(1) Background: The diagnosis of lumbosacral radiculopathy involves anamnesis, an assessment of sensitivity and strength, diagnostic imaging-usually magnetic resonance imaging (MRI)-and electrodiagnostic testing (EDX), typically electromyography (EMG), and electroneurography (ENG). MRI evaluates the structures supporting the spinal cord, while EDX evaluates root functionality. The present study aimed to analyze the concordance of MRI and EDX findings in patients with clinically suspected radiculopathy. Additionally, we investigated the comparison between these two reference tests and various clinical variables and questionnaires. (2) Methods: We designed a prospective epidemiological study of consecutive cases with an observational, descriptive, cross-sectional, and double-blind nature following the STROBE guidelines, encompassing 142 patients with clinical suspicion of lumbosacral radiculopathy. (3) Results: Of the sample, 58.5% tested positive for radiculopathy using EDX as the reference test, while 45.8% tested positive using MRI. The comparison between MRI and EDX in the diagnosis of radiculopathy in patients with clinical suspicion was not significant; the overall agreement was 40.8%. Only the years with symptoms were comparatively significant between the positive and negative radiculopathy groups as determined by EDX. (4) Conclusion: The comparison between lumbar radiculopathy diagnoses in patients with clinically suspected pathology using MRI and EDX as diagnostic modalities did not yield statistically significant findings. MRI and EDX are complementary tests assessing different aspects in patients with suspected radiculopathy; degeneration of the structures supporting the spinal cord does not necessarily imply root dysfunction.

BACKGROUND: Preclinical rheumatoid arthritis (Pre-RA) is defined as the early stage before the development of clinical RA. While cachexia is a well-known and potentially modifiable complication of RA, it is not known if such an association exists also in the Pre-RA stage. To investigate such issue, we aimed to compare the longitudinal alterations in the muscle composition and adiposity of participants with Pre-RA with the matched controls.
METHODS: In this observational cohort study, the Osteoarthritis Initiative (OAI) participants were categorized into Pre-RA and propensity score (PS)-matched control groups. Pre-RA was retrospectively defined as the absence of RA from baseline to year-2, with progression to physician-diagnosed clinical RA between years 3-8 of the follow-up period. Using a validated deep learning algorithm, we measured MRI biomarkers of thigh muscles and adiposity at baseline and year-2 follow-ups of the cohort. The outcomes were the differences between Pre-RA and control groups in the 2-year rate of change for thigh muscle composition [cross-sectional area (CSA) and intramuscular adipose tissue (Intra-MAT)] and adiposity [intermuscular adipose tissue (Inter-MAT) and subcutaneous adipose tissue (SAT)]. Linear mixed-effect regression models were used for comparison.
RESULTS: After 1:3 PS-matching of the groups for confounding variables (demographics, risk factors, co-morbidities, and knee osteoarthritis status), 408 thighs (102 Pre-RA and 306 control) of 322 participants were included (age mean ± SD: 61.7 ± 8.9 years; female/male: 1.8). Over a 2-year period, Pre-RA was associated with a larger decrease in total thigh muscle CSA [estimate, 95% confidence interval (CI): -180.13 mm2/2-year, -252.80 to -107.47, P-value < 0.001]. Further examination of thigh muscle composition showed that the association of the presence of Pre-RA with a larger decrease in muscle CSA over 2 years was noticeable in the quadriceps, flexors, and sartorius muscle groups (P-values < 0.05). Comparison of changes in total adipose tissue showed no difference between Pre-RA and control participants (estimate, 95% CI: 48.48 mm2/2-year, -213.51 to 310.47, P-value = 0.691). However, in the detailed analysis of thigh adiposity, Pre-RA presence was associated with a larger increase in Inter-MAT (estimate, 95% CI: 150.55 mm2/2-year, 95.58 to 205.51, P-value < 0.001).
CONCLUSIONS: Preclinical rheumatoid arthritis is associated with a decrease in muscle cross-sectional area and an increase in intermuscular adipose tissue, similar to rheumatoid cachexia in clinical rheumatoid arthritis. These findings suggest the presence of cachexia in the preclinical phase of rheumatoid arthritis. Given that cachexia, which can exacerbate health outcomes, is potentially modifiable, this study emphasizes the importance of early identification of patients in their preclinical phase.

