Forensic age estimation by MRI of the knee - comparison of two classifications for ossification stages in a German population.

AIM AND OBJECTIVES: In forensic age estimation e.g. for judicial proceedings surpassed age thresholds can be legally relevant. To examine age related differences in skeletal development the recommendations by the Study Group on Forensic Age Diagnostics (AGFAD) are based on ionizing radiation (among others orthopantomograms, plain x-rays of the hand). Vieth et al. and Ottow et al. proposed MRI-classifications for the epiphyseal-diaphyseal fusion of the knee joint to define different age groups in healthy volunteers. The aim of the present study was to directly compare these two classifications in a large German patient population. MATERIALS AND METHODS: MRI of the knee joint of 900 patients (405 female, 495 male) from 10 to 28 years of age were retrospectively analyzed. Acquired T1-weighted turbo spin-echo sequence (TSE) and T2-weighted sequence with fat suppression by turbo inversion recovery magnitude (TIRM) were analyzed for the two classifications. The different bony fusion stages of the two classifications were determined and the corresponding chronological ages assigned. Differences between the sexes were analyzed. Intra- and inter-observer agreements were determined using Cohen's kappa. RESULTS: With the classification of Ottow et al. it was possible to determine completion of the 18th and 21st year of life in both sexes. With the classification of Vieth et al. completion of the 18th year of life for female patients and the 14th and 21st year of life in both sexes could be determined. The intra- and inter-observer agreement levels were very good (κ > 0.82). CONCLUSION: In the large German patient cohort of this study it was possible to determine the 18th year of life with for both sexes with the classification of Ottow et al. and for female patients with the classification of Vieth et al. It was also possible to determine the 21st year of life for all bones with the classification of Ottow et al. and for the distal femur with the classification of Vieth et al.

Clinical evaluation of 3D high-resolution isotropic knee MRI using Multi-Interleaved X-prepared TSE with inTUitive RElaxometry (MIXTURE) for simultaneous morphology and T2 mapping.

PURPOSE: Quantitative MRI techniques such as T2 mapping are useful in comprehensive evaluation of various pathologies of the knee joint yet require separate scans to conventional morphological measurements and long acquisition times. The recently introduced 3D MIXTURE (Multi-Interleaved X-prepared Turbo-Spin Echo with Intuitive Relaxometry) technique can obtain simultaneous morphologic and quantitative information of the knee joint. To compare MIXTURE with conventional methods and to identify differences in morphological and quantitative information. METHODS: Phantom studies were conducted, and in vivo human scans were performed (20 patients) presented with knee arthralgia. MIXTURE is based on 3D TSE without and with T2 preparation modules in an interleaved manner for both morphology with PDW and fat suppressed T2W imaging as well as quantitative T2 mapping within one single scan. Image quality and lesion depiction were visually assessed and compared between MIXTURE and conventional 2D TSE by two experienced radiologists. Contrast-to-noise ratio was used to assess the adjacent tissue contrast in a quantitative way for both obtained PDW and fat suppressed T2W images. Quantitative T2 values were measured in phantom and from in vivo knee cartilage. RESULTS: The overall diagnostic confidence and contrast-to-noise ratio were deemed comparable between MIXTURE and 2D TSE. While the chosen T2 preparation modules for MIXTURE rendered consistent T2 values comparing to the current standard, measured cartilage T2 values ranged from 26.1 to 50.7 ms, with significant difference between the lesion and normal areas (p < 0.05). CONCLUSIONS: MIXTURE can help to provide high-resolution information for both anatomical and pathological assessment.

Automated Landmark Annotation for Morphometric Analysis of Distal Femur and Proximal Tibia.

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.

Evaluation of large language models performance against humans for summarizing MRI knee radiology reports: A feasibility study.

