Objective Establish a model based on radiomics combined with machine learning to predict the short-term prognosis of patients with spontaneous cerebral hemorrhage and validate the model. Methods This study retrospectively collected imaging and clinical data from 573 patients with spontaneous cerebral hemorrhage at the Affiliated Hospital of Jiujiang University,forming a training set; And the data of 100 patients with spontaneous cerebral hemorrhage from the First People's Hospital of Nanning were used as the external validation set.Based on LASSO algorithm for variable dimensionality reduction,10 fold cross validation is used to optimize its regularization parameters.Build a prediction model using the selected optimal parameters.Subsequently,a multi factor Logistic regression model was fitted onto the training set to establish a joint prediction model,and the Area Under the Receiver Operating Characteristic Curve (AUC) was calculated to evaluate the discriminative performance of the model. Results By comparing the performance of clinical models,radiomics models,and joint models,the sensitivity,specificity,and AUC of the clinical model in the training set and external validation set were 0.710,0.792,0.828,and 0.526,0.857,0.706; The sensitivity,specificity,and AUC of the radiomics model in the training set and external validation set were 0.713,0.785,0.832,and 0.772,0.612,0.717; The sensitivity,specificity,and AUC of the joint model in the training set and external validation set were 0.710,0.846,0.860,and 0.579,0.857,and 0.725.Overall,the joint model performs the best.The model evaluation results show that the calibration curve verifies the good predictive accuracy of the joint model; Meanwhile,clinical decision curve analysis confirms that the model has ideal clinical net benefits. Conclusion This study provides an effective personalized prediction tool for the short-term prognosis risk assessment of patients with spontaneous cerebral hemorrhage by integrating radiomics features and clinical baseline data,and constructing a column chart using machine learning methods.

Objective To explore the predictive value of relative cerebral blood volume (rCBV) for collateral circulation and endovascular treatment (EVT) outcomes in stroke patients. Methods A total of 148 patients who underwent EVT for acute anterior circulation large vessel occlusion were included and divided into good prognosis group and poor prognosis group,as well as good collateral circulation group and poor collateral circulation group.The data and CT perfusion (CTP) parameters of the two groups were compared,and multivariate Logistic regression analysis was used to identify independent predictors of prognosis. Results Multivariate analysis showed that admission NIHSS score,core infarct volume (V_CBF < 30%),ASPECTS score,and rCBV were all independent predictors of prognosis (all P < 0.05).ROC curve analysis indicated that the combined prediction model of rCBV,admission NIHSS score,V_CBF < 30%,and ASPECTS score had the best efficacy (AUC = 0.97). Conclusion rCBV can be used as an important marker for evaluating collateral circulation status and predicting EVT outcomes.The combination of clinical and imaging parameters can significantly improve the predictive efficacy of prognosis.

Objective To investigate the value of a radiomics model based on non-contrast CT scans in predicting hematoma expansion in patients with spontaneous intracerebral hemorrhage (SICH). Methods We retrospectively enrolled 393 SICH patients from two medical centers between January 2016 and March 2025.A total of 281 patients from the Shandong University of Traditional Chinese Medicine Affiliated Hospital were randomly divided into a training set (n=197) and an internal validation set (n=84) at a 7:3 ratio,while 112 patients from Shandong Provincial Qianfoshan Hospital served as an independent external test set.Inclusion criteria were:diagnosis of SICH,initial non-contrast CT performed within 6 hours of symptom onset,and a follow-up CT within 72 hours.Exclusion criteria included secondary intracranial hemorrhage,surgical intervention or death prior to the follow-up CT,hemorrhagic transformation of an ischemic cerebral infarction,and images with significant artifacts.A total of 393 eligible patients were enrolled and randomly allocated into training,validation,and test sets in a 7:2:1 ratio.Manual segmentation of the regions of interest was performed using 3D Slicer software.Features were extracted and selected using both traditional radiomics and a ViT-3D deep learning model.After feature fusion and selection,multiple machine learning classifiers—including Logistic Regression,Support Vector Machine,K-Nearest Neighbors,Random Forest,Extra Trees,Extreme Gradient Boosting (XGBoost),LightGBM,and Multi-layer Perceptron were built on the PixelMedAI platform.The models were optimized via five-fold cross-validation on the training set to identify the best-performing one. Results The model incorporating combined features demonstrated superior predictive performance across the training,validation,and test sets compared to other models.Its performance metrics were as follows:Training set (AUC 0.929,Sensitivity 0.923,Specificity 0.788,Accuracy 0.832); Validation set (AUC 0.961,Sensitivity 0.929,Specificity 0.946,Accuracy 0.940); Test set (AUC 0.927,Sensitivity 0.810,Specificity 0.923,Accuracy 0.902).Delong's test confirmed that the AUC of this model was statistically significantly different from those of the other five models. Conclusion A radiomics model based on non-contrast CT shows favorable performance in predicting early hematoma expansion in SICH.The LightGBM model,which integrates clinical,conventional imaging,and radiomic features,demonstrated the best predictive efficacy.

Objective To investigate the predictive value of diffusion kurtosis imaging (DKI) and magnetization transfer ratio (MTR) for surgical outcomes in adults with tethered cord syndrome (TCS). Methods Seventeen adult TCS patients and 17 healthy controls were prospectively enrolled.Preoperative 3.0 T MRI was performed for DKI and MTR imaging of the conus medullaris and caudal spinal cord.Correlations between imaging metrics and postoperative outcomes were analyzed. Results Patients with RR >50% showed significantly higher KA values than those with RR ≤50% (P = 0.002),while MK values were significantly lower (P = 0.031).KA correlated positively with RR (ρ = 0.873,P < 0.001),whereas MK correlated negatively (ρ = -0.534,P = 0.027).MTR at the conus medullaris showed significant positive correlations with RR (ρ = 0.666-0.697,P < 0.05). Conclusion Preoperative DKI measurements (KA,MK) and MTR values significantly correlated with surgical recovery rates in adult TCS,which could potentially aid clinical decision-making.

