Preoperatively Predicting Risk Stratification for GISTs ≤2 cm by Radiomics Model: A Dual-center Study.

The preoperative identification of cervical lymph node metastasis in papillary thyroid carcinoma is essential in tailoring surgical treatment. We aim to develop an ultrasound-based handcrafted radiomics model, a deep learning radiomics model, and a combined model for better predicting cervical lymph node metastasis in papillary thyroid carcinoma patients. A retrospective cohort of 441 patients was included (308 in the training set, 133 in the testing set). Handcrafted radiomics features, manually selected by physicians, were extracted using Pyradiomics software, whereas deep learning radiomics features were extracted from a pretrained DenseNet121 network, a fully automatic process that eliminates the need for manual selection. A combined model integrating radiomics signatures from the above models was developed. ROC analysis was used to evaluate the performance of three models. DeLong's tests were conducted to compare the AUC values of the different models in the training and testing sets. In the training set, the AUC value of the combined model (0.790) was significantly higher than that of the handcrafted radiomics (0.743, p = 0.021) and deep learning radiomics (0.730, p = 0.003) models. In the testing set, although the AUC value of the combined model (0.761) was higher than that of the handcrafted radiomics model (0.734, p = 0.368) and deep learning radiomics model (0.719, p = 0.228), statistical significance was not reached. The handcrafted radiomics model exhibited high accuracy in both the training and testing sets (0.714 and 0.707), while the deep learning radiomics model showed accuracy below 0.7 in both the training and testing sets (0.698 and 0.662). The combined model based on conventional ultrasound images enhances the predictive performance compared to different radiomics models alone.

ObjectiveTo evaluate the utility of combining unenhanced and contrast-enhanced CT intratumoral and peritumoral radiomic features with clinical variables for distinguishing benign from malignant parotid gland tumors.MethodsWe retrospectively collected clinical and imaging data from 171 patients with pathologically confirmed parotid gland tumors treated at Baoding First Central Hospital between June 2019 and June 2025 (101 benign, 70 malignant). Tumor ROIs were manually delineated slice-by-slice on non-contrast, arterial-phase and venous-phase CT images, and peritumoral regions were automatically expanded by 1–4 mm. The cohort was randomly split into training and test sets at a 7:3 ratio. After extraction and selection of radiomic features, multiple models were constructed for intratumoral, various peritumoral ranges (1–4 mm) and intratumoral+peritumoral combinations. Model performance was evaluated by ROC curves, the optimal radiomics model was selected and integrated with the clinical model to produce a combined model, and a nomogram was subsequently developed.ResultsThe AUC values of the intratumoral, peritumoral (1–4 mm) and intratumoral+peritumoral models in the training set were 0.966, 0.953, 0.927, 0.983, 0.947, 0.959, 0.956, 0.909 and 0.976, respectively; in the test set the AUCs were 0.797, 0.766, 0.791, 0.714, 0.710, 0.805, 0.836, 0.778 and 0.753, respectively. According to the DeLong test, in the training set the differences between intratumor+peritumor 3mm vs. peritumor 3mm and between intratumor+peritumor 3mm vs. intratumor+peritumor 4mm were statistically significant (p = 0.022 and p = 0.026, respectively); in the test set, differences among the models were not statistically significant (P > 0.05). From this, it can be seen the combined intratumoral + 2 mm peritumoral radiomics model demonstrated superior diagnostic performance compared to models based exclusively on either intratumoral or peritumoral features. Consequently, this model was designated as the optimal radiomic signature and was integrated with independent clinical risk factors—specifically symptomatology and tumor margin status—to construct a combined clinical–radiomics predictive model. In the training and test sets, the AUC values of the radiomics model were 0.956 and 0.836, respectively, while those of the clinical model were 0.774 and 0.703. The combined model achieved AUC values of 0.974 and 0.844, demonstrating significantly superior diagnostic performance compared to the standalone clinical or radiomics models, along with the highest clinical utility. According to the Delong test, in the training set the differences between the clinical model and the combined model, and between the clinical model and the radiomics model, were statistically significant (p = 0.000 and p = 0.000, respectively); in the test set, differences among the models were not statistically significant (P > 0.05).ConclusionA multiphase CT radiomics approach that fuses intratumoral features with a 2 mm peritumoral zone robustly distinguishes benign from malignant parotid gland tumors. Integration with key clinical predictors further enhances diagnostic accuracy, supporting clinical translation of the combined model for noninvasive tumor characterization.