OBJECTIVES: This study addresses the critical need for accurate summarization in radiology by comparing various Large Language Model (LLM)-based approaches for automatic summary generation. With the increasing volume of patient information, accurately and concisely conveying radiological findings becomes crucial for effective clinical decision-making. Minor inaccuracies in summaries can lead to significant consequences, highlighting the need for reliable automated summarization tools. METHODS: We employed two language models - Text-to-Text Transfer Transformer (T5) and Bidirectional and Auto-Regressive Transformers (BART) - in both fine-tuned and zero-shot learning scenarios and compared them with a Recurrent Neural Network (RNN). Additionally, we conducted a comparative analysis of 100 MRI report summaries, using expert human judgment and criteria such as coherence, relevance, fluency, and consistency, to evaluate the models against the original radiologist summaries. To facilitate this, we compiled a dataset of 15,508 retrospective knee Magnetic Resonance Imaging (MRI) reports from our Radiology Information System (RIS), focusing on the findings section to predict the radiologist's summary. RESULTS: The fine-tuned models outperform the neural network and show superior performance in the zero-shot variant. Specifically, the T5 model achieved a Rouge-L score of 0.638. Based on the radiologist readers' study, the summaries produced by this model were found to be very similar to those produced by a radiologist, with about 70% similarity in fluency and consistency between the T5-generated summaries and the original ones. CONCLUSIONS: Technological advances, especially in NLP and LLM, hold great promise for improving and streamlining the summarization of radiological findings, thus providing valuable assistance to radiologists in their work.

Improving inceptionV4 model based on fractional-order snow leopard optimization algorithm for diagnosing of ACL tears.

In the current research study, a new method is presented to diagnose Anterior Cruciate Ligament (ACL) tears by introducing an optimized version of the InceptionV4 model. Our proposed methodology utilizes a custom-made variant of the Snow Leopard Optimization Algorithm, known as the Fractional-order Snow Leopard Optimization Algorithm (FO-LOA), to extract essential features from knee magnetic resonance imaging (MRI) images. This results in a substantial improvement in the accuracy of ACL tear detection. By effectively extracting critical features from knee MRI images, our proposed methodology significantly enhances diagnostic accuracy, potentially reducing false negatives and false positives. The enhanced model based on FO-LOA underwent thorough testing using the MRNet dataset, demonstrating exceptional performance metrics including an accuracy rate of 98.00%, sensitivity of 98.00%, precision of 97.00%, specificity of 98.00%, F1-score of 98.00%, and Matthews Correlation Coefficient (MCC) of 88.00%. These findings surpass current methodologies like Convolutional Neural Network (CNN), Inception-v3, Deep Belief Networks and Improved Honey Badger Algorithm (DBN/IHBA), integration of the CNN with an Amended Cooking Training-based Optimizer version (CNN/ACTO), Self-Supervised Representation Learning (SSRL), signifying a significant breakthrough in ACL injury diagnosis. Using FO-SLO to optimize the InceptionV4 framework shows promise in improving the accuracy of ACL tear identification, enabling prompt and efficient treatment interventions.

Evaluation of Bony Femoral Morphological Parameters in Anterior Cruciate Ligament Injury Using Magnetic Resonance Imaging: A Retrospective Unmatched Case-Control Study.

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.

Five-minute knee MRI: An AI-based super resolution reconstruction approach for compressed sensing. A validation study on healthy volunteers.

PURPOSE: To investigate the potential of combining Compressed Sensing (CS) and a newly developed AI-based super resolution reconstruction prototype consisting of a series of convolutional neural networks (CNN) for a complete five-minute 2D knee MRI protocol. METHODS: In this prospective study, 20 volunteers were examined using a 3T-MRI-scanner (Ingenia Elition X, Philips). Similar to clinical practice, the protocol consists of a fat-saturated 2D-proton-density-sequence in coronal, sagittal and transversal orientation as well as a sagittal T1-weighted sequence. The sequences were acquired with two different resolutions (standard and low resolution) and the raw data reconstructed with two different reconstruction algorithms: a conventional Compressed SENSE (CS) and a new CNN-based algorithm for denoising and subsequently to interpolate and therewith increase the sharpness of the image (CS-SuperRes). Subjective image quality was evaluated by two blinded radiologists reviewing 8 criteria on a 5-point Likert scale and signal-to-noise ratio calculated as an objective parameter. RESULTS: The protocol reconstructed with CS-SuperRes received higher ratings than the time-equivalent CS reconstructions, statistically significant especially for low resolution acquisitions (e.g., overall image impression: 4.3 ±â€¯0.4 vs. 3.4 ±â€¯0.4, p < 0.05). CS-SuperRes reconstructions for the low resolution acquisition were comparable to traditional CS reconstructions with standard resolution for all parameters, achieving a scan time reduction from 11:01 min to 4:46 min (57 %) for the complete protocol (e.g. overall image impression: 4.3 ±â€¯0.4 vs. 4.0 ±â€¯0.5, p < 0.05). CONCLUSION: The newly-developed AI-based reconstruction algorithm CS-SuperRes allows to reduce scan time by 57% while maintaining unchanged image quality compared to the conventional CS reconstruction.

Influence of leg axis alignment on MRI T2* mapping of the knee in young professional soccer players.

