefficient (ICC). For the manual annotations, the inter-observer absolute difference was 1.53 ± 1.22 mm (mean ± SD) for the landmark positions and 0.56 ± 0.55 mm (mean ± SD) for the morphometric measurements. Automated versus manual landmark extraction differed by an average of 2.05 mm. The automated measurements demonstrated an absolute difference of 0.78 ± 0.60 mm (mean ± SD) from their manual counterparts. Overall, 92% of the automated landmarks were within 4 mm of the expert mean position, and 95% of all morphometric measurements were within 2 mm of the expert mean measurements. The ICC (manual versus automated) for automated morphometric measurements was between 0.926 and 1. Manual annotations required on average 18 min of operator interaction time, while automated annotations only needed 7 min of operator-independent computing time. Considering the time consumption and variability among observers, there is a clear need for a more efficient, standardized, and operator-independent algorithm. Our automated method demonstrated excellent accuracy and reliability for landmark positioning and morphometric measurements. Above all, this automated method will lead to a faster, scalable, and operator-independent morphometric analysis of the knee.

He Sui,1,&ast; Jin Li,2,3,&ast; Lin Liu,1 Zhongwen Lv,1 Yunfei Zhang,4 Yongming Dai,4 Zhanhao Mo1 1China-Japan Union Hospital of Jilin University, Changchun, People’s Republic of China; 2Jilin Province People’s Hospital, Changchun, People’s Republic of China; 3The Department of Trauma Surgery, Shanghai Oriental Hospital, Shanghai, People’s Republic of China; 4Central Research Institute, United Imaging Healthcare, Shanghai, 201800, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Zhanhao Mo, China-Japan Union Hospital of Jilin University, No. 126 Xiantai Street, Erdao District, Changchun, People’s Republic of China, Email mozhanhao@jlu.edu.cnPurpose: The three-dimensional (3D) sequence of magnetic resonance imaging (MRI) plays a critical role in the imaging of musculoskeletal joints; however, its long acquisition time limits its clinical application. In such conditions, compressed sensing (CS) is introduced to accelerate MRI in clinical practice. We aimed to investigate the feasibility of an isotropic 3D variable-flip-angle fast spin echo (FSE) sequence with CS technique (CS-MATRIX) compared to conventional 2D sequences in knee imaging.Methods: Images from different sequences of both the accelerated CS-MATRIX and the corresponding conventional acquisitions were prospectively analyzed and compared. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the structures within the knees were measured for quantitative analysis. The subjective image quality and diagnostic agreement were compared between CS-MATRIX and conventional 2D sequences. Quantitative and subjective image quality scores were statistically analyzed with the paired t-test and Wilcoxon signed-rank test, respectively. Diagnostic agreements of knee substructure were assessed using Cohen’s weighted kappa statistic.Results: For quantitative analysis, images from the CS-MATRIX sequence showed a significantly higher SNR than T2-fs 2D sequences for visualizing cartilage, menisci, and ligaments, as well as a higher SNR than proton density (pd) 2D sequences for visualizing menisci and ligaments. There was no significant difference between CS-MATRIX and 2D T2-fs sequences in subjective image quality assessment. The diagnostic agreement was rated as moderate to very good between CS-MATRIX and 2D sequences.Conclusion: This study demonstrates the feasibility and clinical potential of the CS-MATRIX sequence technique for detecting knee lesions The CS-MATRIX sequence allows for faster knee imaging than conventional 2D sequences, yielding similar image quality to 2D sequences.Keywords: knee MRI, compressed sensing, 3D variable-flip-angle fast spin echo

This paper focuses on different types of backbone networks for machine learning architectures which perform classification of knee Magnetic Resonance Imaging (MRI) images. This paper aims to compare different types of feature extraction networks for the same classification task, in terms of accuracy and performance. Multiple variations of machine learning models were trained based on the MRNet architecture, choosing AlexNet, ResNet, VGG-11, VGG-16, and Efficientnet as the backbone. The models were evaluated on the MRNet validation dataset, computing Area Under the Receiver Operating Characteristics Curve (ROC-AUC), accuracy, f1 score, and Cohen's Kappa as evaluation metrics. The MRNet-VGG16 model variant shows the best results for Anterior Cruciate Ligament (ACL) tear detection. For general abnormality detection, MRNet-VGG16 is dominated by MRNet-Resnet in confidence between 0.5 and 0.75 and by MRNet-VGG11 for confidence more than 0.8. Due to the non-uniform nature of backbone network performance on different MRI planes, it is advisable to use an LR ensemble of: VGG16 on a coronal plane for all classification tasks; on an axial plane for abnormality and ACL tear detection; Alexnet on a sagittal plane for abnormality detection, and an axial plane for meniscal tear detection; and VGG11 on a sagittal plane for ACL tear detection. The results also indicate that the Cohen's Kappa metric is valuable in model evaluation for the MRNet dataset, as it provides deeper insights on classification decisions. [ABSTRACT FROM AUTHOR]

