This study aimed to identify preoperative metabolic and radiological predictors of adherent perinephric fat (APF) and to develop a predictive scoring system for its assessment. We conducted a prospective study of consecutive patients with renal tumors undergoing open or minimally invasive partial nephrectomy (PN). APF was intraoperatively defined as the need for subcapsular renal dissection to isolate the tumor. Patient characteristics were compared according to APF presence. Multivariable logistic regression analysis was performed, and the resulting model was used to develop a predictive scoring system. A total of 200 patients were included in the analysis, of whom 34 (17%) had APF. On multivariable analysis, presence of perinephric fat stranding (p = 0.003), posterior perinephric fat thickness ≥ 25 mm (p < 0.001), serum urea ≥ 33 mg/dl (p = 0.004), albumin ≤ 4.3 g/dl (p = 0.007), and HDL cholesterol ≤ 53 mg/dl (p = 0.019) were predictors of APF. A model incorporating these five variables achieved an area under the receiver operating characteristic curve of 0.92. These parameters were subsequently integrated into the novel SHARP-U (Stranding, HDL cholesterol, Albumin, Renal Perinephric fat thickness, Urea) score, ranging from 0 to 7, to predict the presence of APF. The SHARP-U score provides a simple and reliable tool for preoperative prediction of APF in patients undergoing partial nephrectomy. Early identification of individuals at risk may aid surgical planning and patient counseling. External prospective validation of the SHARP-U score is warranted to confirm its clinical applicability.

Development and validation of a machine learning model based on interpretable clinical characteristics for preoperative prediction of Ki-67 expression in pituitary adenomas.

Accurate preoperative identification of muscle-invasive bladder cancer (MIBC) is critical for clinical decision-making but remains challenging. In this study, we aimed to develop and validate a novel predictive model that integrates contrast-enhanced ultrasound (CEUS) radiomics features with the Vesical Imaging Reporting and Data System (VI-RADS) score to improve the preoperative discrimination of MIBC. In this retrospective, single-center study, we enrolled 116 consecutive patients with pathologically confirmed bladder tumor who underwent pre-operative CEUS between May 2015 and October 2024. Patients were randomly allocated to training and validation cohorts in a 7:3 ratio. The CEUS frame at peak tumor enhancement was selected for analysis. Tumors were manually segmented on the largest cross-sectional plane using 3D-Slicer to generate regions of interest. Radiomic features were extracted using PyRadiomics. After sequential feature reduction and model selection, radiomic predictors were integrated with clinically significant variables to construct a combined model. Three CEUS radiomic features were identified as relevant to MIBC. Among clinical variables, the VI-RADS score (P=0.04, odds ratio 1.89) was independently associated with MIBC. Of the five evaluated classifiers, XGBoost achieved the best performance for both the radiomic (area under the curve 0.86) and the combined (area under the curve 0.96) models. Finally, SHapley Additive exPlanations analysis was performed to interpret the model, and calibration curves and decision curve analysis were employed to evaluate its accuracy and clinical utility. This study developed and conducted preliminary validation of a model integrating CEUS radiomics and the VI-RADS score, demonstrating its feasibility and potential for preoperative MIBC prediction.

Noninvasive preoperative prediction of perineural invasion in intrahepatic cholangiocarcinoma based on dynamic contrast-enhanced MRI.

Predictors associated with failing to achieve a patient-acceptable symptom state in the Oxford Knee Score following total knee arthroplasty.

Integrating lesser omentum adipose CT in dual-phase tumor imaging: A multi-label deep learning framework for preoperative microvascular invasion prediction and survival analysis in hepatocellular carcinoma.

Differentiating between sparsely granulated and densely granulated somatotroph tumors (SGSTs and DGSTs) currently relies on postoperative immunohistochemistry. This study aimed to evaluate whether triglyceride (TG), uric acid (UA), and their composite TG-UA index [ln(TG × 1000/UA)] could serve as preoperative indicators for distinguishing granulation subtypes of somatotroph tumors. In this multicenter retrospective cohort study, 230 patients with somatotroph tumors were analyzed. Logistic regression and generalized additive models assessed associations and potential nonlinear associations between metabolic indicators and granulation subtypes. Predictive performance was compared between models using UA and TG separately and those using the TG-UA index. SGSTs were associated with significantly higher TG, growth hormone, insulin-like growth factor 1, and TG-UA index values. The TG-UA index remained an independent predictor of the SGST subtype (OR = 1.514, p = 0.014). Predictive performance was similar between models (p = 0.108). The TG-UA index is a promising noninvasive biomarker for identifying the SGST subtype in somatotroph tumors. Although limited by its retrospective design and lack of long-term data, this study provides a foundation for future prospective validation.