Objective s To explore the feasibility of predicting the efficacy of induction chemotherapy (IC) in patients with nasopharyngeal carcinoma (NPC) based on pre-treatment tumor T-stage and magnetic resonance imaging (MRI) features. Methods A total of 238 patients with biopsy-confirmed NPC were included. All patients received IC and were categorized as responders or poor responders according to the Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1). The following clinical characteristics and MRI features were assessed: age,sex,T-stage,N-stage,clinical stage,IC regimen; involvement of retropharyngeal lymph nodes (RLNs) and cervical lymph nodes (CLNs),their locations,nodal grouping (NG),lymph node necrosis,extranodal extension (ENE),and carotid space involvement (CSI). The area under the receiver operating characteristic curve (AUC),sensitivity,specificity,and accuracy were used to evaluate the model's performance in predicting IC efficacy. A 10-fold cross-validation approach was employed to assess the diagnostic performance and generalizability of the predictive model. The DeLong test was used to compare differences in diagnostic efficacy between the model and each independent risk predictor. Results Of the 238 patients,124 were classified as responders and 114 as poor responders. Multivariate Logistic regression analysis revealed that T-stage (OR = 0.096,95% CI: 0.026-0.349,P < 0.001),CSI (OR = 0.125,95% CI: 0.053-0.298,P < 0.001),and ENE of cervical lymph nodes (OR = 0.039,95% CI: 0.018-0.085,P < 0.001) were independent predictors of IC response. The model constructed based on these independent predictors achieved an AUC of 0.867 (95% CI: 0.817-0.907),which was significantly higher than that of each individual predictor (all P < 0.001). The model demonstrated a sensitivity of 0.855 (95% CI: 0.780-0.912),a specificity of 0.754 (95% CI: 0.665-0.830),and an accuracy of 0.807 (95% CI: 0.751-0.855). The mean AUC obtained through 10-fold cross-validation was 0.872 (95% CI: 0.836-0.909). Conclusion A model incorporating tumor T-stage and MRI features shows potential for predicting the efficacy of IC in NPC before treatment,which may provide valuable guidance for developing personalized therapeutic strategies.

Objective To investigate the value of texture analysis of diffusion-weighted imaging (DWI) in differentiating the origin site from the peripheral region of sinonasal inverted papilloma (SNIP). Methods Clinical and imaging data of 44 patients with pathologically confirmed SNIP were retrospectively analyzed.The origin and periphery of SNIP were determined based on surgical records.Regions of interest (ROIs) were manually delineated on DWI at both sites to perform texture analysis,and quantitative parameters including mean apparent diffusion coefficient (ADC_mean),10th percentile (ADC_10%),90th percentile (ADC_90%),skewness,kurtosis,and entropy were obtained.The Mann-Whitney U test or paired t-test was used to compare differences in DWI texture analysis parameters between the origin and periphery of SNIP.Multivariate Logistic regression analysis was performed to identify the optimal diagnostic parameters,and their discriminatory performance was assessed using receiver operating characteristic (ROC) curve analysis.Interobserver agreement for texture parameter measurements was evaluated using the intraclass correlation coefficient (ICC). Results The origin site exhibited significantly lower ADC_mean,ADC_10%,ADC_90%,and entropy than the peripheral region (all P < 0.05).Multivariate Logistic regression analysis showed that ADC_90% [odds ratio（OR）= 3.976,95% confidence interval（CI）: 1.927-8.202,P < 0.001]and entropy (OR = 1.931,95% CI: 1.032-3.614,P = 0.040) were associated with the SNIP origin site.The combined model of ADC_90% and entropy demonstrated optimal discriminatory efficacy in differentiating the origin from the peripheral region [area under the curve （AUC）= 0.861,95% CI: 0.781-0.940]. Conclusion sDWI texture analysis-derived parameters,especially ADC_90% and entropy,provide significant diagnostic value in differentiating the origin site from the peripheral region of SNIP.

Objective To apply bibliometric methods for a visualized analysis of research hotspots and trends in magnetic resonance imaging (MRI) of endolymphatic hydrops (EH), thereby providing references for future development in this field. Methods English publications from 2000 to 2025 on MRI of EH were retrieved from the Web of Science database. CiteSpace 6.4.R1 software was employed to visualize collaborative networks among countries, institutions, and authors, as well as keyword co-occurrence. Results A total of 422 articles were included. Annual publication output demonstrated a rapidly increasing trend, peaking in 2021 (57 articles). Japan dominated in publication volume (158 articles) and international collaboration, whereas China ranked second (94 articles) but exhibited the highest betweenness centrality (0.45). Nagoya University was identified as the core research institution (105 articles). Keyword clustering revealed that current research hotspots focus on the glymphatic system, blood-labyrinth barrier evaluation, and artificial intelligence-assisted diagnosis. Conclusion MRI research of EH has evolved from a technical exploration phase into an active, interdisciplinary field. Future investigations are expected to advance toward precise quantification and multimodal integration.