Background and Aim Meniscal tears are one of the most frequent disorders affecting the knee joint in athletes and normal people. MRI the first choice of imaging of knee joint but in recent days, ultrasound (US) has made strides in imaging of musculoskeletal disorders due to improvement of imaging qualities. This study aimed to investigate the role of US in diagnosis of meniscus tears as compared to MRI. Patients and Methods A total of 100 patients examined by high definition US and under go to MRI examination of the knee joint. Results Regarding the diagnostic performance of US compared to MRI, the sensitivity reached (89.1%), specificity (∼72.2%), positive predictive value (∼90.1%), negative predictive value (70.1%), and accuracy (84.7%). Conclusion Ultrasonography may be used as a screening tool before arthroscopy in selected cases where MRI was a contraindication or is not available or if the patient was not affording. Ultrasonography showed a dynamic image of the meniscus and thus may prove useful if studied in conjunction with correct clinical examination.

Aim: This study has the primary objective of studying the effect of Wharton jelly mesenchymal stem cells (WJMSCs) in the treatment of knee osteoarthritis. As a secondary end point, we report on the efficacy of such therapy. Patients and methods: 16 patients with advanced Kellgren stage were treated using two doses of expanded WJMSCs given 1 month apart. Patients were followed for 48 months using the Knee Injury and Osteoarthritis Outcome Score (KOOS) and 12 months using magnetic resonance imaging (MRI). Results: Treatment was well tolerated. One patient developed moderate effusion and one superficial phlebitis. We observed functional and pain improvement at 12 and 48 months (p < 0.0001), with statistically significant improvement on MRI scans at 12 months in cartilage loss, osteophytes, bone marrow lesions, effusion and synovitis (p < 0.01), and highly significant improvement in subchondral sclerosis (p < 0.0001). Conclusion: WJMSCs are safe and potentially effective in producing significant improvement in KOOS and MRI scores when administered intra-articularly in knee osteoarthritis cases under ultrasound guidance. [ABSTRACT FROM AUTHOR]

Rationale and Objectives: Train and apply natural language processing (NLP) algorithms for automated radiology-arthroscopy correlation of meniscal tears.Materials and Methods: In this retrospective single-institution study, we trained supervised machine learning models (logistic regression, support vector machine, and random forest) to detect medial or lateral meniscus tears on free-text MRI reports. We trained and evaluated model performances with cross-validation using 3593 manually annotated knee MRI reports. To assess radiology-arthroscopy correlation, we then randomly partitioned this dataset 80:20 for training and testing, where 108 test set MRIs were followed by knee arthroscopy within 1 year. These free-text arthroscopy reports were also manually annotated. The NLP algorithms trained on the knee MRI training dataset were then evaluated on the MRI and arthroscopy report test datasets. We assessed radiology-arthroscopy agreement using the ensembled NLP-extracted findings versus manually annotated findings.Results: The NLP models showed high cross-validation performance for meniscal tear detection on knee MRI reports (medial meniscus F1 scores 0.93-0.94, lateral meniscus F1 scores 0.86-0.88). When these algorithms were evaluated on arthroscopy reports, despite never training on arthroscopy reports, performance was similar, though higher with model ensembling (medial meniscus F1 score 0.97, lateral meniscus F1 score 0.99). However, ensembling did not improve performance on knee MRI reports. In the radiology-arthroscopy test set, the ensembled NLP models were able to detect mismatches between MRI and arthroscopy reports with sensitivity 79% and specificity 87%.Conclusion: Radiology-arthroscopy correlation can be automated for knee meniscal tears using NLP algorithms, which shows promise for education and quality improvement. [ABSTRACT FROM AUTHOR]