The overarching prognostic role of tumor progression prior to cytoreductive hepatectomy in NETLM.

Preoperative prediction of rectal cancer stage via CT imaging and an adaptive attention multiscale feature fusion network

Tumor and Perirenal Adipose Tissue Radiomic Models for Pathological T-Stage Prediction and Biological Exploration in Clear Cell Renal Cell Carcinoma.

Knowledge-guided gadolinium-free MRI radiomics predict 1p/19q co-deletion in IDH-mutant adult-type diffuse gliomas: A dual-center study.

Prediction of pathological risk factors in rectal cancer using combined extracellular volume fraction from T1 mapping and apparent diffusion coefficient.

Multiperspective tumor heterogeneity metrics for preoperative prediction of IASLC grading in clinical stage IA lung adenocarcinomas: A multicenter study.

Objective This study aimed to develop an explainable fusion model that integrates intratumoral, peritumoral, and habitat features derived from MRI to evaluate its feasibility for predicting the WHO/ISUP nuclear grade of clear cell renal cell carcinoma (ccRCC). Methods We retrospectively enrolled 154 patients with pathologically confirmed ccRCC and partitioned them into a training set (n = 108) and an independent test set (n = 46). On contrast-enhanced T1-weighted images, regions of interest were manually delineated layer-by-layer along the tumor margin and expanded outward by 1 mm, 2 mm, 3 mm, 4 mm and 5 mm to derive peritumoral regions. Tumor habitat regions were identified using the K-means clustering algorithm. After extraction and selection of radiomic features, radiomics and habitat models were constructed using five machine learning algorithms. These effective features were then integrated into a nomogram. Model performance was assessed by plotting receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC). Model calibration and clinical utility were evaluated using calibration curves and decision curve analysis (DCA). Model interpretability was enhanced by employing Shapley Additive exPlanations (SHAP). Results Three habitat subregions were identified within tumors. The integrated habitat region(Habitat) model demonstrated the highest performance among the evaluated habitat models, with AUCs of 0.894 and 0.877 in the training and test sets, respectively. The Peri2mm model achieved AUCs of 0.884 and 0.839, outperforming other peritumoral ranges. Therefore, the 2-mm peritumoral margin was considered a potentially optimal analysis range in this cohort.When the integrated habitat region signature was combined with intratumoral features, 2-mm peritumoral features and the independent clinical predictor (corticomedullary enhancement level) in a nomogram, predictive performance was further improved, achieving AUCs of 0.934 and 0.912. SHAP bee swarm and force plots provided intuitive visualization of the habitat model’s decision-making process. Conclusion The nomogram, which integrates intratumoral, peritumoral and habitat radiomic features derived from MRI, demonstrated excellent performance for noninvasive preoperative prediction of WHO/ISUP nuclear grade in ccRCC and holds promise as an adjunctive tool for individualized therapy planning and prognostic assessment. However, its clinical application requires further external validation.

Small gastrointestinal stromal tumors (SGISTs, maximum diameter≤2 cm) still carry a risk of malignancy, and their preoperative evaluation remains a significant challenge. Radiomics, an emerging technique for analyzing image data, has yet to be employed to assess the risk stratification of SGISTs. To develop and validate a CT radiomics model for the preoperative prediction of risk stratification in patients with SGISTs. This study enrolled 133 patients with SGISTs, including 97 in the low-grade group and 36 in the high-grade group. Patients were randomly assigned to a training set (n = 93) and a testing set (n = 40) at a ratio of 7:3. Radiomics features were extracted from preoperative CT images, and dimensionality reduction was performed using the LR-LASSO to identify the most predictive features for constructing the radiomics model. Clinical features were evaluated using univariate and multivariate logistic regression analyses to develop a clinical model. Subsequently, the optimal radiomics and clinical features were integrated to establish a combined model. Model performance was evaluated using ROC curve analysis, and a corresponding nomogram was generated to facilitate clinical application. The Delong test was used to compare the ROC curves, with a p-value < 0.05 considered statistically significant. Univariable clinical analysis identified maximal tumour diameter as the only significant predictor, with the clinical model achieving an AUC of 0.641 (95% CI: 0.533-0.748). Among the radiomics signatures derived from multiphase CT (non-contrast to delayed phases), the model based on portal venous phase images demonstrated the highest discriminative ability, yielding the best AUC values in both the training set (AUC = 0.848, 95% CI: 0.764-0.931) and the testing set (AUC = 0.824, 95% CI: 0.696-0.953). The combined model, which integrated radiomics features with maximum tumour diameter, demonstrated improved performance, attaining an AUC of 0.862 (95% CI: 0.743-0.975) in the training set and 0.859 (95% CI: 0.743-0.975) in the testing set. Notably, the predictive performance of both the radiomics and combined models was significantly greater than that of the clinical model (DeLong test, P < 0.05). However, no statistically significant differences were observed between the AUC values of the radiomics and combined models. Calibration curves indicated a good fit, and the DCA demonstrated that both the radiomics model and the combined model provided greater clinical benefits. The radiomics model demonstrated superior performance to the clinical model for the preoperative prediction of risk stratification in SGISTs. As a visualization tool, the nomogram of the combined model plays a critical role in optimizing early surgical resection decisions. The radiomics model could serve as an effective tool for non-invasive risk stratification of SGISTs, offering clear advantages over risk stratification models based solely on conventional clinical parameters. This approach could support improved preoperative clinical decisionmaking.