Objective To explore the clinical value of deep learning reconstruction (DLR) combined with black-blood technique in evaluating morphological characteristics of carotid atherosclerotic plaques,using contrast-enhanced high-resolution magnetic resonance imaging of the carotid artery vessel wall (HRMRI) as the reference standard. Methods We retrospectively collected data from 20 patients with carotid atherosclerosis who underwent both carotid computed tomography angiography (CTA) and HRMRI within a two-week interval between December 2024 and May 2025.A total of 40 plaques were included.CTA and black-blood images were reconstructed using DLR and hybrid iterative reconstruction (HIR) algorithms,respectively,forming four groups: D-black blood,D-CTA,H-black blood,and H-CTA.Using HRMRI as the reference standard,morphological characteristics including the degree of lumen stenosis,maximum wall thickness (Max WT),normalized wall index (NWI),and fibrous cap status were evaluated.Diagnostic performance for NWI > 0.56,severe lumen stenosis,and thin and/or ruptured fibrous cap was assessed.The Wilcoxon signed-rank test and Friedman test were used to compare measurements among groups. Results The degree of carotid lumen stenosis in the D-black blood group was significantly higher than that in the D-CTA group (Z = 2.634,P = 0.008).The D-black blood group demonstrated a sensitivity of 1.000 and specificity of 0.971 for detecting severe lumen stenosis,outperforming the H-black blood group (sensitivity 1.000,specificity 0.912).Both Max WT and NWI values were significantly higher in black-blood groups than in CTA groups (P < 0.001).For diagnosing NWI > 0.56,both D-black blood and H-black blood groups achieved a sensitivity of 1.000 and specificity of 1.000,superior to the D-CTA group (sensitivity 0.895,specificity 1.000) and H-CTA group (sensitivity 0.868,specificity 1.000).The D-black blood group showed a sensitivity of 1.000 and specificity of 0.950 for detecting thin and/or ruptured fibrous caps,exceeding the H-black blood group (sensitivity 1.000,specificity 0.750). Conclusion CTA black-blood images provide high diagnostic value for evaluating lumen stenosis,maximum wall thickness,plaque burden,and fibrous cap characteristics.DLR combined with black-blood technique enables better assessment of plaque and lumen morphological features and is suitable for clinical application.

Objective To retrospectively analyze the relationship between mammographic radiation dose and glandular composition, to evaluate the utility and effectiveness of Radimetrics™ in collecting patient data from full-field digital mammography (FFDM) examinations, and to identify factors associated with increased mean glandular dose (MGD). Methods From July 2022 to July 2023, a total of 2138 FFDM images from 533 randomly selected patients were collected to assess breast composition. Using Radimetrics™, we analyzed the correlations between patient age, breast compression force, breast compression thickness, tube voltage, tube current-time product, breast parenchymal composition, and MGD. In patients with MGD exceeding the diagnostic reference level (fourth quartile, ≥75%), potential causes for the increased radiation exposure were investigated. Results The MGD for the 2,138 FFDM images was （2.00 ± 0.32） mGy. Mammographic parameters including tube voltage, tube current-time product, and breast compression force showed positive correlations with MGD per image (all P < 0.05). In contrast, patient age and breast compression thickness exhibited negative correlations with MGD per image (all P< 0.05). The "dense breast" group had a significantly higher MGD than the "non-dense breast" group (P< 0.05), and the "dense" group was younger than the "non-dense" group (P< 0.05). Conclusion The radiation dose management system is practical and effective for collecting patient examination data and analyzing factors related to radiation dose in FFDM examinations.

Objective TTo investigate the imaging characteristics of solitary sternal lesions synchronously displayed on routine breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in patients with breast cancer,and to evaluate its diagnostic value in differentiating benign from metastatic sternal lesions. Methods This retrospective study analyzed data from breast cancer patients who underwent routine breast DCE-MRI at our institution between January 2014 and June 2025.A total of 77 patients with incidentally detected solitary sternal lesions and complete clinical information were enrolled,including 34 benign and 43 metastatic lesions.PET-CT or pathological results served as the reference standard.Differences between the two groups were compared regarding maximal lesion diameter,location,morphology,margin,enhancement pattern,degree of enhancement,time-signal intensity curve (TIC) type,T₁-weighted imaging (T₁WI) signal,fat-suppressed T₂-weighted imaging (FS-T₂WI) signal,diffusion-weighted imaging (DWI) characteristics,and apparent diffusion coefficient (ADC) values.Univariate analysis was performed using the t-test,chi-square test,or Fisher's exact test,followed by multivariate Logistic regression to identify independent predictors. Results Statistically significant differences were observed between benign and metastatic lesions in maximal diameter,morphology,margin,enhancement pattern,degree of enhancement,FS-T₂WI signal homogeneity,DWI characteristics,and ADC values (all P < 0.05).Maximal diameter demonstrated the highest diagnostic performance (sensitivity 0.84,specificity 0.79,accuracy 0.82).Multivariate Logistic regression analysis revealed that FS-T₂WI signal homogeneity (inhomogeneous vs.homogeneous:OR = 25.03,P < 0.001; mixed vs.homogeneous:OR = 14.74,P = 0.033) and enhancement pattern (ring-like vs.homogeneous:OR = 29.01,P = 0.045) were independent predictors for differentiating benign from metastatic sternal lesions. Conclusion Breast DCE-MRI enables synchronous visualization of sternal lesions and provides significant value in differentiating benign from metastatic sternal lesions in breast cancer patients.FS-T₂WI signal homogeneity and enhancement pattern are key independent predictive factors that can improve diagnostic accuracy and assist in clinical decision-making.