Abstract Background This work was conducted to assess the diagnostic efficiency of isotropic three-dimensional VISTA-fast spin echo versus standard two-dimensional fast spin echo at 1.5 T MRI, in the assessment of internal knee derangement in symptomatic patients, aiming to obtain similar diagnostic accuracy in a shorter time span, with reduction of partial volume artifacts by thin continuous sections. Results This was a non-randomized control study including 39 patients (32 male and 7 females, mean age 37 years old). A correlative study was done utilizing MRI standard 2D FSE (protocol A) versus 3D-VISTA-FSE (protocol B) for medial meniscus (MM) and lateral meniscus (LM), as well as anterior cruciate ligament ACL lesions, comparing the MRI results with the findings of arthroscopy as the gold standard. Both protocols depicted medial meniscus lesions with accuracy, specificity, and sensitivity (97.44%, 96.30%, and 100% respectively), lateral meniscus lesions with accuracy, specificity, and sensitivity (97.44%, 100%, and 50% respectively), and ACL lesions with accuracy, specificity, and sensitivity (100%, 100%, and 100% respectively), while there were no PCL lesions depicted through the study population. Comparing the time factor between both protocols revealed protocol A to consume 13.7 min, while protocol B consumed 6.6 min. Conclusion Three-dimensional isotropic VISTA-FSE sequence, although having similar accuracy in diagnosing cruciate and meniscal lesions as the standard sequences, facilitates thin-section data acquisition and multi-planar image reformation in standard and non-standard planes, without intersection gaps that are crucial for the detection and dissection of compound structures; also, it allows a shorter time span, which is more advantageous for patients, particularly the traumatized and emergency patients.

Introduction: A meniscal tear is the most common injury to the knee, and commonly occurring from both athletic events and activities of daily living. The diagnosis of a meniscal tear may require Magnetic Resonance Imaging (MRI), which is costly. In remote and rural parts of our country, MRI is not available so ultrasonographic examination of knee can be used as diagnostic tool to overcome financial burden to such population groups. Aim: To correlate the accuracy of Ultrasonography (USG) and MRI for diagnosing meniscal tears and also to correlate the specificity, sensitivity, and predictive values of USG for meniscal tears in comparison with MRI. Materials and Methods: It was an observational study. It included 50 patients who presented to our institute with complain of acute or chronic knee pain and restriction of movement with clinical signs and symptoms of meniscal tear with history of trauma. All patients underwent ultrasonographic examination of knee along with MRI and arthroscopy. The statistical analysis was done by using Statistical Package for Social Sciences (SPSS) 22.0 software. Accuracy, sensitivity, specificity, Positive Predictive Value (PPV) and Negative Predictive Value (NPV) were calculated based on detection of meniscal tear. Results: This study comprised of 50 patients: 45 were males and 5 were females whose median age was 29 years. Upon combining both medial and lateral menisci, USG showed mean accuracy of 72%, mean sensitivity of 48.6% and mean specificity of 85.7%. MRI showed mean accuracy of 76%, mean sensitivity of 50% and the mean specificity of 90.6%. Conclusion: According to this study, USG has shown reasonable accuracy, sensitivity, specificity, PPV and NPV in comparison to MRI in detecting meniscal lesions.This study has proved that USG can be a good negative test for meniscal tear as we can exclude normal meniscus from abnormal, thus patient with normal meniscus could be prevented from undergoing costly MRI as their initial investigation. So, it can be used as an effective diagnostic screening tool.

Background One of the important factors affecting the biomechanics of the knee joint is the posterior tibial slope which is the tibial plateau's anatomical inclination toward the posterior of the sagittal plane. This inclination, which affects anterior-posterior stability, is important for the kinematics of the knee joint. Changes in the tibial slope may cause a deficit in the stability and function of the knee joint. We aimed to examine the inclination of the posterior horn of the meniscus and posterior tibial slope in healthy individuals and investigate the effect of body mass index on these measurements. Methodology A total of 34 magnetic resonance images and lateral knee radiographs were evaluated in this study. The study included individuals aged 15 to 78 without a history of previous injury or surgery of their knee. Results In the measurements made on magnetic resonance images, a statistically significant difference was found between 25% lateral meniscus slope (mean ± SD = 28.08 ± 1.88) and 25% medial meniscus slope (mean ± SD = 27.31 ± 1.41) (p = 0.05). At the same time, a statistically significant difference (p = 0.011) was found between 25% medial combined slope (mean ± SD = 29.05 ± 3.80) and 25% lateral combined slope (mean ± SD = 30.62 ± 2.99). There was no statistically significant difference between tibial and meniscus slopes, body mass index, gender, and age. Conclusions Our study results have shown that the 25% lateral meniscus and combined slopes are greater than the 25% medial meniscus slope., Competing Interests: Human subjects: Consent for treatment and open access publication was obtained or waived by all participants in this study. Near East University Scientific Research Ethics Board issued approval YDU/2021-901314. Animal subjects: All authors have confirmed that this study did not involve animal subjects or tissue. Conflicts of interest: In compliance with the ICMJE uniform disclosure form, all authors declare the following: Payment/services info: All authors have declared that no financial support was received from any organization for the submitted work. Financial relationships: All authors have declared that they have no financial relationships at present or within the previous three years with any organizations that might have an interest in the submitted work. Other relationships: All authors have declared that there are no other relationships or activities that could appear to have influenced the submitted work., (Copyright © 2024, Yilmaz et al.)