ObjectiveDeep learning signatures (DLS) extracted from CT images can noninvasively reflect tumor heterogeneity and have shown promise in prognostic modeling for esophageal squamous cell carcinoma (ESCC). To develop and validate a CT-based DL model combined with nutritional biomarkers to predict 3-year overall survival (OS) in ESCC, and to investigate transcriptomic differences between DLS-based risk groups.Materials and methodsThis retrospective multicenter study included 662 postoperative ESCC patients from three hospitals and 16 additional patients from The Cancer Genome Atlas (TCGA). DL features extraction from CT images based on the Crossformer architecture. Skeletal muscle index was measured at the L3 vertebra to assess low skeletal muscle mass (LSMM). Cox regression was used to build clinical, DL, and combined models. Model performance was evaluated using the concordance index (C-index). Transcriptomic analysis of the TCGA cohort was performed to identify metabolic pathway differences between DLS-based risk groups.ResultsThe DL model achieved a C-index of 0.743 (95% CI: 0.683–0.803) in the internal validation cohort and 0.692 (95% CI: 0.576–0.809) in the external cohort. Pathological T and N stages, Neuroaggression, Vascular invasion, and LSMM were identified as independent clinical predictors. The combined model achieved a C-index of 0.753 (95% CI: 0.697–0.808) internally and 0.725 (95% CI: 0.613–0.838) externally. DLS–based risk stratification revealed significant differences in metabolic activity between groups, supporting its biological relevance.ConclusionThe combined model enables preoperative OS prediction in ESCC. DLS–based stratification reflects transcriptomic metabolic heterogeneity and enhances the biological interpretability of imaging features.Critical relevance statementThis study developed a CT-based DLS and combined it with nutritional markers for prognostic modeling in ESCC. Transcriptomic analysis of DLS-based groups revealed metabolic heterogeneity, enhancing the biological interpretability of the DL model.Key PointsA combined DLS and nutritional model enables individualized preoperative survival prediction in ESCC.DLS-based risk groups defined by the DLS exhibited transcriptomic differences in key metabolic pathways, revealing biological underpinnings of imaging-based phenotypes.Attention map visualization revealed consistent spatial focus on morphologically distinct tumor regions, enhancing the interpretability of deep learning predictions.Graphical

This systematic review and meta-analysis evaluated the diagnostic performance of artificial intelligence (AI) models that analyze preoperative prostate MRI images in conjunction with clinical parameters for predicting extraprostatic extension (EPE) in prostate cancer. A comprehensive search of PubMed, Embase, and Web of Science up to July 2025 identified 14 eligible studies involving 2,131 patients. The pooled analysis demonstrated that integrated radiomics-clinical models achieved high diagnostic performance, with a sensitivity of 0.83 (95% CI: 0.78-0.87), specificity of 0.82 (95% CI: 0.77-0.86), and an area under the curve (AUC) of 0.89 (95% CI: 0.86-0.92). The diagnostic odds ratio (DOR) was 19.82 (95% CI: 12.33-31.86), indicating robust discrimination between EPE-positive and EPE-negative cases. Subgroup analysis suggested models using deep learning algorithms had marginally higher accuracy (DOR: 24.6) than those using traditional machine learning (DOR: 17.3), though the difference was not statistically significant. Heterogeneity among studies stemmed from variations in MRI protocols, segmentation methods, and modeling approaches. No significant publication bias was detected. The results affirm that integrating radiomic features from multiparametric MRI (e.g., T2-weighted, diffusion-weighted imaging) with clinical variables (e.g., PSA, Gleason score) significantly outperforms conventional assessments for preoperative EPE prediction, demonstrating excellent diagnostic accuracy and supporting its potential clinical application in risk stratification. This supports the potential of combined models to enhance risk stratification and guide personalized surgical planning. Future research should prioritize standardized radiomics workflows, external validation, and multi-center collaborations to facilitate clinical adoption.