Objective To investigate the value of cardiac magnetic resonance feature tracking (CMR-FT) for quantitative assessment and prognostic risk stratification in patients with myocarditis. Methods This retrospective study enrolled 54 patients with myocarditis and 30 healthy volunteers. CMR-FT was used to compare differences in cardiac function and myocardial strain parameters among myocarditis patients with impaired ejection fraction (EF), myocarditis patients with preserved EF, and healthy controls. Receiver operating characteristic (ROC) curves were plotted to assess diagnostic performance. Patients were further divided into event and non-event groups based on the occurrence of endpoint events. Multivariate Cox regression analysis was used to identify prognostic risk factors. According to the cutoff values derived from ROC curves of independent risk factors, patients were classified into high-risk and low-risk groups, and survival differences were compared between the groups. Results Compared with the control group, myocarditis patients with LVEF ≥50% showed decreased LVGRS, LVGCS, LVGLS, and RVGLS (all P < 0.05). ROC curve analysis indicated that LVGRS had the highest diagnostic efficacy in distinguishing preserved EF myocarditis patients from healthy controls (AUC = 0.811). During follow-up, 16 patients experienced major adverse cardiac events (MACE). Multivariate Cox regression analysis revealed that LVEDVi (HR = 1.134, 95% CI: 1.036-1.242, P = 0.007), LVGLS (HR = 1.395, 95% CI: 1.059-1.837, P= 0.018), and LVGRS (HR = 0.895, 95% CI: 0.807-0.994,P= 0.038) were independently associated with adverse outcomes. The AUCs for predicting MACE were 0.813, 0.789, and 0.744 for LVEDVi, LVGLS, and LVGRS, respectively. Kaplan-Meier survival curves demonstrated that the high-risk group (LVEDVi >84.75 ml/m², LVGLS >-10.96%, LVGRS <17.28%) had significantly lower event-free survival than the low-risk group (all P< 0.05). Conclusion CMR-FT can effectively distinguish myocarditis patients with preserved EF from healthy individuals, facilitating early detection of impaired cardiac function. Furthermore, cardiac function and strain parameters derived from this technique provide prognostic information in patients with myocarditis; increased LVEDVi and impaired LVGLS and LVGRS indicate a higher risk burden and are significantly associated with adverse outcomes.

Objective To assess the impact of ultra-high-resolution photon-counting detector CT (UHR PCD-CT) combined with ultra-low-dose protocols on detection rate, image quality, and volume measurement accuracy of pulmonary nodules across varying sizes and types. Methods A thoracic phantom containing simulated pulmonary nodules was scanned on a UHR PCD-CT system at four dose levels (CTDIvol: 9.05, 1.00, 0.07, and 0.03 mGy). All images were reconstructed with 0.2 mm and 1.0 mm slice thicknesses, a 1024×1024 matrix, a BI64 convolution kernel, and Quantum Iterative Reconstruction (QIR) at Level 3. Quantitative analysis included nodule detection rate, image noise (standard deviation, SD), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Nodule volumes were measured using dedicated AI-based software, with absolute percentage error (APE_volume) calculated. Subjective image quality was scored on a 5-point scale using images acquired at 9.05 mGy as the reference standard. Results With decreasing dose, nodule detection rates decreased while APE_volume increased. Solid nodules (SNs) exhibited higher detection rates than ground-glass nodules (GGNs), and nodules ≥8 mm demonstrated superior detection rates and volume measurement accuracy compared with smaller nodules. For both nodule types, SD increased with decreasing dose, whereas SNR and CNR decreased; the reduction in CNR was more pronounced in nodules ≥8 mm (all P < 0.05). Subjective analysis indicated that image quality at 1.00 mGy was comparable to the reference dose of 9.05 mGy, and images acquired at 0.07 mGy remained diagnostically acceptable (all P < 0.05). Conclusion Even at ultra-low doses (0.03-0.07 mGy), UHR PCD-CT combined with AI-assisted diagnostic software maintains clinically acceptable detection rates for pulmonary nodules (particularly SNs and those ≥5 mm in diameter) and diagnostic image quality, demonstrating promising clinical potential.

Objective To develop and validate a deep learning model integrating Vision Transformer (ViT) architecture with radiomics features for preoperative noninvasive prediction of perineural invasion (PNI) in esophageal squamous cell carcinoma (ESCC). Methods This retrospective study enrolled 197 patients with histopathologically confirmed ESCC from two medical centers. Patients from center 1 (n = 133) constituted the training set, and those from center 2 (n = 64) constituted the test set. Radiomics features, including topological and fractal features, were extracted from preoperative contrast-enhanced CT images. Concurrently, deep learning features were extracted using the ViT architecture. Five models were constructed: clinical model, radiomics model, ViT model, deep learning-radiomics (DLR) fusion model, and comprehensive model. Results In the training set, the area under the curve (AUC) values for the clinical, radiomics, ViT, DLR, and comprehensive models were 0.541, 0.700, 0.785, 0.858, and 0.855, respectively. The DLR model demonstrated optimal performance, significantly outperforming the single-modality models (all P < 0.01). In the test set, the AUC values for the clinical, radiomics, ViT, DLR, and comprehensive models were 0.669, 0.585, 0.657, 0.640, and 0.662, respectively. Conclusion The DLR fusion model integrating ViT and radiomics features enables effective preoperative noninvasive prediction of PNI status in ESCC patients, providing a valuable decision-support tool for individualized clinical management.

