Aims: To compare the accuracy of the optic nerve sheath diameter (ONSD) measured by ocular ultrasonography (US) versus magnetic resonance imaging (MRI) for the diagnosis of increased intracranial pressure (ICP). Material and methods: A systematic search of studies evaluating US ONSD or MRI ONSD for the diagnosis of increased ICP was performed. Data were extracted independently by two authors. We used the bivariate random-effects model to evaluate the diagnostic feasibility of measuring the ONSD in patients increased ICP. A summary receiver operating characteristic (SROC) graph was adopted to calculate sensitivity and specificity. Subgroup analysis was used to explore potential difference in US ONSD and MRI ONSD. Results: A total of 31 studies were included, in which there were 1783 patients diagnosed with US ONSD and 730 patients diagnosed with MRI ONSD. Twenty studies reporting US ONSD were included for quantitative synthesis. The US ONSD had a high diagnostic accuracy, involving estimated sensitivity of 0.92 (95%CI 0.87-0.95), estimated specificity of 0.85 (95%CI 0.79-0.89), positive likelihood ratio (PLR) of 6.0 (95%CI 4.3-8.4), negative likelihood ratio (NLR) of 0.10 (95%CI 0.06-0.15) and Diagnostic Odds Ratio (DOR) of 62 (95%CI 33-117). The data of 11 studies adopting MRI ONSD was pooled. The MRI ONSD demonstrated estimated sensitivity of 0.70 (95%CI 0.60-0.78), estimated specificity of 0.85 (95%CI 0.80-0.90), PLR of 4.8 (95%CI 3.4-6.7), NLR of 0.35 (95%CI 0.27-0.47) and DOR of 13 (95%CI 8-22). The subgroup analysis showed that US ONSD demonstrated a higher sensitivity (0.92 versus 0.70; p<0.01) and almost equal specificity (0.85 vs. 0.85; p=0.67) compared with MRI ONSD. Conclusion: Measurement of ONSD can be a useful tool to predict raised ICP. The US ONSD demonstrated better accuracy than MRI ONSD for the diagnosis of increased ICP.

Background: Lateral malleolar avulsion fractures (LMAFs) and subfibular ossicles (SFOs) are distinct entities that both present as small bone fragments near the lateral malleolus in imaging but require different treatment strategies. Clinical and radiological differentiation is challenging, which can impede timely and precise management. Magnetic resonance imaging (MRI) is the diagnostic gold standard for differentiating LMAFs from SFOs, whereas radiological differentiation using computed tomography (CT) alone is challenging in routine practice. Deep convolutional neural networks (DCNNs) have shown promise in musculoskeletal imaging diagnostics, but robust, multicenter evidence in this specific context is lacking. Objective: This study aims to evaluate several state-of-the-art DCNNs—including the latest You Only Look Once (YOLO) v12 algorithm—for detecting and classifying LMAFs and SFOs in CT images, using MRI-based diagnoses as the gold standard and to compare model performance with radiologists reading CT alone. Methods: In this retrospective study, 1918 patients (LMAF: n=1253, 65.3%; SFO: n=665, 34.7%) were enrolled from 2 hospitals in China between 2014 and 2024. MRI served as the gold standard and was independently interpreted by 2 senior musculoskeletal radiologists. Only CT images were used for model training, validation, and testing. CT images were manually annotated with bounding boxes. The cohort was randomly split into a training set (n=1092, 56.93%), internal validation set (n=476, 24.82%), and external test set (n=350, 18.25%). Four deep learning models—faster R-CNN, single shot multibox detector (SSD), RetinaNet, and YOLOv12—were trained and evaluated using identical procedures. Model performance was assessed using mean average precision at intersection over union=0.5 (mAP50), area under the receiver operating curve (AUC), accuracy, sensitivity, and specificity. The external test set was also independently interpreted by 2 musculoskeletal radiologists with 7 and 15 years of experience, with results compared with the best-performing model. Saliency maps were generated using Shapley values to enhance interpretability. Results: Among the evaluated models, YOLOv12 achieved the highest detection and classification performance, with a mAP50 of 92.1% and an AUC of 0.983 on the external test set—significantly outperforming faster R-CNN (mAP50 63.7%; AUC 0.79); SSD (mAP50 63%; AUC 0.63); and RetinaNet (mAP50 67.0%; AUC 0.73)—all P<.001. When using CT alone, radiologists performed at a moderate level (accuracy: 75.6% and 69.1%; sensitivity: 75.0% and 65.2%; specificity: 76.0% and 71.1%), whereas YOLOv12 approached MRI-based reference performance (accuracy: 92.0%; sensitivity: 86.7%; specificity: 82.2%). Saliency maps corresponded well with expert-identified regions. Conclusions: While MRI (read by senior radiologists) is the gold standard for distinguishing LMAFs from SFOs, CT-based differentiation is challenging for radiologists. A CT-only DCNN (YOLOv12) achieved substantially higher performance than radiologists interpreting CT alone and approached the MRI-based reference standard, highlighting its potential to augment CT-based decision-making where MRI is limited or unavailable.

The presence of multiple accessory spleens in the abdominal cavity is typically limited to two, with cases involving a higher number being exceedingly rare. Concurrently, accessory spleen infarction is remarkably uncommon, primarily resulting from torsion of the vascular pedicle. In this report, we present a case of a 19-year-old male who experienced infarction in one of four accessory spleens. Imaging diagnosis proved challenging, with the definitive diagnosis being made through postoperative pathology, revealing no torsion in the affected accessory spleen. Following surgery combined with anti-inflammatory and analgesic treatment, the patient exhibited an uneventful recovery. No complications were observed at the 3-month follow-up. This case indicates the challenge and difficulty of diagnosing accessory splenic infarction without torsion in imaging diagnosis. Employing a multimodality approach and diffusion-weighted imaging may aid in confirming the diagnosis.