BACKGROUND: Investigation of the association between leg axis alignment and biochemical MRI in young professional soccer players in order to identify a potential influence of the leg axis on cartilage regions at risk. METHODS: Sixteen professional soccer players (21 ± 3 years) underwent static and dynamic leg axis analysis via radiation free DIERS formetric 4 D as well as 3-T MRI examination of both knees. Quantitative T2* mapping of the knee cartilage was performed and T2* values were evaluated as 144 regions of interest. Subgroup analysis was performed in players with severe varus alignment (> 6°). RESULTS: Analysis of the leg axis geometry revealed a mean static alignment of 6.6° ± 2.5 varus and a mean dynamic alignment of 5.1° ± 2.6 varus. Quantitative T2* mapping showed significantly increased T2* values in the superficial cartilage layer compared to the deeper region (p < 0.001) as well as a significant increase in relaxation times in the femoral cartilage from anterior to intermediate to posterior (p < 0.001). Combination of both methods revealed a significant correlation for the degree of varus alignment and the femoral, posterior, deep region of the medial knee compartment (r = 0.4; p = 0.03). If severe varus alignment was present this region showed a significant increase in relaxation time compared to players with a less pronounced leg axis deviation (p = 0.003). CONCLUSION: This study demonstrates that varus alignment in young soccer players is associated with elevated T2* relaxation times in the deep cartilage layer of the medial, posterior, femoral compartment and might therefore be a contributing factor in the early pathogenesis of manifest cartilage lesions. Therefore, these findings should be considered in the development of preventive training programs.

Deep Learning-reconstructed Parallel Accelerated Imaging for Knee MRI

BACKGROUND: Deep learning (DL) can improve image quality by removing noise from accelerated MRI. OBJECTIVE: To compare the quality of various accelerated imaging applications in knee MRI with and without DL. METHOD: We analyzed 44 knee MRI scans from 38 adult patients using the DL-reconstructed parallel acquisition technique (PAT) between May 2021 and April 2022. The participants underwent sagittal fat-saturated T2-weighted turbo-spin-echo accelerated imaging without DL (PAT-2 [2-fold parallel accelerated imaging], PAT-3, and PAT-4) and with DL (DL with PAT-3 [PAT-3DL] and PAT-4 [PAT-4DL]). Two readers independently evaluated subjective image quality (diagnostic confidence of knee joint abnormalities, subjective noise and sharpness, and overall image quality) using a 4-point grading system (1-4, 4=best). Objective image quality was assessed based on noise (noise power) and sharpness (edge rise distance). RESULTS: The mean acquisition times for PAT-2, PAT-3, PAT-4, PAT-3DL, and PAT-4DL sequences were 2:55, 2:04, 1:33, 2:04, and 1:33 min, respectively. Regarding subjective image quality, PAT-3DL and PAT-4DL scored higher than PAT-2. Objectively, DL-reconstructed imaging had significantly lower noise than PAT-3 and PAT-4 (P <0.001), but the results were not significantly different from those for PAT-2 (P >0.988). Objective image sharpness did not differ significantly among the imaging combinations (P =0.470). The inter-reader reliability ranged from good to excellent (κ = 0.761­0.832). CONCLUSION: PAT-4DL imaging in knee MRI exhibits similar subjective image quality, objective noise, and sharpness levels compared with conventional PAT-2 imaging, with an acquisition time reduction of 47%.

Charting Aging Trajectories of Knee Cartilage Thickness for Early Osteoarthritis Risk Prediction: An MRI Study from the Osteoarthritis Initiative Cohort.