Objective To investigate the imaging subtypes, pathological characteristics, and prognostic significance of hepatobiliary phase (HBP) hyperintense hepatocellular carcinoma (HCC) based on gadoxetic acid disodium (Gd-EOB-DTPA)-enhanced MRI. Methods A retrospective analysis was conducted on 211 patients with pathologically confirmed solitary HCC who underwent curative hepatic resection. Patients were classified into a hyperintense group (n=54) and a hypointense group (n=157) based on HBP signal intensity. Imaging findings, clinical data, and pathological features were compared between the two groups. Recurrence-free survival (RFS) was evaluated using Kaplan-Meier curves, with group differences assessed by the log-rank test. Independent predictors of RFS were identified using Cox proportional hazards regression analysis. Results In the hyperintense group, type I (homogeneous) accounted for 51.9% (28/54), type Ⅱ (nodule-in-nodule) for 18.5% (10/54), and type Ⅲ (mosaic) for 29.6% (16/54). Serum AFP (8.3 ng/mL vs. 26.9 ng/mL, P=0.009) and PIVKA-Ⅱ (36.7 mAU/mL vs. 126.7 mAU/mL, P=0.003) levels were significantly lower in the hyperintense group. Pathologically, the hyperintense group showed higher proportions of moderately to well-differentiated tumors (85.2%) and trabecular-pseudoacinar patterns (53.7%), with higher rates of green hepatoma (61.1% vs. 12.7%,P< 0.001) and fibrous capsule formation (83.3% vs. 61.8%,P=0.004), but a lower incidence of microvascular invasion (11.1% vs. 26.1%,P=0.022). After a median follow-up of 34 months, the 1-, 3-, and 5-year RFS rates in the hyperintense group (98.1%, 83.3%,and 66.7%, respectively) were significantly higher than those in the hypointense group (88.5%, 70.7%, and 47.8%,respectively) (P=0.003). Multivariate Cox analysis identified HBP hyperintensity (HR=0.472, 95% CI: 0.226-0.861,P=0.022), PIVKA-Ⅱ < 40 mAU/mL (HR=0.514, 95% CI: 0.317-0.725, P=0.003), and moderate-to-high tumor differentiation (HR=0.567, 95% CI: 0.314-0.887,P=0.039) as independent predictors of postoperative RFS. Conclusion HBP-hyperintense HCC is characterized predominantly by homogeneous imaging features and exhibits clinicopathological characteristics associated with lower tumor aggressiveness. HBP hyperintensity may serve as a valuable imaging biomarker for predicting postoperative recurrence risk in HCC, providing important guidance for patient risk stratification and clinical decision-making.

Objective To investigate the efficacy of a dual-region [hepatocellular carcinoma （HCC） primary tumor and spleen] CT radiomics model in predicting early recurrence (ER) in patients undergoing postoperative adjuvant transarterial chemoembolization (PA-TACE) after curative hepatectomy for HCC. Methods A retrospective analysis was conducted on 172 patients who received PA-TACE. Radiomics features were extracted from arterial and portal venous phase contrast-enhanced CT images of the abdomen acquired within one week before curative resection, along with clinical and serological data. ER-related radiomics features were selected from both the HCC and spleen regions. Least absolute shrinkage and selection operator (LASSO) regression combined with Logistic regression was used to construct radiomics scores (Rad-scores) for each region and a combined Rad-score integrating both regions. A nomogram incorporating clinical variables and the dual-region Rad-score was subsequently developed and evaluated in terms of discrimination, calibration, and clinical utility. Results All three radiomics scores demonstrated good performance in predicting ER. The combined Rad-score performed optimally, achieving an area under the curve (AUC) of 0.845 (95% confidence interval [CI]: 0.776-0.914) in the training cohort and 0.843 (95% CI: 0.715-0.970) in the validation cohort. Multivariate logistic regression identified maximum tumor diameter, AFP classification, and the combined Rad-score as independent prognostic factors for ER. Decision curve analysis (DCA) and clinical impact curve (CIC) demonstrated favorable clinical utility for the nomogram. Conclusion The multimodal dual-region radiomics model combining HCC and spleen features serves as an independent prognostic tool for ER following curative hepatectomy and PA-TACE. The integration of dual-region radiomics signatures with clinicopathological factors exhibits promising clinical application value.

Objective To develop and validate an interpretable, individualized prediction model integrating multi-regional radiomics features and body composition parameters for predicting microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC). Methods This retrospective study enrolled 248 patients with pathologically confirmed HCC from two independent medical centers. Patients from Center 1 were randomly allocated to a training set (n = 93) and an internal validation set (n = 41) at a 7∶3 ratio, while patients from Center 2 served as an independent external test set (n = 114). The endpoint was MVI status (positive vs. negative). Body composition parameters were measured on non-contrast CT images, and parameters associated with HCC-MVI were selected using univariate and multivariate logistic regression analyses. Subsequently, on portal venous phase CT images, the tumor region was segmented, and multiple concentric regions were generated by expanding outward from the tumor boundary at 2-mm intervals (4-14 mm), resulting in a total of 13 regions of interest (ROIs) grouped into three categories: tumor region, peritumoral region, and combined tumor-peritumoral region. Radiomics features were extracted from these ROIs. Optimal feature subsets were constructed using multiple feature selection methods, and corresponding radiomics models were built using a support vector machine (SVM) classifier. The SHAP (SHapley Additive exPlanations) method was employed to visualize the contribution of features in the better-performing models. Finally, an individualized prediction model was constructed by integrating selected body composition parameters and the radiomics models. Results Among the multi-regional radiomics models constructed, the ROI12 model (combined tumor and 12 mm peritumoral region) demonstrated optimal performance across all datasets, with AUC values of 0.918 (95% CI: 0.862-0.974), 0.841 (95% CI: 0.720-0.961), and 0.790 (95% CI: 0.707-0.872) in the training, internal validation, and external test sets, respectively. SHAP analysis revealed the importance of features included in this model. The body composition parameter model, comprising subcutaneous fat area and visceral fat area, achieved AUC values of 0.775 (95% CI: 0.682-0.868), 0.686 (95% CI: 0.524-0.849), and 0.764 (95% CI: 0.678-0.850), respectively. The integrated model significantly outperformed the single models in the training set, internal validation set, and external test set (all P < 0.05 by DeLong's test), with AUC values of 0.949 (95% CI: 0.906-0.993), 0.922 (95% CI: 0.838-1.000), and 0.868 (95% CI: 0.803-0.932), respectively. A nomogram was developed for visualization. Calibration curves and decision curve analysis demonstrated good predictive consistency and clinical utility across all datasets. Conclusion Across multiple centers, the individualized prediction model integrating tumor, peritumoral, and body composition parameters effectively predicts the presence of MVI in HCC, supporting precision medicine in clinical practice.