This paper focuses on different types of backbone networks for machine learning architectures which perform classification of knee Magnetic Resonance Imaging (MRI) images. This paper aims to compare different types of feature extraction networks for the same classification task, in terms of accuracy and performance. Multiple variations of machine learning models were trained based on the MRNet architecture, choosing AlexNet, ResNet, VGG-11, VGG-16, and Efficientnet as the backbone. The models were evaluated on the MRNet validation dataset, computing Area Under the Receiver Operating Characteristics Curve (ROC-AUC), accuracy, f1 score, and Cohen’s Kappa as evaluation metrics. The MRNet-VGG16 model variant shows the best results for Anterior Cruciate Ligament (ACL) tear detection. For general abnormality detection, MRNet-VGG16 is dominated by MRNet-Resnet in confidence between 0.5 and 0.75 and by MRNet-VGG11 for confidence more than 0.8. Due to the non-uniform nature of backbone network performance on different MRI planes, it is advisable to use an LR ensemble of: VGG16 on a coronal plane for all classification tasks; on an axial plane for abnormality and ACL tear detection; Alexnet on a sagittal plane for abnormality detection, and an axial plane for meniscal tear detection; and VGG11 on a sagittal plane for ACL tear detection. The results also indicate that the Cohen’s Kappa metric is valuable in model evaluation for the MRNet dataset, as it provides deeper insights on classification decisions.

PurposeStandard knee MRI is performed under unloading (ULC) conditions and not much is known about changes of the meniscus, ligaments or cartilage under loading conditions (LC). The aim is to study the influence of loading of different knee structures at 3Tesla (T) in subjects with osteoarthritis (OA) and normal controls.Materials and methods30 subjects, 10 healthy and 20 with radiographic evidence of OA (10 mild and 10 moderate) underwent 3T MRI under ULC and LC at 50% body weight. All images were analyzed by two musculoskeletal radiologists identifying and grading cartilage, meniscal, ligamentous abnormalities. The changes between ULC and LC were assessed. For meniscus, cartilage and ligaments the changes of lesions, signal and shape were evaluated. In addition, for the meniscus changes in extrusion were examined. A multivariate regression model was used for correlations to correct the data for the impact of age, gender, BMI. A paired T-Test was performed to calculate the differences in meniscus extrusion.ResultsSubjects with degenerative knee abnormalities demonstrated significantly increased meniscus extrusion under LC when compared to normal subjects (p=0.0008-0.0027). Subjects with knee abnormalities and higher KL scores showed significantly more changes in lesion, signal and shape of the meniscus (80% (16/20) vs. 20% (2/10); p=0.0025), ligaments and cartilage during LC.ConclusionThe study demonstrates that axial loading has an effect on articular cartilage, ligament, and meniscus morphology, which is more significant in subjects with degenerative disease and may serve as an additional diagnostic tool for disease diagnosis and assessing progression in subjects with knee OA.