Knee osteoarthritis (OA), a prevalent joint disease in the U.S., poses challenges in terms of predicting of its early progression. Although high-resolution knee magnetic resonance imaging (MRI) facilitates more precise OA diagnosis, the heterogeneous and multifactorial aspects of OA pathology remain significant obstacles for prognosis. MRI-based scoring systems, while standardizing OA assessment, are both time-consuming and labor-intensive. Current AI technologies facilitate knee OA risk scoring and progression prediction, but these often focus on the symptomatic phase of OA, bypassing initial-stage OA prediction. Moreover, their reliance on complex algorithms can hinder clinical interpretation. To this end, we make this effort to construct a computationally efficient, easily-interpretable, and state-of-the-art approach aiding in the radiographic OA (rOA) auto-classification and prediction of the incidence and progression, by contrasting an individual's cartilage thickness with a similar demographic in the rOA-free cohort. To better visualize, we have developed the toolset for both prediction and local visualization. A movie demonstrating different subtypes of dynamic changes in local centile scores during rOA progression is available at https://tli3.github.io/KneeOA/. Specifically, we constructed age-BMI-dependent reference charts for knee OA cartilage thickness, based on MRI scans from 957 radiographic OA (rOA)-free individuals from the Osteoarthritis Initiative cohort. Then we extracted local and global centiles by contrasting an individual's cartilage thickness to the rOA-free cohort with a similar age and BMI. Using traditional boosting approaches with our centile-based features, we obtain rOA classification of KLG ≤ 1 versus KLG = 2 (AUC = 0.95, F1 = 0.89), KLG ≤ 1 versus KLG ≥ 2 (AUC = 0.90, F1 = 0.82) and prediction of KLG2 progression (AUC = 0.98, F1 = 0.94), rOA incidence (KLG increasing from < 2 to ≥ 2; AUC = 0.81, F1 = 0.69) and rOA initial transition (KLG from 0 to 1; AUC = 0.64, F1 = 0.65) within a future 48-month period. Such performance in classifying KLG ≥ 2 matches that of deep learning methods in recent literature. Furthermore, its clinical interpretation suggests that cartilage changes, such as thickening in lateral femoral and anterior femoral regions and thinning in lateral tibial regions, may serve as indicators for prediction of rOA incidence and early progression. Meanwhile, cartilage thickening in the posterior medial and posterior lateral femoral regions, coupled with a reduction in the central medial femoral region, may signify initial phases of rOA transition.

Wrisberg variant of the lateral discoid meniscus in children: review of the literature and presentation of case series.

INTRODUCTION: The Wrisberg variant of the discoid lateral meniscus is a very rare disorder and is characterized by the hypermobility and instability of the meniscus caused by the absence of its posterior tibial attachment, with only its meniscofemoral junction (Wrisberg's ligament) maintained, and inserted in the posterior horn of the meniscus. As a result, the posterior horn of the lateral meniscus is mobile; often subluxing into the joint. MATERIALS AND METHODS: A total of eight skeletally immature patients with symptomatic Wrisberg variant of the discoid lateral meniscus were included in this study. Each knee was evaluated with MRI and arthroscopy. We graded unstable discoid menisci according to their discoid morphology (complete vs. incomplete), meniscal intra-substance degeneration, and the presence or absence of meniscal tears. All eight menisci were evaluated as degenerated with no meniscal tears. Five of them were evaluated as complete. Due to the severely degenerated meniscus, we considered it unnecessary to repair the detached posterior tibial ligament, so we performed a reshaping of the discoid meniscus, restoring a C-shape, excising the hypertrophied central part of the meniscus, and creating a posterior horn with a remaining rim of 6-8 mm. For evaluation of the knee function preoperatively and postoperatively we used the online International Knee Documentation Committee (IKDC) system. The purpose of this study is to emphasize the importance of MRI in identifying and revealing the unstable (Wrisberg variant) type of discoid meniscus in children. RESULTS: The mean patient age at the time of surgery was 8.25 ± 2.91 years (range 5-13 years). The average follow-up was 3.75 ± 0.46 years (range 3-4) years. The mean preoperative IKDC score was 22.37 ± 1.50 (range 21-25) points. The mean postoperative IKDC score was 80.50 ± 1.77 (range 79-84) points. CONCLUSIONS: MRI is a valuable tool in the evaluation of the shape, stability, and consistency of symptomatic discoid menisci. It is helpful for the detection of the unstable Wrisberg variant.

A Machine Learning Approach for Knee Injury Detection from Magnetic Resonance Imaging.

The knee is an essential part of our body, and identifying its injuries is crucial since it can significantly affect quality of life. To date, the preferred way of evaluating knee injuries is through magnetic resonance imaging (MRI), which is an effective imaging technique that accurately identifies injuries. The issue with this method is that the high amount of detail that comes with MRIs is challenging to interpret and time consuming for radiologists to analyze. The issue becomes even more concerning when radiologists are required to analyze a significant number of MRIs in a short period. For this purpose, automated tools may become helpful to radiologists assisting them in the evaluation of these images. Machine learning methods, in being able to extract meaningful information from data, such as images or any other type of data, are promising for modeling the complex patterns of knee MRI and relating it to its interpretation. In this study, using a real-life imaging protocol, a machine-learning model based on convolutional neural networks used for detecting medial meniscus tears, bone marrow edema, and general abnormalities on knee MRI exams is presented. Furthermore, the model's effectiveness in terms of accuracy, sensitivity, and specificity is evaluated. Based on this evaluation protocol, the explored models reach a maximum accuracy of 83.7%, a maximum sensitivity of 82.2%, and a maximum specificity of 87.99% for meniscus tears. For bone marrow edema, a maximum accuracy of 81.3%, a maximum sensitivity of 93.3%, and a maximum specificity of 78.6% is reached. Finally, for general abnormalities, the explored models reach 83.7%, 90.0% and 84.2% of maximum accuracy, sensitivity and specificity, respectively.