Objective To investigate the clinical utility of high-resolution magnetic resonance imaging (HR-MRI) scoring in assessing pathological differentiation, lymph node metastasis, and perineural invasion in elderly patients with rectal cancer. Methods A retrospective analysis was conducted on 184 elderly rectal cancer cases treated, including 116 males and 68 females (male-to-female ratio 1.71∶1), aged 60-89 years with a mean age of （70.39 ± 6.26） years. Body mass index (BMI) ranged from 14.88 to 39.96 kg/m², with a mean of （23.01 ± 3.42） kg/m². Seventy patients had a smoking history, 62 had a drinking history, 78 had hypertension, and 30 had diabetes. Tumor staging distribution was as follows: T1, 11 cases; T2, 34 cases; T3, 130 cases; and T4, 9 cases. Tumor differentiation included 2 cases of well differentiation, 150 cases of moderate differentiation, and 32 cases of poor differentiation. All patients underwent HR-MRI examination and pathological testing. Baseline clinical data were collected, and the associations between HR-MRI scores, tumor differentiation, and T stage were analyzed. Univariate and multivariate Logistic regression models were used to identify risk factors for lymph node metastasis and perineural invasion, while receiver operating characteristic (ROC) curves were applied to evaluate the diagnostic performance of HR-MRI scores. Results HR-MRI scores showed no significant difference between the moderately-to-well differentiated group and the poorly differentiated group (P>0.05). However, significant differences were observed across T stages (P<0.001), with higher scores in T3 and T4 stages compared with T1 and T2 stages (P<0.008). Pathological examination revealed 66 cases with lymph node metastasis and 118 without. Significant differences between these two groups were found in T stage, tumor differentiation, tumor diameter, vascular invasion, perineural invasion, and HR-MRI score (P<0.05). Logistic regression indicated that vascular invasion was an independent risk factor for lymph node metastasis (P<0.05). ROC analysis showed that with a cutoff value of 2.50 points, HR-MRI scoring yielded a sensitivity of 74.24%, specificity of 65.25%, Youden index of 0.394, and an area under the curve (AUC) of 0.663 (95% CI: 0.582-0.744), suggesting moderate predictive value for lymph node metastasis. Additionally, 51 patients presented with perineural invasion, while 133 did not. Significant differences were found between the two groups in T stage, tumor differentiation, vascular invasion, lymph node metastasis status, and HR-MRI score (P<0.05). Logistic regression analysis demonstrated that T stage and vascular invasion were independent influencing factors for perineural invasion (P<0.05). ROC analysis revealed that with a cutoff value of 2.60 points, the sensitivity, specificity, Youden index, and AUC for predicting perineural invasion were 72.55%, 63.91%, 0.365, and 0.660 (95% CI: 0.575-0.746), respectively, indicating certain predictive significance. Conclusion HR-MRI scores are closely associated with T stage, lymph node metastasis, and perineural invasion in elderly patients with rectal cancer. However, their independent value in predicting the degree of differentiation requires further validation through functional imaging studies.

Objective To investigate the utility of habitat imaging (HI) based on multiparametric magnetic resonance imaging (mpMRI) for the noninvasive prediction of cervical cancer (CC) risk. Methods This retrospective study included 247 patients with pathologically confirmed CC treated. According to the NCCN guidelines and Sedlis criteria, patients were divided into high-risk and low-risk groups. Using simple random sampling, patients were assigned to a training set (n = 173) and a test set (n = 74) at a 7∶3 ratio. Tumor lesions were segmented into k habitat subregions via K-means clustering on integrated mpMRI data, including DCE-MRI and IVIM sequences. Habitat maps were constructed, and the proportion of each subregion was calculated. Logistic regression was employed to identify independent risk factors and to develop clinical (tumor marker), HI-based, and combined clinical-HI predictive models. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). The DeLong test was used to compare differences in model performance. Results Three optimal habitat subregions were identified. DCE-MRI-derived habitats (H1) were defined as follows: H1.1 (high wash-in, high wash-out), H1.2 (high wash-in, low wash-out), and H1.3 (low wash-in, low wash-out). IVIM-derived habitats (H2) included: H2.1 (low f, D, and D^* values), H2.2 (low f, high D and D^* values), and H2.3 (high f and D, low D^* values). In both the training and test sets, the low-risk group exhibited a significantly lower proportion of H1.1 and higher proportions of H1.2 and H2.3 compared with the high-risk group (P < 0.05). Additionally, in the training set, the low-risk group showed a significantly higher proportion of H1.3 and a lower proportion of H2.1 than the high-risk group (P < 0.05). Logistic regression identified SCC-Ag, CA125, and H1.1 as independent risk factors for high-risk CC (OR = 1.074, 1.030, and 3.625; P = 0.031, 0.018, and 0.003, respectively), whereas H2.3 was a protective factor (OR = 0.009, P = 0.024). The combined clinical-HI model achieved the highest predictive performance, with AUCs of 0.814 and 0.818 in the training and test sets, respectively. In the training set, the AUC differed significantly between the clinical model and the clinical-HI model (P = 0.012), and between the clinical model and the clinical-H2.3 model (P = 0.042); however, no significant difference was observed between the clinical-HI model and the HI model. Conclusion The clinical-HI model provides a robust and noninvasive tool for preoperative risk stratification in cervical cancer. By integrating imaging-derived habitat features with clinical biomarkers, this approach enables accurate prediction of tumor risk, offering potential to optimize surgical planning, guide adjuvant therapy, reduce overtreatment, and ultimately improve patient outcomes.