Background Simultaneous injury of two or more knee ligaments with concurrent tears involving the anterior cruciate and medial collateral ligaments is considered to be associated with femorotibial knee dislocations (KD). The purpose of this study is to characterize multiligamentous knee injury patterns associated with dislocations on MRI and to describe the incidence of their sequelae such as tibial plateau fractures, peroneal nerve injuries, and posterolateral corner (PLC) injuries. Participants and methods After obtaining institutional ethical committee approval, we retrospectively identified 108 multiligamentous knee injuries in 100 patients who met with trauma and were treated at our tertiary care center between April 2014 and December 2018. Descriptive statistics were reported using numbers and percentages for categorical variables in cases of multiligamentous injuries, ipsilateral tibial plateau fractures, ipsilateral femoral fractures, peroneal nerve injury, arterial injury, compartment syndrome, and PLC injuries. Results The most common (39.8%) injury pattern was a combined disruption of the anterior cruciate ligament, posterior cruciate ligament, and PLC. Schenck KD III-M was the most common injury type in KD, constituting 16.7%. Medial-sided injuries were the most common injury patterns seen with KD. There was a significant risk of peroneal nerve injury with lateral-sided injuries. Conclusion KD, though rare, may have devastating clinical sequelae such as compartment syndrome if not recognized and treated. Therefore, it is necessary to recognize imaging findings of femorotibial joint dislocations and associated injuries to the adjacent neurovascular bundles.

Background: This work was conducted to assess the diagnostic efficiency of isotropic three-dimensional VISTA-fast spin echo versus standard two-dimensional fast spin echo at 1.5 T MRI, in the assessment of internal knee derangement in symptomatic patients, aiming to obtain similar diagnostic accuracy in a shorter time span, with reduction of partial volume artifacts by thin continuous sections. Results: This was a non-randomized control study including 39 patients (32 male and 7 females, mean age 37 years old). A correlative study was done utilizing MRI standard 2D FSE (protocol A) versus 3D-VISTA-FSE (protocol B) for medial meniscus (MM) and lateral meniscus (LM), as well as anterior cruciate ligament ACL lesions, comparing the MRI results with the findings of arthroscopy as the gold standard. Both protocols depicted medial meniscus lesions with accuracy, specificity, and sensitivity (97.44%, 96.30%, and 100% respectively), lateral meniscus lesions with accuracy, specificity, and sensitivity (97.44%, 100%, and 50% respectively), and ACL lesions with accuracy, specificity, and sensitivity (100%, 100%, and 100% respectively), while there were no PCL lesions depicted through the study population. Comparing the time factor between both protocols revealed protocol A to consume 13.7 min, while protocol B consumed 6.6 min. Conclusion: Three-dimensional isotropic VISTA-FSE sequence, although having similar accuracy in diagnosing cruciate and meniscal lesions as the standard sequences, facilitates thin-section data acquisition and multi-planar image reformation in standard and non-standard planes, without intersection gaps that are crucial for the detection and dissection of compound structures; also, it allows a shorter time span, which is more advantageous for patients, particularly the traumatized and emergency patients. [ABSTRACT FROM AUTHOR]

Abstract Background Majority of musculoskeletal cross-sectional imaging requests have a non-revealing and non-specific clinical history of pain. However, the location of pain is very relevant towards arriving at a specific orthopedic diagnosis. The purpose of this research was to study the impact of skin marker placement and training of technologists prior to knee MRI in detection of clinically important findings. Methods Total 200 consecutive left knee MRIs were evaluated before and after technologist training with regards to marker placement at the site of clinical symptoms or palpable finding. Marker location in relation to the knee was recorded and important findings were classified as correlated important finding, non-correlated important finding, other compartment important finding in non-correlated cases, and diffuse abnormality, i.e. tri-compartmental cartilage defects in both correlated and non-correlated cases. Differences among scans before and after technologist training were analyzed. Results The marker placement was observed in higher proportion of patients in post-training scans (78% vs 60%, p = 0.00). The most common location of the marker was in anterior or anterolateral knee (32% and 34% cases, respectively). The marker-important finding correlation was also higher post training, but not statistically significant (53% versus 38%, p = 0.57). Important findings correlated with the marker in more than 50% of the scans in the post-training set. Conclusion Marker placement can aid in detection of clinically important imaging finding and technologist training aids in increased rates of marker placement and improved correlation.