The value of magnetic resonance imaging in the preoperative diagnosis of tibial plateau fractures: a systematic literature review.

PURPOSE: The outcome of a tibial plateau fracture (TPF) depends on the fracture reduction achieved and the extent of soft-tissue lesions, including lesions in the ligaments, cartilage, and menisci. Sub-optimal treatment can result in poor knee function and osteoarthritis. Preoperative planning is primarily based on conventional X-ray and computed tomography (CT), which are unsuitable for diagnosing soft-tissue lesions. Magnetic resonance imaging (MRI) is not routinely performed. To date, no literature exists that clearly states the indications for preoperative MRI. This systematic review aimed to determine the frequency of soft-tissue lesions in TPFs, the association between fracture type and soft-tissue lesions, and the types of cases for which MRI is indicated. METHODS: A systematic review of the literature was based on articles located in PubMed/MEDLINE and the Cochrane Central Register of Controlled Trials (CENTRAL), supplemented by searching the included articles' reference lists and the ePublication lists of leading orthopedic and trauma journals. RESULTS: A total of 1138 studies were retrieved. Of these, 18 met the eligibility criteria and included a total of 877 patients. The proportion of total soft-tissue lesions was 93.0%. The proportions of soft-tissue lesions were as follows: medial collateral ligament 20.7%, lateral collateral ligament 22.9%, anterior cruciate ligament 36.8%, posterior cruciate ligament 14.8%, lateral meniscus 48.9%, and medial meniscus 24.5%. A weak association was found between increasing frequency of LCL and ACL lesions and an increase in fracture type according to Schatzker's classification. No standard algorithm for MRI scans of TPFs was found. CONCLUSION: At least one ligament or meniscal lesion is present in 93.0% of TPF cases. More studies with higher levels of evidence are needed to find out in which particular cases MRI adds value. However, MRI is recommended, at least in young patients and cases of high-energy trauma.

Denoising of three-dimensional fast spin echo magnetic resonance images of knee joints using spatial-variant noise-relevant residual learning of convolution neural network.

PURPOSE: Two-dimensional (2D) fast spin echo (FSE) techniques play a central role in the clinical magnetic resonance imaging (MRI) of knee joints. Moreover, three-dimensional (3D) FSE provides high-isotropic-resolution magnetic resonance (MR) images of knee joints, but it has a reduced signal-to-noise ratio compared to 2D FSE. Deep-learning denoising methods are a promising approach for denoising MR images, but they are often trained using synthetic noise due to challenges in obtaining true noise distributions for MR images. In this study, inherent true noise information from two number of excitations (2-NEX) acquisition was used to develop a deep-learning model based on residual learning of convolutional neural network (CNN), and this model was used to suppress the noise in 3D FSE MR images of knee joints. METHODS: A deep learning-based denoising method was developed. The proposed CNN used two-step residual learning over parallel transporting and residual blocks and was designed to comprehensively learn real noise features from 2-NEX training data. RESULTS: The results of an ablation study validated the network design. The new method achieved improved denoising performance of 3D FSE knee MR images compared with current state-of-the-art methods, based on the peak signal-to-noise ratio and structural similarity index measure. The improved image quality after denoising using the new method was verified by radiological evaluation. CONCLUSION: A deep CNN using the inherent spatial-varying noise information in 2-NEX acquisitions was developed. This method showed promise for clinical MRI assessments of the knee, and has potential applications for the assessment of other anatomical structures.

Prevalence and Radiological Characteristics of the Fabella in Turkish Population.