Objective To investigate the diagnostic value of the clear cell likelihood score (ccLS) based on magnetic resonance imaging (MRI) in differentiating clear cell renal cell carcinoma (ccRCC) from non-clear cell renal cell carcinoma (non-ccRCC). Methods We retrospectively analyzed MR imaging data from 119 patients with pathologically confirmed ccRCC and 42 patients with non-ccRCC. Two radiologists independently evaluated all enrolled lesions using the ccLS algorithm and assigned scores ranging from 1 to 5, with final scores determined by consensus. Weighted Kappa statistics were used to assess interobserver agreement. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis, and the area under the curve (AUC) was calculated to determine the optimal diagnostic threshold, accuracy, sensitivity, and specificity. Results In the ccRCC group, 97 (81.5%) lesions were scored ≥4 and 22 (18.5%) were scored <4. In the non-ccRCC group, 35 (83.3%) lesions were scored <4 and 7 (16.7%) were scored ≥4. The two observers demonstrated good agreement in ccLS assessment (weighted Kappa = 0.698, P < 0.001). ROC curve analysis yielded an AUC of 0.915. At a threshold of 4, the ccLS demonstrated optimal diagnostic performance, with an accuracy of 82.0%, sensitivity of 81.5%, and specificity of 83.3% for discriminating ccRCC from non-ccRCC. Conclusion The ccLS exhibits high diagnostic value for differentiating ccRCC from non-ccRCC.

Objective To investigate the value of intratumoral and peritumoral magnetic resonance imaging (MRI)-based radiomics models in the preoperative assessment of parametrial invasion (PMI) in early-stage cervical squamous cell carcinoma. Methods Clinical and MRI data of 162 patients with cervical squamous cell carcinoma were retrospectively collected. Radiomics features were extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). The least absolute shrinkage and selection operator (LASSO) algorithm was employed for feature selection. Intratumoral, peritumoral, and combined intratumoral-peritumoral radiomics signatures were constructed, and radiomics scores (Radscores) were calculated. Clinical, radiomics, and combined models were developed by incorporating independent clinical predictors. Model performance was evaluated using receiver operating characteristic (ROC) curves, cross-validation, calibration curves, and decision curve analysis (DCA). Results Maximum tumor diameter (MTD) and squamous cell carcinoma antigen (SCC-Ag) were identified as independent clinical predictors of PMI. ROC curve analysis demonstrated that the combined model achieved an area under the curve (AUC) of 0.898, which was superior to that of the intratumoral model (0.819), the peritumoral model (0.838), the intratumoral-peritumoral radiomics model (0.851), and the clinical model (0.762). Cross-validation and calibration curves indicated good model stability and calibration. DCA revealed that the combined model provided the highest net benefit in clinical decision-making. A web-based nomogram was developed based on the combined model to facilitate clinical application. Conclusion The combined model integrating intratumoral and peritumoral MRI radiomics with clinical factors can effectively predict PMI in early-stage cervical squamous cell carcinoma, potentially providing reference for preoperative risk stratification and individualized treatment.

Objective To address the inefficiency and subjectivity of manual segmentation of knee cartilage,this study aimed to develop an automated segmentation model based on deep learning to enhance the accuracy and efficiency of early osteoarthritis(OA)diagnosis. Methods A spatial attention-enhanced Res-nnUNet model was proposed,which integrates residual connections and gated attention mechanisms to optimize feature fusion.The model was trained and validated using the SK10 public database(800 cases)and a clinical single-center dataset(249 knee MRI cases with T₁WI/PD sequences).A gold standard was established through double-blind labeling. Results On the test set,Res-nnUNet achieved a mean Dice similarity coefficient(DSC)of 89.0%,significantly outperforming comparison models(U-Net:77.9%,nnUNet:85.3%,ResUNet:79.7%;all P<0.01).The DSCs for femoral and tibial cartilage were(77.0±0.86)% and(84.7±1.30)%,respectively,with lower standard deviations compared with other models.Visualization demonstrated accurate identification of the femoral trochlear groove(error<0.5 mm)and thin posterior tibial plateau cartilage(Hausdorff distance 1.58 mm). Conclusion By leveraging spatial attention mechanisms,Res-nnUNet improves the segmentation accuracy and stability of fine cartilage structures.It provides a reliable automated tool for early quantitative assessment of OA and shows significant clinical potential.

Objective To investigate the clinical manifestations and MRI characteristics of neonatal subpial hemorrhage(SPH),providing imaging evidence for early diagnosis. Methods Clinical data and MRI findings of 14 neonates with SPH confirmed at Henan Provincial People's Hospital from January 2017 to July 2024 were retrospectively analyzed. Results A total of 14 neonates with SPH were included, comprising 10 term infants(≥37 weeks,71.4%)and 4 preterm infants(<37 weeks,28.6%).MRI demonstrated localized subpial hemorrhage in all cases:solitary lesions in 11(78.6%)and multiple lesions in 3(21.4%).Lesions were located in the temporal lobe(6 cases,42.9%),occipital lobe(4 cases,28.6%),frontal lobe(2 cases,14.3%),and cerebellum(2 cases,14.3%).The lesions typically appeared oval or irregular,closely apposed to the cerebral cortex with clear demarcation from adjacent cerebrospinal fluid and brain parenchyma.Compression of the underlying parenchyma was observed;the“yin-yang sign”was present in 12 cases(85.7%)and the“sandwich sign”in 2 cases(14.3%).Based on the presence or absence of parenchymal infarction adjacent to the SPH lesion,patients were categorized into a non-infarction group(n=10,71.4%)and an infarction group(n=4,28.6%).The proportion of temporal-lobe involvement was significantly higher in the infarction group than in the non-infarction group(100% vs. 20%,P=0.015). Conclusion Neonatal SPH exhibits characteristic MRI features.Localized subpial hemorrhage accompanied by the “yin-yang sign”is valuable for identifying SPH.Temporal-lobe involvement is statistically associated with infarction-type SPH (types B/C),suggesting that enhanced assessment of adjacent parenchymal ischemic changes is warranted when lesions are located in the temporal lobe.