The present study aimed to develop and validate a fusion model based on multi-phase contrast-enhanced computed tomography (CECT) radiomics features combined with clinical features to preoperatively predict the expression levels of Ki-67 in patients with gastric cancer (GC). A total of 164 patients with GC who underwent surgical treatment at our hospital between September 2015 and September 2023 were retrospectively included and were randomly divided into a training set (n=114) and a testing set (n=50). Using Pyradiomics, radiomics features were extracted from multi-phase CECT images and were combined with significant clinical features through various machine learning algorithms [support vector machine (SVM), random forest (RandomForest), K-nearest neighbors (KNN), LightGBM and XGBoost] to build a fusion model. Receiver operating characteristic, area under the curve (AUC), calibration curve and decision curve analysis (DCA) were used to evaluate, validate and compare the predictive performance and clinical utility of the model. Among the three single-phase models, for the arterial phase model, the SVM radiomics model had the highest AUC value in the training set, which was 0.697; and the RandomForest radiomics model had the highest AUC value in the testing set, which was 0.658. For the venous phase model, the SVM radiomics model had the highest AUC value in the training set, which was 0.783; and the LightGBM radiomics model had the highest AUC value in the testing set, which was 0.747. For the delayed phase model, the KNN radiomics model had the highest AUC value in the training set, which was 0.772; and the SVM radiomics model had the highest AUC in the testing set, which was 0.719. The clinical feature model had the lowest AUC values in both the training set and the testing set, which were 0.614 and 0.520, respectively. Notably, the multi-phase model and the fusion model, which were constructed by combining the clinical features and the multi-phase features, demonstrated excellent discriminative performance, with the fusion model achieving AUC values of 0.933 and 0.817 in the training and testing sets, thus outperforming other models (DeLong test, both P<0.05). The calibration curve showed that the fusion model had goodness of fit (Hosmer-Lemeshow test, >0.5 in the training and validation sets). The DCA showed that the net benefit of the fusion model in identifying high expression of Ki-67 was improved compared with that of other models. Furthermore, the fusion model achieved an AUC value of 0.805 in the external validation data from The Cancer Imaging Archive. In conclusion, the fusion model established in the present study was revealed to have excellent performance and is expected to serve as a non-invasive tool for predicting Ki-67 status and guiding clinical treatment.

BACKGROUND. Habitat imaging provides a novel approach to capture spatial heterogeneity within lesions. OBJECTIVE. The purpose of this study was to develop a ternary-classification habitat model to characterize lung adenocarcinoma presenting as a subsolid nodule (SSN) on CT and to test the model's diagnostic performance compared with 2D and radiomic models. METHODS. This retrospective study included 747 patients (median age, 56 years; 241 men, 506 women) with 834 resected lung adenocarcinomas that presented as SSNs on low-dose CT between July 2018 and July 2023. Adenocarcinomas from one center were divided into training (n = 440) and internal test (n = 189) sets; adenocarcinomas from three other centers formed an external test set (n = 205). Adenocarcinomas were classified as noninvasive adenocarcinoma, grade 1 invasive adenocarcinoma (IAC), or grade 2 or 3 (hereafter, grade 2/3) IAC. Ternary-classification models were built in the training set using multivariable multinomial logistic regression analyses (2D model: diameter and consolidation-to-tumor ratio; habitat model: volume and volume ratio of attenuation-based subregions; radiomic model: extracted radiomic features; combined model: habitat and radiomic features). Performance was evaluated using macroaveraged and class-specific AUCs. RESULTS. The optimal number of habitats was four. The 2D, habitat, radiomic, and combined models had macroaveraged AUCs in the internal test set of 0.857, 0.909, 0.914, and 0.912 and in the external test set of 0.871, 0.919, 0.924, and 0.926, respectively. Those four models had class-specific AUCs in the external test set for noninvasive adenocarcinoma of 0.945, 0.956, 0.961, and 0.955; for grade 1 IAC of 0.792, 0.858, 0.857, and 0.862; and for grade 2/3 IAC of 0.875, 0.940, 0.952, and 0.961, respectively. In the external test set, macroaveraged AUCs and class-specific AUCs for grades 1 and 2/3 IAC were significantly higher for habitat, radiomic, and combined models versus the 2D model, but not for other model comparisons; class-specific AUCs for noninvasive adenocarcinoma were not significantly different for any model comparisons. CONCLUSION. The habitat model performed significantly better than the 2D model in ternary adenocarcinoma classification; its performance was not significantly different from the radiomic and combined models. CLINICAL IMPACT. The habitat model's combination of interpretability and diagnostic performance supports its utility for noninvasive risk stratification of SSNs encountered during lung cancer screening.