To develop and validate a non-invasive deep learning model that integrates voxel-level radiomics with multi-sequence MRI to predict microsatellite instability (MSI) status in patients with endometrial carcinoma (EC). This two-center retrospective study included 375 patients with pathologically confirmed EC from two medical centers. Patients underwent preoperative multiparametric MRI (T2WI, DWI, CE-T1WI), and MSI status was determined by immunohistochemistry. Tumor regions were manually segmented, and voxel-level radiomics features were extracted following IBSI guidelines. A dual-channel 3D deep neural network based on the Vision-Mamba architecture was constructed to jointly process voxel-wise radiomics feature maps and MR images. The model was trained and internally validated on cohorts from Center I and tested on an external cohort from Center II. Performance was compared with Vision Transformer, 3D-ResNet, and traditional radiomics models. Interpretability was assessed with feature importance ranking and SHAP value visualization. The Vision-Mamba model achieved strong predictive performance across all datasets. In the external test cohort, it yielded an AUC of 0.866, accuracy of 0.875, sensitivity of 0.833, and specificity of 0.900, outperforming other models. Integrating voxel-level radiomics features with MRI enabled the model to better capture both local and global tumor heterogeneity compared to traditional approaches. Interpretability analysis identified glszm_SizeZoneNonUniformityNormalized, ngtdm_Busyness, and glcm_Correlation as top features, with SHAP analysis revealing that tumor parenchyma, regions of enhancement, and diffusion restriction were pivotal for MSI prediction. The proposed voxel-level radiomics and deep learning model provides a robust, non-invasive tool for predicting MSI status in endometrial carcinoma, potentially supporting personalized treatment decision-making.

Purpose: To assess the diagnostic value of CT and MRI in distinguishing nonunited avulsion fracture (NAF) of the lateral malleolus from os subfibulare (OSF). Materials and methods: In this retrospective study, 114 subfibular ossicles (SFOs) in 108 patients were evaluated by CT and MRI for shape, margin, size, CT attenuation, spatial orientation, and anatomical relations. Surgical, arthroscopic, and follow-up findings served as reference standards. Logistic regression and receiver operating characteristic (ROC) analyses assessed diagnostic performance. Results: NAFs were associated with higher incidences of lateral ankle pain (92.3% vs. 71.4%, p = 0.003) and instability (29.2% vs. 10.2%, p = 0.014) than OSF. CT showed that NAF had a more irregular shape, rougher margins, higher attenuation, and anteroposterior orientation compared to OSF (all p < 0.05). MRI revealed ligamentous attachment predominated in NAF (72.3%), while OSF mostly showed discontinuity or apposition (91.8%, p < 0.001). The combined CT model achieved an AUC of 0.782, accuracy of 74.3%, sensitivity of 91.9%, and specificity of 56.8%. MRI-based ligamentous attachment MRI strict criterion yielded an AUC 0.821, with a sensitivity of 72.3% and a specificity of 91.8%, while the MRI inclusive criterion was 0.752, 95.4% and 55.1%. Ossicle size correlated with symptom severity ( p < 0.001). Conclusion: MRI is highly effective for differentiating NAF from OSF by directly visualizing SFO-ligament attachments, while CT provides complementary morphological detail. The combined use of CT and MRI delivers robust diagnostic performance, supporting clinical decision-making in lateral malleolar lesions. Critical relevance statement: CT and MRI can distinguish a nonunited avulsion fracture from os subfibulare. Especially, MRI can visually display the relationship between SFO and the lateral collateral ligament. Key Points: Distinguishing chronic lateral malleolus avulsion fractures from congenital accessory bones remains diagnostically challenging. MRI directly visualizing ligament attachment to the bone fragment best differentiates fractures from accessory bones. Combining MRI and CT findings provides comprehensive evidence for clinical management decisions. Graphical

Objective: The invasiveness of pituitary neuroendocrine tumor is an important basis for formulating individualized treatment plans and improving the prognosis of patients. Radiomics can predict invasiveness preoperatively. To investigate the value of multiparameter magnetic resonance imaging (mpMRI) radiomics in predicting pituitary neuroendocrine tumor invasion into the cavernous sinus (CS) before surgery.Patients and methods: The clinical data of 133 patients with pituitary neuroendocrine tumor (62 invasive and 71 non-invasive) confirmed by surgery and pathology who underwent preoperative mpMRI examination were retrospectively analyzed. Data were divided into training set and testing set according to different field strength equipment. Radiomics features were extracted from the manually delineated regions of interest in T1WI, T2WI and CE-T1, and the best radiomics features were screened by LASSO algorithm. Single radiomics model (T1WI, T2WI, CE-T1) and combined radiomics model (T1WI+T2WI+CE-T1) were constructed respectively. In addition, clinical features were screened to establish clinical model. Finally, the prediction model was evaluated by ROC curve, calibration curve and decision curve analysis (DCA).Results: A total of 10 radiomics features were selected from 306 primitive features. The combined radiomics model had the highest prediction efficiency. The area under curve (AUC) of the training set was 0.885 (95% CI, 0.819-0.952), and the accuracy, sensitivity, and specificity were 0.951,0.826, and 0.725. The AUC of the testing set was 0.864 (95% CI, 0.744-0.985), and the accuracy, sensitivity, and specificity were 0.829,0.952, and 0.700. DCA showed that the combined radiomics model had higher clinical net benefit.Conclusion: The combined radiomics model based on mpMRI can effectively and accurately predict the invasiveness of pituitary neuroendocrine tumor to CS preoperatively, and provide decision-making basis for clinical individualized treatment.