Objective To investigate the risk factors for hemoptysis recurrence in lung cancer patients with massive hemoptysis after interventional hemostatic surgery,and to construct and validate a prediction model,thereby providing a reference for clinical risk assessment and intervention strategies. Methods Clinical data of 362 lung cancer patients with massive hemoptysis who underwent interventional hemostatic surgery at the Second Affiliated Hospital of Navy Medical University from January 2023 to August 2025 were retrospectively collected.The patients were randomly allocated to a training set(n=254)and a validation set(n=108) at a 7∶3 ratio using a random number table.Both sets were further divided into recurrence and non-recurrence groups according to postoperative hemoptysis recurrence status.General data,tumor characteristics,surgical parameters,and laboratory indicators were collected and compared.LASSO regression was used to screen potential predictive factors,followed by multivariate Logistic regression to identify independent risk factors and construct a prediction model,which was visualized using a nomogram.The model's discrimination,calibration,and clinical utility were assessed using receiver operating characteristic(ROC)curves,calibration curves,and decision curve analysis(DCA). Results The hemoptysis recurrence rate in the training set was 25.59%(65/254).Multivariate analysis identified TNM stage,maximum tumor diameter,prothrombin time(PT),C-reactive protein(CRP),albumin(ALB),and creatinine(Cr)as independent risk factors for postoperative hemoptysis recurrence(all P<0.05).The prediction model based on these factors achieved an area under the curve(AUC)of 0.787(95%CI:0.723-0.851)in the training set and 0.738(95%CI:0.666-0.810)in the validation set.The Hosmer-Lemeshow goodness-of-fit test indicated good calibration in both the training set (χ²=2.851,P=0.094)and the validation set(χ²=4.126,P=0.127),with calibration curves fitting well against the ideal line(all P>0.05).DCA demonstrated a positive net clinical benefit within a threshold probability range of 0.05-0.80. Conclusion The prediction model constructed in this study demonstrates good predictive performance and clinical applicability for hemoptysis recurrence after interventional surgery in lung cancer patients.It can be used to identify high-risk patients and guide individualized interventions,thereby helping to reduce the risk of postoperative hemoptysis recurrence.

Objective To investigate the association between abdominal fat indexes measured by quantitative CT(QCT)and white matter hyperintensities(WMH)in patients with type 2 diabetes mellitus(T2DM),and to evaluate their diagnostic value. Methods CT and MRI data of 247 patients with T2DM were retrospectively analyzed.According to cranial MRI findings,subjects were divided into no-WMH,mild-WMH,and moderate-to-severe WMH groups.QCT software was used to measure subcutaneous fat area(SFA),visceral fat area(VFA),total fat area(TFA),and the ratio of VFA to SFA(VFA/SFA)at the L₃ vertebral level.Differences among groups were compared.Multivariate Logistic regression was used to identify independent influencing factors for WMH.Receiver operating characteristic(ROC)curves were constructed to analyze the predictive efficacy of single and combined indicators for the occurrence and severity of WMH. Results Age,duration of T2DM,history of hypertension,glycated hemoglobin A1c(HbA1c),homeostasis model assessment for insulin resistance(HOMA-IR),VFA,TFA,and VFA/SFA were significantly higher in the WMH group than in the non-WMH group(all P<0.05).Age,body mass index(BMI),HbA1c,fasting plasma glucose(FPG),homocysteine(HCY),HOMA-IR,VFA,TFA,and VFA/SFA were significantly higher in the moderate-to-severe WMH group than in the mild WMH group(all P<0.05).Multivariate Logistic regression analysis showed that age,duration of T2DM,HbA1c,history of hypertension,and VFA were independent influencing factors for WMH.ROC curve analysis showed that for predicting WMH,the AUCs for VFA,VFA/SFA,HbA1c,and their combination were 0.744,0.733,0.652,and 0.781,respectively;sensitivities were 76.4%,91.2%,48.0%,and 78.4%,respectively;and specificities were 67.7%,49.5%,78.8%,and 67.7%,respectively.For predicting moderate-to-severe WMH,the corresponding AUCs were 0.736,0.709,0.692,and 0.818;sensitivities were 87.0%,88.4%,53.6%,and 79.7%;and specificities were 48.1%,41.8%,77.2%,and 70.9%,respectively. Conclusion sVFA measured by QCT is independently associated with the occurrence and severity of WMH in patients with T2DM.The combined indicators of VFA,VFA/SFA,and HbA1c demonstrate good diagnostic value for predicting the occurrence and severity of WMH in these patients.

Objective To investigate the imaging characteristics of malignant transformation in adult sacrococcygeal teratomas and to improve clinical diagnostic accuracy. Methods A retrospective analysis was performed on CT and MRI data from 18 adults with pathologically confirmed malignant transformation of sacrococcygeal teratoma.The morphological features and functional imaging characteristics were systematically evaluated and summarized. Results Morphological analysis revealed mixed cystic-solid lesions in 15 cases(83.3%,15/18),solid lesions in 2 cases(11.1%,2/18),and purely cystic lesions in 1 case(5.6%,1/18).Ill-defined margins were observed in 14 cases(77.8%,14/18).Regarding composition,typical fat components or calcifications were present in 9 cases(50.0%,9/18).Indicators suggestive of malignancy included ill-defined margins in 14 cases(77.8%,14/18),hyperintensity on diffusion-weighted imaging(DWI)in all 14 cases with ill-defined margins(100%),heterogeneous marked enhancement of solid/mixed cystic-solid components on contrast-enhanced scans in 13 cases(92.9%,13/14),and enhancement of septations and cyst walls in 1 cystic case(7.1%,1/14).Associated malignant manifestations included destruction of the sacrum and coccyx(27.8%,5/18)and pelvic/inguinal lymph node metastasis or peritoneal thickening(38.9%,7/18). Conclusion Malignant transformation in adult sacrococcygeal teratomas demonstrates characteristic imaging features in lesion composition,morphological characteristics,and functional imaging.Accurate recognition of these features provides an important basis for clinical formulation of individualized treatment plans.