Distinguishing lipoma from liposarcoma is challenging on conventional MRI examination. In case of uncertain diagnosis following MRI, further invasive procedure (percutaneous biopsy or surgery) is often required to allow for diagnosis based on histopathological examination. Radiomics and machine learning allow for several types of pathologies encountered on radiological images to be automatically and reliably distinguished. The aim of the study was to assess the contribution of radiomics and machine learning in the differentiation between soft-tissue lipoma and liposarcoma on preoperative MRI and to assess the diagnostic accuracy of a machine-learning model compared to musculoskeletal radiologists. 86 radiomics features were retrospectively extracted from volume-of-interest on T1-weighted spin-echo 1.5 and 3.0 Tesla MRI of 38 soft-tissue tumors (24 lipomas and 14 liposarcomas, based on histopathological diagnosis). These radiomics features were then used to train a machine-learning classifier to distinguish lipoma and liposarcoma. The generalization performance of the machine-learning model was assessed using Monte-Carlo cross-validation and receiver operating characteristic curve analysis (ROC-AUC). Finally, the performance of the machine-learning model was compared to the accuracy of three specialized musculoskeletal radiologists using the McNemar test. Machine-learning classifier accurately distinguished lipoma and liposarcoma, with a ROC-AUC of 0.926. Notably, it performed better than the three specialized musculoskeletal radiologists reviewing the same patients, who achieved ROC-AUC of 0.685, 0.805, and 0.785. Despite being developed on few cases, the trained machine-learning classifier accurately distinguishes lipoma and liposarcoma on preoperative MRI, with better performance than specialized musculoskeletal radiologists.

To assess the accuracy and reliability of using cone beam computed tomography (CBCT) compared to X-ray six weeks after injury for predicting scaphoid union. Overall; 52 patients with scaphoid fractures between April 2018 and March 2019 were prospectively included in this study. The mean age was 34.52 (13–88) years, and the gender ratio male/female 43/9. Of the fractures, 26 had occurred on the right side, and 26 on the left side. In total, 28 % of patients were manual workers. All patients underwent X-ray and CBCT six weeks after injury. Four readers, two radiologists, and two hand surgeons analyzed the findings using double-blinded X-ray and CBCT and categorized fractures as consolidated based on a 50 % visibility threshold concerning trabecular bridges. Proximal pole sclerosis, communition, cyst formation, and humpback deformity were similarly analyzed for all cases. Agreement between readers was calculated using Kappa, and sensitivity, specificity, and accuracy using RStudio software. The gold standard was the radiologic and clinical follow-up for all patients at two months. Inter-reader agreement between the four readers was moderate concerning X-ray (0.543) but substantial concerning CBCT (0.641). It was almost perfect between seniors regarding CBCT (Kappa = 0.862). Sensitivity, specificity, and accuracy were 0.75–0.78, 0.4, and 0.61–0.64, respectively, for two readers regarding CBCT. The X-ray values were 0.65–0.71, 0.35–0.4, and 0.53–0.59, respectively. CBCT proves more accurate and reliable than X-ray for diagnosing scaphoid union at an early follow-up and prevents longer immobilization and interruption of activity or work.

Objective: To assess the diagnostic performance of morphological MRI features separately and in combination for distinguishing low- from high-grade soft tissue sarcoma (STS). Methods and materials: We retrospectively analysed pre-treatment MRI examinations with T1, T2 with and without fat suppression (FS) and contrast-enhanced T1 obtained in 64 patients with STS categorized histologically as low (n = 21) versus high grade (n = 43). Two musculoskeletal radiologists blinded to histology evaluated MRI features. Diagnostic performance was calculated for each reader and for MRI features showing significant association with histology (p < 0.05). Logistic regression analysis was performed to develop a diagnostic model to identify high-grade STS. Results: Among all evaluated MRI features, only six features had adequate interobserver reproducibility (kappa>0.5). Multivariate logistic regression analysis revealed a significant association with tumour grade for lesion heterogeneity on FS images, intratumoural enhancement≥51% of tumour volume and peritumoural enhancement for both readers (p < 0.05). For both readers, the presence of each of the three features yielded odds ratios for high grade versus low grade from 4.4 to 9.1 (p < 0.05). The sum of the positive features for each reader independent of reader expertise yielded areas under the curve (AUCs) > 0.8. The presence of ≥2 positive features indicated a high risk for high-grade sarcoma, whereas ≤1 positive feature indicated a low-to-moderate risk Conclusion: A diagnostic MRI score based on tumour heterogeneity, intratumoural and peritumoural enhancement enables identification of lesions that are likely to be high-grade as opposed to low-grade STS. Advances in knowledge: Tumour heterogeneity in Fat Suppression sequence, intratumoural and peritumoural enhancement is identified as signs of high-grade sarcoma.

Conventional radiography is the first modality to investigate the radio-ulno-carpal joint in the event of trauma or instability. This study sought to determine the reliability of cone beam computer tomography (CBCT) and scout of view in evaluating carpal alignment compared with conventional radiographs in order to assess the influence of wrist kinematics on usual measurements. We prospectively recruited 305 patients who successively underwent plain radiography and CBCT. 51 patients with prior acute unilateral wrist trauma were eligible for entry into the study (mean age of 39 years). Three blinded readers performed the measurements separately. The axial method and bony axial lines defined previously in the literature were applied, with three categories of measurements performed, consisting of distal radio-ulnar, radiocarpal, and radio/carpometacarpal measurements. Intraclass correlation coefficients (ICCs) for paired t-test were calculated to assess inter- and intra-observer agreements. Inter-observer agreement was very high (>0.94) for all modalities. Intra-observer reliability between scout view and CBCT was almost perfect for all measurements. Intra-observer reliability between radiograph and scout view/CBCT was perfect for distal radio-ulnar measurements, substantial for radio-carpal, and moderate for radio/carpometacarpal measurements. In the absence of a strict position control between two imaging acquisitions, only distal radio-ulnar measurements were shown perfectly reliable when using these two imaging methods, which is suggestive of a minor relevance of ulnar/radial deviation. Excepting for some angles, the radio-carpal and radio-carpometacarpal measurements were shown to differ according to wrist position, being thus more sensitive to flexion/extension of the wrist.