Background Over time, there has been a noticeable increase in anterior cruciate ligament (ACL) injuries. The current imperative is to anticipate predisposing factors and proactively prevent ACL injuries. The occurrence of ACL injuries has been linked to diverse factors associated with the morphology of the distal femur. Objectives Through this study, we aim to compare the anatomic variables of distal femur morphology such as notch width (NW), bicondylar width (BW), notch entrance width (NEW), and notch width index (NWI) between patients with ACL injuries and non-injured patients using MRI. We also aim to make a comparison of these factors between male and female genders to assess the gender variability. Material and methods A retrospective case-control study was conducted amongst patients who underwent MRI Knee scan for clinical suspicion of internal derangement during the study period. We selected the first 125 individuals who were found to have ACL injury in the MRI scans and selected another 125 individuals who had an intact ACL in the scans, to serve as controls in the study. Demographic information was retrieved from the hospital's electronic records, and the assessment of NW, NWI, BW, and NEW was conducted through a review of MRI sequences. They were then compared between the cases and control groups, as well as between male and female genders. Results The ACL-injured group exhibited statistically significant reductions in NW and NWI. While 17.39 mm was the mean NW among cases, 17.86 was the mean value among controls. Similarly, the mean NWI was 0.25 among patients with ACL injuries and 0.27 among controls. Gender-based comparisons also revealed statistically significant differences in NW and NWI measurements, where females were reported to have comparatively lower measurements. The mean NW for males and females in the injured group were 18.26 mm and 15.40 mm, respectively, while it was 18.71 mm and 16.90 mm, respectively, in the control group. In the case of NEW, males in the injured group had a slightly higher value (21.33 mm) than the controls (20.65). Females on the other hand exhibited a lower mean value of NEW in ACL-injured group (18.51 mm) in comparison to the non-injured (18.79 mm). BW did not seem to show a significant difference between the two groups. Conclusions In the studied population, ACL injuries demonstrated a higher occurrence in individuals with a narrow femoral intercondylar NWI. If any of these characteristics are identified in an MRI, it may be helpful to identify individuals who are at a higher risk of developing ACL injuries and may thereby help in planning preventative strategies., Competing Interests: The authors have declared that no competing interests exist., (Copyright © 2024, Maheshwari et al.)

Objective: To assess the accuracy of routine knee MRI in detecting acute popliteal artery and/or common peroneal nerve (CPN) dysfunction following multiligamentous knee injury (MLKI), with correlation of MRI findings to clinical outcome. Materials and methods: Routine MRI knee examinations in 115 MLKI patients (54/115 with acute neurovascular injury, 61/115 without neurovascular injury) were retrospectively reviewed. Cases were classified by injury mechanism and ligamentous injuries sustained. MRI examinations were reviewed by two readers for vascular (arterial flow void, arterial calibre, intimal flap, perivascular hematoma) and CPN (intraneural T2-hyperintensity, calibre, discontinuity, perineural hematoma) injuries. Accuracy of routine knee MRI in the diagnosis of acute neurovascular injury and correlation of MRI findings to clinical outcome were evaluated. Results: Patients included 86/115 males, mean age 33 years. The accuracy of MRI in diagnosis of acute CPN injury was 80.6%, 83.6% (readers 1 and 2): sensitivity (78%, 79.7%), specificity (80%, 86.7%), PPV (78%, 82.5%), and NPV (82.7%, 84.4%). Increased intraneural T2 signal showed a significant correlation to acute CPN dysfunction (p < 0.05). MRI was 75%, 69.8% (readers 1 and 2) accurate in detecting acute vascular injury: sensitivity (73.3%, 86.7%), specificity (75.2%, 67.3%), PPV (30.5%, 36.1%), and NPV (95%, 97.1%). No MRI features of vascular injury showed a statistical correlation with clinical outcome. Neurovascular complications were more common in ultra-low-energy injuries and KD-V3L pattern of ligament disruption. Conclusion: Routine MRI is of limited accuracy in assessing vascular complication, but higher accuracy in assessing CPN injury following MLKI. Increased intraneural T2 signal on conventional knee MR imaging shows statistically significant association with clinically documented acute CPN dysfunction following MLKI. [ABSTRACT FROM AUTHOR]

Abstract Maintaining anterolateral rotational stability of the knee requires a complex set of structures, most notably the anterior cruciate ligament. However, lateral knee structures such as the anterolateral ligament (ALL) also play an important role. There has been controversy over the role the ALL plays in an ACL deficient knee to maintain rotational stability. In this study, we examined ACL deficient knees with and without intact ALLs, for rotatory laxity using a pivot shift examination. This was graded using International Knee Document Committee (IKDC) criteria. MRI was used to view the ALL and its status. We found no statistically significant difference in rotational stability of ACL deficient knees, with or without intact ALLs. We did however find a statistically significant association between injury to the ALL and other concomitant lateral structures such as the lateral collateral ligament, biceps femoris tendon, and iliotibial band. This supports that the ALL works in concert with the other lateral structures in the knee and the ACL, to provide rotational stability. This suggests that as an isolated structure, the ALL's contribution to clinical rotational stability is not significant, even in the presence of an ACL tear. [ABSTRACT FROM AUTHOR]