BACKGROUND: This study aimed to evaluate and analyze the prevalence and radiological characteristics of the fabella in the Turkish population, detecting differences between genders by examining magnetic resonance imaging (MRI) images of subjects. METHODS: A total number of 504 patients aged >18 years who were admitted to the orthopedics and traumatology clinic between November 2018 and October 2020 were included in this retrospective cross-sectional study. Bilateral MRI images that were taken from each patient were randomly selected. Age, sex, laterality (right or left knee), and size of the fabella were retrieved from institutional database records. P-value<0.05 is considered statistically significant. RESULTS: A total of 504 patients were included with 213 males and 291 females. The overall prevalence of fabella was 20.63%. The mean length, thickness, and width of the fabella were 6.05 mm, 4.63 mm, and 5.92 mm, respectively, in the overall population. The fabella was significantly wider, thicker, and longer in males compared to females in the Turkish population. CONCLUSION: This study revealed similar prevalence rates of the fabella in the Turkish population with Caucasian populations and similar size of the fabella in the Asian population. When different prevalence rates and sizes of the fabella among different ethnic populations are considered, it is critical to understand the prevalence or radiological features of the fabella in Turkish subjects to avoid misinterpretation of fabella diseases.

Deep collaborative network with alpha matte for precise knee tissue segmentation from MRI.

BACKGROUND AND OBJECTIVE: Precise segmentation of knee tissues from magnetic resonance imaging (MRI) is critical in quantitative imaging and diagnosis. Convolutional neural networks (CNNs), being state of the art, often challenged by the lack of image-specific adaptation, such as low tissue contrasts and structural inhomogeneities, thereby leading to incomplete segmentation results. METHODS: This paper presents a deep learning-based automatic segmentation framework for precise knee tissue segmentation. A novel deep collaborative method is proposed, which consists of an encoder-decoder-based segmentation network in combination with a low rank tensor-reconstructed segmentation network. Low rank reconstruction in MRI tensor sub-blocks is introduced to exploit the morphological variations in knee tissues. To model the tissue boundary regions and effectively utilize the superimposed regions, trimap generation is proposed for defining high, medium and low confidence regions from the multipath CNNs. The secondary path with low rank reconstructed input mitigates the conditions in which the primary segmentation network can potentially fail and overlook the boundary regions. The outcome of the segmentation is solved as an alpha matting problem by blending the trimap with the source input. RESULTS: Experiments on Osteoarthritis Initiative (OAI) datasets with all the 6 musculoskeletal tissues provide an overall segmentation dice score of 0.8925, where Femoral and Tibial part of cartilage achieving an average dice exceeding 0.9. The volumetric metrics also indicate the superior performances in all tissue compartments. CONCLUSIONS: Experiments on Osteoarthritis Initiative (OAI) datasets and a self-prepared scan validate the effectiveness of the proposed method. Inclusion of extra prediction scale allowed the model to distinguish and segment the tissue boundary accurately. We specifically demonstrate the application of the proposed method in a cartilage segmentation-based thickness map for diagnosis purposes.

Ultrasound-guided intra-articular injection of expanded umbilical cord mesenchymal stem cells in knee osteoarthritis: a safety/efficacy study with MRI data.

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.

Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learning.

Background: This study aimed to build a deep learning model to automatically segment heterogeneous clinical MRI scans by optimizing a pre-trained model built from a homogeneous research dataset with transfer learning. Methods: Conditional generative adversarial networks pretrained on the Osteoarthritis Initiative MR images was transferred to 30 sets of heterogenous MR images collected from clinical routines. Two trained radiologists manually segmented the 30 sets of clinical MR images for model training, validation and test. The model performance was compared to models trained from scratch with different datasets, as well as two radiologists. A 5-fold cross validation was performed. Results: The transfer learning model obtained an overall averaged Dice coefficient of 0.819, an averaged 95 percentile Hausdorff distance of 1.463 mm, and an averaged average symmetric surface distance of 0.350 mm on the 5 random holdout test sets. A 5-fold cross validation had a mean Dice coefficient of 0.801, mean 95 percentile Hausdorff distance of 1.746 mm, and mean average symmetric surface distance of 0.364 mm. It outperformed other models and performed similarly as the radiologists. Conclusions: A transfer learning model was able to automatically segment knee cartilage, with performance comparable to human, using heterogeneous clinical MR images with a small training data size. In addition, the model proved robust when tested through cross validation and on images from a different vendor. We found it feasible to perform fully automated cartilage segmentation of clinical knee MR images, which would facilitate the clinical application of quantitative MRI techniques and other prediction models for improved patient treatment planning.

MR Imaging of the Knee Posterolateral and Posteromedial Corner Injuries.

The posteromedial and posterolateral corners of the knee are important areas to consider when assessing the patient with a possible knee injury. An understanding of the anatomy, associated biomechanics, and typical injury patterns in these regions will improve the value that the radiologist interpreting the MRIs brings to this patient population.