OBJECTIVE: Persistent reluctance to perform magnetic resonance imaging (MRI) in patients with abandoned and/or epicardial leads of cardiac implantable electronic devices is related to in vitro studies reporting tip heating. While there is a plethora of data on the safety of MRI in conditional and non-conditional implantable devices, there is a clear lack of safety data in patients with abandoned and/or epicardial leads.
RESULTS: Relevant literature was identified in Medline and CINAHL using the key terms \'magnetic resonance imaging\' AND \'abandoned leads\' OR \'epicardial leads\'. Secondary literature and cross-references were supplemented. For reporting guidance, the Preferred Reporting Items for Systematic reviews and Meta-Analyses 2020 was used. International Prospective Register of Systematic Reviews (PROSPERO) registration number 465530. Twenty-one publications with a total of 656 patients with 854 abandoned and/or epicardial leads and 929 MRI scans of different anatomical regions were included. No scan-related major adverse cardiac event was documented, although the possibility of under-reporting of critical events in the literature should be considered. Furthermore, no severe device dysfunction or severe arrhythmia was reported. Mainly transient lead parameter changes were observed in 2.8% in the subgroup of patients with functional epicardial leads. As a possible correlate of myocardial affection, subjective sensations occurred mainly in the subgroup with abandoned epicardial leads (4.0%), but no change in myocardial biomarkers was observed.
CONCLUSIONS: Existing publications did not report any relevant adverse events for MRI in patients with abandoned and/or epicardial leads if performed according to strict safety guidelines. However, a more rigorous risk-benefit calculation should be made for patients with epicardial leads.

This review examines the advancements in magnetic resonance imaging (MRI) techniques and their pivotal role in diagnosing and managing gliomas, the most prevalent primary brain tumors. The paper underscores the importance of integrating modern MRI modalities, such as diffusion-weighted imaging and perfusion MRI, which are essential for assessing glioma malignancy and predicting tumor behavior. Special attention is given to the 2021 WHO Classification of Tumors of the Central Nervous System, emphasizing the integration of molecular diagnostics in glioma classification, significantly impacting treatment decisions. The review also explores radiogenomics, which correlates imaging features with molecular markers to tailor personalized treatment strategies. Despite technological progress, MRI protocol standardization and result interpretation challenges persist, affecting diagnostic consistency across different settings. Furthermore, the review addresses MRI\'s capacity to distinguish between tumor recurrence and pseudoprogression, which is vital for patient management. The necessity for greater standardization and collaborative research to harness MRI\'s full potential in glioma diagnosis and personalized therapy is highlighted, advocating for an enhanced understanding of glioma biology and more effective treatment approaches.

BACKGROUND: Robust predictive models of clinical impairment and worsening in multiple sclerosis (MS) are needed to identify patients at risk and optimize treatment strategies.
OBJECTIVE: To evaluate whether machine learning (ML) methods can classify clinical impairment and predict worsening in people with MS (pwMS) and, if so, which combination of clinical and magnetic resonance imaging (MRI) features and ML algorithm is optimal.
METHODS: We used baseline clinical and structural MRI data from two MS cohorts (Berlin: n = 125, Amsterdam: n = 330) to evaluate the capability of five ML models in classifying clinical impairment at baseline and predicting future clinical worsening over a follow-up of 2 and 5 years. Clinical worsening was defined by increases in the Expanded Disability Status Scale (EDSS), Timed 25-Foot Walk Test (T25FW), 9-Hole Peg Test (9HPT), or Symbol Digit Modalities Test (SDMT). Different combinations of clinical and volumetric MRI measures were systematically assessed in predicting clinical outcomes. ML models were evaluated using Monte Carlo cross-validation, area under the curve (AUC), and permutation testing to assess significance.
RESULTS: The ML models significantly determined clinical impairment at baseline for the Amsterdam cohort, but did not reach significance for predicting clinical worsening over a follow-up of 2 and 5 years. High disability (EDSS ≥ 4) was best determined by a support vector machine (SVM) classifier using clinical and global MRI volumes (AUC = 0.83 ± 0.07, p = 0.015). Impaired cognition (SDMT Z-score ≤ -1.5) was best determined by a SVM using regional MRI volumes (thalamus, ventricles, lesions, and hippocampus), reaching an AUC of 0.73 ± 0.04 (p = 0.008).
CONCLUSIONS: ML models could aid in classifying pwMS with clinical impairment and identify relevant biomarkers, but prediction of clinical worsening is an unmet need.

BACKGROUND: Traumatic bone marrow lesions (BML) are frequently identified on knee MRI scans in patients following an acute full-thickness, complete ACL tear. BMLs coincide with regions of elevated localized bone loss, and studies suggest these may act as a precursor to the development of post-traumatic osteoarthritis. This study addresses the labour-intensive manual assessment of BMLs by using a 3D U-Net for automated identification and segmentation from MRI scans.
METHODS: A multi-task learning approach was used to segment both bone and BML from T2 fat-suppressed (FS) fast spin echo (FSE) MRI sequences for BML assessment. Training and testing utilized datasets from individuals with complete ACL tears, employing a five-fold cross-validation approach and pre-processing involved image intensity normalization and data augmentation. A post-processing algorithm was developed to improve segmentation and remove outliers. Training and testing datasets were acquired from different studies with similar imaging protocol to assess the model\'s performance robustness across different populations and acquisition conditions.
RESULTS: The 3D U-Net model exhibited effectiveness in semantic segmentation, while post-processing enhanced segmentation accuracy and precision through morphological operations. The trained model with post-processing achieved a Dice similarity coefficient (DSC) of 0.75 ± 0.08 (mean ± std) and a precision of 0.87 ± 0.07 for BML segmentation on testing data. Additionally, the trained model with post-processing achieved a DSC of 0.93 ± 0.02 and a precision of 0.92 ± 0.02 for bone segmentation on testing data. This demonstrates the approach\'s high accuracy for capturing true positives and effectively minimizing false positives in the identification and segmentation of bone structures.
CONCLUSIONS: Automated segmentation methods are a valuable tool for clinicians and researchers, streamlining the assessment of BMLs and allowing for longitudinal assessments. This study presents a model with promising clinical efficacy and provides a quantitative approach for bone-related pathology research and diagnostics.