Gastric cancer staging is frequently limited by the low sensitivity of routine imaging for occult peritoneal metastasis (OPM), necessitating invasive staging laparoscopy. We developed a Multimodal Model, integrating primary tumor radiomics from CT with clinical factors to non-invasively predict OPM in locally advanced gastric cancer. The model was trained and internally validated in a large cohort (n = 940) and externally validated across two independent multi-center cohorts (n = 309), an incremental cohort (n = 477), and a prospective clinical trial cohort (n = 168). In all cohorts, the model achieved robust performance (AUCs: 0.834-0.857), significantly outperforming single-modality models. Crossover validation showed AI assistance increased the average radiologist AUC from 0.735 to 0.872. Transcriptomic analysis revealed that the model’s low-risk stratification correlated with an enhanced antitumor immune microenvironment (CD8 T cells, TNFα signaling). This validated model provides a practical tool for accurate, non-invasive OPM prediction and individualized treatment planning.

ObjectivesWaiting for postoperative pathologic confirmation of visceral pleural invasion (VPI) may delay treatment decisions. This study aimed to develop a contrast-enhanced CT-based radiomics model for preoperative prediction of VPI in early-stage non-small cell lung cancer (NSCLC).Materials and methodsWe retrospectively enrolled 523 surgically resected NSCLC patients (195 with VPI, 328 without VPI) with clinically staged IA based on preoperative imaging between December 2019 and June 2022. Patients were randomly divided into training, validation, and testing sets at a ratio of 5:2:3. For each patient, 13 CT features were recorded, including the types I–V tumor relationships to the pleura. Regions of interest (ROIs) were segmented semi-automatically using deep learning. Least absolute shrinkage and selection operator (LASSO) regression was applied to select key radiomics features. Three models were developed: a CT-feature model, a radiomics model, and a combined model. The performance and clinical utility of these models were evaluated using the area under the curve (AUC) and decision curve analysis.ResultsThe tumor relationship to the pleura, density, maximum diameter, and spiculation were selected to construct the CT-feature model. A total of 10 optimal features formed the radiomics model. The radiomics model achieved an AUC of 0.812 in the testing set, outperforming the CT-feature model (0.714). Furthermore, the combined model showed a slightly higher AUC (0.825) compared to the radiomics model.ConclusionsThe radiomics model demonstrated satisfactory performance for predicting VPI in early-stage NSCLC, outperforming the CT-feature model. The integration of radiomics and CT features may provide enhanced predictive value.Critical relevance statementThis study constructed a contrast-enhanced CT-based radiomics model with promising performance for the preoperative prediction of VPI, which aims to guide treatment planning for early-stage NSCLC.Key PointsVPI affects the tumor-node-metastasis (TNM) staging of tumors and subsequent treatment strategies.The radiomics model outperformed the CT-feature model in predicting VPI.The contrast-enhanced CT-based radiomics model may be valuable for optimizing clinical decision-making.Graphical

Lung neuroendocrine neoplasms (L-NENs) are increasingly recognized, yet reliable preoperative assessment of the Ki-67 proliferation index remains invasive and subject to sampling variability. We aimed to develop and validate a clinical-radiomics nomogram that uses routine chest CT to estimate Ki-67 status in patients with L-NENs. In this retrospective multicenter study, 199 patients with histologically confirmed L-NENs from four hospitals between January 2014 and April 2024 were enrolled, all of whom underwent preoperative dual-phase contrast-enhanced CT. Following manual 3D tumor segmentation, a total of 1,874 radiomics features were extracted from fused non-contrast and arterial/venous phase images. Feature selection was performed using Pearson correlation analysis (removing redundant features with correlation coefficients > 0.8), followed by further variable compression via LASSO regression to identify discriminative radiomics features. Based on the selected features, five classification models were constructed, and the best-performing one was combined with clinical predictors identified through univariate and multivariate analyses to develop a radiomics-based nomogram. The model's discriminative ability, calibration, and clinical utility were evaluated in the training set (n = 116), internal test set (n = 50), and external validation set (n = 33) using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA), respectively. The LR-based radiomics model demonstrated high discriminatory ability, achieving AUCs of 0.912 (95% CI: 0.858-0.965) in the training set and 0.943 (0.887-0.999) in the testing set, significantly outperforming other models. Consequently, it was combined with independent clinical predictors-largest tumor diameter, smoking history, and age-to build a nomogram. The final combined model exhibited excellent performance across all datasets, with AUCs of 0.958 (0.925-0.990) in training, 0.930 (0.865-0.995) in testing, and 0.911 (0.867-0.955) in external validation, accompanied by good calibration and a superior net benefit on decision curve analysis. The CT-based clinical-radiomics nomogram provides an accurate, non-invasive tool for pre-operative Ki-67 estimation in L-NENs, potentially guiding treatment decisions. Prospective, larger-scale validation is warranted. Not applicable.