A fully automated knee magnetic resonance imaging (MRI) segmentation method to study osteoarthritis (OA) was developed using a novel hierarchical set of random forests (RF) classifiers to learn the appearance of cartilage regions and their boundaries. A neighborhood approximation forest is used first to provide contextual feature to the second-level RF classifier that also considers local features and produces location-specific costs for the layered optimal graph image segmentation of multiple objects and surfaces (LOGISMOS) framework. Double-echo steady state MRIs used in this paper originated from the OA Initiative study. Trained on 34 MRIs with varying degrees of OA, the performance of the learning-based method tested on 108 MRIs showed significant reduction in segmentation errors ( p<\textsf 0.05 ) compared with the conventional gradient-based and single-stage RF-learned costs. The 3-D LOGISMOS was extended to longitudinal-3-D (4-D) to simultaneously segment multiple follow-up visits of the same patient. As such, data from all time-points of the temporal sequence contribute information to a single optimal solution that utilizes both spatial 3-D and temporal contexts. 4-D LOGISMOS validation on 108 MRIs from baseline, and 12 month follow-up scans of 54 patients showed significant reduction in segmentation errors ( p<\textsf 0.01 ) compared with 3-D. Finally, the potential of 4-D LOGISMOS was further explored on the same 54 patients using five annual follow-up scans demonstrating a significant improvement of measuring cartilage thickness ( p<\textsf 0.01 ) compared with the sequential 3-D approach. [ABSTRACT FROM PUBLISHER]

Objective: To present a novel method for automated segmentation of knee menisci from MRIs. To evaluate quantitative meniscal biomarkers for osteoarthritis (OA) estimated thereof.Method: A segmentation method employing convolutional neural networks in combination with statistical shape models was developed. Accuracy was evaluated on 88 manual segmentations. Meniscal volume, tibial coverage, and meniscal extrusion were computed and tested for differences between groups of OA, joint space narrowing (JSN), and WOMAC pain. Correlation between computed meniscal extrusion and MRI Osteoarthritis Knee Score (MOAKS) experts' readings was evaluated for 600 subjects. Suitability of biomarkers for predicting incident radiographic OA from baseline to 24 months was tested on a group of 552 patients (184 incident OA, 386 controls) by performing conditional logistic regression.Results: Segmentation accuracy measured as dice similarity coefficient was 83.8% for medial menisci (MM) and 88.9% for lateral menisci (LM) at baseline, and 83.1% and 88.3% at 12-month follow-up. Medial tibial coverage was significantly lower for arthritic cases compared to non-arthritic ones. Medial meniscal extrusion was significantly higher for arthritic knees. A moderate correlation between automatically computed medial meniscal extrusion and experts' readings was found (ρ = 0.44). Mean medial meniscal extrusion was significantly greater for incident OA cases compared to controls (1.16 ± 0.93 mm vs 0.83 ± 0.92 mm; P < 0.05).Conclusion: Especially for medial menisci an excellent segmentation accuracy was achieved. Our meniscal biomarkers were validated by comparison to experts' readings as well as analysis of differences w.r.t groups of OA, JSN, and WOMAC pain. It was confirmed that medial meniscal extrusion is a predictor for incident OA. [ABSTRACT FROM AUTHOR]

The use of Cartesian and Blade techniques also affects image quality. The Cartesian technique is more commonly used in Knee MRI examinations. Cartesian technique is vulnerable to movement, giving rise to motion artifacts. This motion artifact is often caused by too long scanning time, so ETL settings are important. An alternative to reducing this risk is to use the Blade technique and by setting the appropriate ETL. The research objective was to determine the differences image quality and anatomical information and to determine the technique that produced quality images and MRI anatomical information on the sagittal knee section between the Cartesian ETL and Blade T2 Weighted TSE combination. This is experiment research. Samples of 10 volunteers, carried out scanning with Cartesian and Blade techniques with variations ETL 14, 16, 18. Focus of assessment on ACL, PCL, meniscus, fluid, and fat. Image quality includes SNR and CNR. The assessment of the anatomical information by a radiologist. Data analyzed with Anova, Friedman, and Wilcoxon test. The results study showed that overall, there are significant differences in image quality between Cartesian and Blade techniques with p-value 0.005. There are differences in anatomical information with p-value