This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.

OBJECTIVE: The purpose of this study was to investigate the ability of radiomic characteristics of magnetic resonance images to predict vascular endothelial growth factor (VEGF) expression in hepatocellular carcinoma (HCC) patients.
METHODS: One hundred and twenty-four patients with HCC who underwent fat-suppressed T2-weighted imaging (FS-T2WI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) one week before surgical resection were enrolled in this retrospective study. Immunohistochemical analysis was used to evaluate the expression level of VEGF. Radiomic features were extracted from the axial FS-T2WI, DCE-MRI (arterial phase and portal venous phase) images of axial MRI. Least absolute shrinkage and selection operator (LASSO) and stepwise regression analyses were performed to select the best radiomic features. Multivariate logistic regression models were constructed and validated using tenfold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models.
RESULTS: Our results show that there were 94 patients with high VEGF expression and 30 patients with low VEGF expression among the 124 HCC patients. The FS-T2WI, DCE-MRI and combined MRI radiomics models had AUCs of 0.8713, 0.7819, and 0.9191, respectively. There was no significant difference in the AUC between the FS-T2WI radiomics model and the DCE-MRI radiomics model (p > 0.05), but the AUC for the combined model was significantly greater than the AUCs for the other two models (p < 0.05) according to the DeLong test. The combined model had the greatest net benefit according to the DCA results.
CONCLUSIONS: The radiomic model based on multisequence MR images has the potential to predict VEGF expression in HCC patients. The combined model showed the best performance.

Background: Psoas muscle abscess (PMA) is an uncommon yet severe condition characterized by diagnostic and therapeutic challenges due to its varied etiology and nonspecific symptoms. This study aimed to evaluate the effectiveness and accuracy of various imaging techniques used in the image-guided percutaneous drainage (PD) of PMA. Methods: A systematic review was conducted following the PRISMA guidelines. We searched PubMed, Google Scholar, and Science Direct for studies published in English from 1998 onwards that reported on the use of PD in treating PMA, detailing outcomes and complications. Imaging modalities guiding PD were also examined. Results: We identified 1570 articles, selecting 39 for full review. Of these, 23 met the inclusion criteria; 19 were excluded due to unspecified PMA, absence of imaging guidance for PD, or inconclusive results. Eleven studies utilized computed tomography (CT) for PD, with six also using magnetic resonance imaging (MRI). Ten studies implemented ultrasound (US)-guided PD; variations in diagnostic imaging included combinations of US, CT, and MRI. A mixed approach using both CT and US was reported in two articles. Most studies using CT-guided PD showed complete success, while outcomes varied among those using US-guided PD. No studies employed MRI-guided PD. Conclusions: This review supports a multimodal approach for psoas abscess management, using MRI for diagnosis and CT for drainage guidance. We advocate for Cone Beam CT (CBCT)-MRI fusion techniques with navigation systems to enhance treatment precision and outcomes, particularly in complex cases with challenging abscess characteristics.

Hepatocellular carcinoma (HCC) is the sixth most common malignant tumor and the third leading cause of cancer death worldwide. Most patients are diagnosed at an advanced stage, and systemic chemotherapy is the preferred treatment modality for advanced HCC. Curcumin (CUR) is a polyphenolic antineoplastic drug with low toxicity obtained from plants. However, its low bioavailability and poor solubility limit its functionality. In this study, radiofrequency- (RF) enhanced responsive nanoflowers (NFs), containing superparamagnetic ferric oxide nanoclusters (Fe3O4 NCs), - CUR layer, - and MnO2 (CUR-Fe@MnO2 NFs), were verified to have a thermal therapeutic effect. Transmission electron microscopy was used to characterize the CUR-Fe@MnO2 NFs, which appeared flower-like with a size of 96.27 nm. The in vitro experimental data showed that RF enhanced the degradation of CUR-Fe@MnO2 NFs to release Mn2+ and CUR. The cytotoxicity test results indicated that after RF heating, the CUR-Fe@MnO2 NFs significantly suppressed HCC cell proliferation. Moreover, CUR-Fe@MnO2 NFs were effective T 1/T 2 contrast agents for molecular magnetic resonance imaging due to the release of Mn2+ and Fe3O4 NCs.