Purpose: To investigate the accuracy of MRI in assessment of sports related knee injuries. Materials and methods: From August 2012 to March 2013 thirty patients referred for sports related knee pain have been included in this study. Patients were subjected to a dedicated MR knee study and correlated knee arthroscopy and surgery. Results: The study included thirty patients complaining of sports related knee pain, only 5 patients (16.6%) were with normal MRI findings and 25 patients (83.4%) were with abnormal MRI findings. Among the 25 patients who had injuries of their knees, 15 patients (60%) had ACL injuries, 2 patients (8%) had PCL injuries, 10 patients (40%) had meniscal injuries, 8 patients (32%) had collateral ligament injuries, 5 patients (20%) had bone injuries and 2 patients (8%) had muscular injuries. Only 7 patients (28%) were represented with isolated injury and 18 patients (72%) were represented with combined injuries. In correlation with arthroscopies and surgeries, morphological analysis was true-positive in 23 (92%) patients of the 25 injured patients, and true-negative in 3 (60%) patients of the 5 normal patients. Morphological analysis revealed overall 92% sensitivity and 60% specificity. Regarding the 15 patients who had ACL injuries, 13 patients (86.6%) were true-positive and 8 patients (80%) of the 10 patients who had meniscal injuries were true-positive. Conclusion: MRI represents the optimal imaging tool in the evaluation of the sports related knee injuries, which has been shown to be an accurate and non invasive method of diagnosing ligament, meniscal, cartilage and muscular knee injuries.

Background: Majority of musculoskeletal cross-sectional imaging requests have a non-revealing and non-specific clinical history of pain. However, the location of pain is very relevant towards arriving at a specific orthopedic diagnosis. The purpose of this research was to study the impact of skin marker placement and training of technologists prior to knee MRI in detection of clinically important findings.Methods: Total 200 consecutive left knee MRIs were evaluated before and after technologist training with regards to marker placement at the site of clinical symptoms or palpable finding. Marker location in relation to the knee was recorded and important findings were classified as correlated important finding, non-correlated important finding, other compartment important finding in non-correlated cases, and diffuse abnormality, i.e. tri-compartmental cartilage defects in both correlated and non-correlated cases. Differences among scans before and after technologist training were analyzed.Results: The marker placement was observed in higher proportion of patients in post-training scans (78% vs 60%, p = 0.00). The most common location of the marker was in anterior or anterolateral knee (32% and 34% cases, respectively). The marker-important finding correlation was also higher post training, but not statistically significant (53% versus 38%, p = 0.57). Important findings correlated with the marker in more than 50% of the scans in the post-training set.Conclusion: Marker placement can aid in detection of clinically important imaging finding and technologist training aids in increased rates of marker placement and improved correlation. [ABSTRACT FROM AUTHOR]

Purpose: The medial patellofemoral ligament (MPFLL)/lateral patellar retinaculum (LPR) ratio were assessed in knees as a means to detect patellar malalignment. We also aimed to evaluate the prevalence of the various types of trochlear dysplasia in patients with patellar malalignment. Materials and methods: After approval of our institutional ethics committee, we conducted a retrospective study that included 450 consecutive patients to evaluate them for the presence of patellar malalignment. Parameters investigated were the trochlear type, sulcus angle, presence of a supratrochlear spur, MPFLL, LPR, patella alta, and patella baja by means of 1.5T magnetic resonance imaging (MRI). Overall, 133 patients were excluded because of the presence of major trauma, multiple ligament injuries, bipartite patella, and/or previous knee surgery. The Dejour classification was used to assess trochlear dysplasia. Two experienced radiologists (HKY, EEE) evaluated the images. Their concordance was assessed using the kappa (κ) test. Results: The frequencies of patellar malalignment and trochlear dysplasia were 34.7 and 63.7 %, respectively. The frequency of trochlear dysplasia associated with patellar malalignment was 97.2 %. An MPFLL/LPR ratio of 1.033-1.041 had high sensitivity and specificity for malalignment. The researchers' concordance was good (κ = 0.89, SE = 0.034, P < 0.001). Conclusion: Trochlear dysplasia is frequently associated with patellar malalignment. An increased MPFLL/LPR ratio is useful for detecting patellar malalignment on knee MRI, which is a novel quantitative method based on ligament length. [ABSTRACT FROM AUTHOR]