This study aims to detect vascular and neural invasion in prostate cancer through MRI, utilize habitat analysis of the tumor microenvironment, construct a radiomic feature model, thereby enhancing diagnostic accuracy and prognostic assessment for prostate cancer, ultimately improving patients' quality of life. We retrospectively collected records of 400 patients with pathologically verified prostate cancer from January to December 2023. We developed a radiomic features model within the tumor habitat using MRI data and identified independent risk factors through multivariate analysis to construct a clinical model. Finally, we assessed the performance of these features using the DeLong test (through the area under the receiver operating characteristic curve, AUC), evaluated the calibration curve with the Hosmer-Lemeshow test, and performed decision curve analysis. In the training set, the optimal algorithm based on the intratumoral heterogeneity score had an AUC value of 0.882 (CI: 0.843-0.921); in the test set, the AUC value was 0.860 (CI: 0.792-0.928). The traditional radiomics model (considering the entire tumor) had an AUC value of 0.761 (CI: 0.695-0.827) in the training set and 0.732 (CI: 0.630-0.834) in the test set. The combined model that integrates habitat scores and Gleason scores had an AUC value of 0.889 (CI: 0.8509-0.9276) in the training set and 0.886 (CI: 0.8183-0.9533) in the test set, outperforming the single models. By deeply analyzing the tumor microenvironment and combining radiomics models, the diagnostic precision and predictive accuracy of vascular and nerve invasion in prostate cancer can be significantly improved. This approach provides a valuable tool for optimizing treatment plans, improving patient prognosis, and reducing unnecessary medical interventions.

Dual-phenotype hepatocellular carcinoma (DPHCC) is highly aggressive and difficult to distinguish from hepatocellular carcinoma (HCC). To develop and validate clinical and radiomics models based on contrast-enhanced MRI for the preoperative diagnosis of DPHCC. Retrospective. A total of 87 patients with DPHCC and 92 patients with non-DPHCC randomly divided into a training cohort (n=125: 64 non-DPHCC; 61 DPHCC) and a validation cohort (n=54: 28 non-DPHCC; 26 DPHCC). A 3.0 T; dynamic contrast-enhanced MRI with time-resolved T1-weighted imaging sequence. In the clinical model, the maximum tumor diameter and hepatitis B virus (HBV) were independent risk factors of DPHCC. In the radiomics model, a total of 1781 radiomics features were extracted from tumor volumes of interest (VOIs) in the arterial phase (AP) and portal venous phase (PP) images. For feature reduction and selection, Pearson correlation coefficient (PCC) and recursive feature elimination (RFE) were used. Clinical, AP, PP, and combined radiomics models were established using machine learning algorithms (support vector machine [SVM], logistic regression [LR], and logistic regression-least absolute shrinkage and selection operator [LR-LASSO]) and their discriminatory efficacy assessed and compared. The independent sample t test, Mann-Whitney U test, Chi-square test, regression analysis, receiver operating characteristic curve (ROC) analysis, Pearson correlation analysis, the Delong test. A P value < 0.05 was considered statistically significant. In the validation cohort, the combined radiomics model (area under the curve [AUC]=0.908, 95% confidence interval [CI]: 0.831-0.985) showed the highest diagnostic performance. The AUCs of the PP (AUC=0.879, 95% CI: 0.779-0.979) and combined radiomics models were significantly higher than that of clinical model (AUC=0.685, 95% CI: 0.526-0.844). There were no significant differences in AUC between AP or PP radiomics model and combined radiomics model (P=0.286, 0.180 and 0.543). MRI radiomics models may be useful for discriminating DPHCC from non-DPHCC before surgery. 4 TECHNICAL EFFICACY: Stage 2.

ObjectiveThis study aims to explore the impact of different ROI delineation strategies on the axillary lymph nodes metastasis (ALNM) prediction model by analyzing two-dimensional ultrasound images of lymph nodes. In addition, we integrated clinical and pathological information to construct a comprehensive model, and based on this model, developed a nomogram for individualized assessment of the probability of ALNM.MethodsA total of 146 axillary lymph nodes were randomly divided into a training set and a testing set at a ratio of 8:2. Clinical and pathological features were selected using univariate and multivariate logistic regression analyses, followed by the construction of a clinical prediction model. Radiomic features were extracted from both the internal and surrounding regions of the two-dimensional ultrasound images of the axillary lymph nodes. The least absolute shrinkage and selection operator (LASSO) algorithm was then used to select and retain the optimal features, followed by the construction of a radiomic prediction model. A combined prediction model was developed by integrating the clinical and radiomic models, and a nomogram was created for the combined prediction model.ResultsThe clinical status of axillary lymph nodes was an independent predictor for metastasis. The clinical prediction model based on the status of axillary lymph nodes achieved an AUC of 0.728 in the testing set. The radiomic prediction model based on the LASSO logistic regression algorithm with a 1 mm extended region had the highest AUC of 0.856 in the testing set. The combined prediction model integrating the clinical and optimal radiomic models achieved an AUC of 0.841 in the testing set, with a sensitivity of 77.4% and an accuracy of 79.5%. This combined model outperformed the individual clinical and radiomic models and was more effective in predicting axillary lymph node metastasis.ConclusionThis study developed a predictive model for ALNM based on ultrasound images of ALNs and their peripheral extended regions. The results demonstrated that the combined model incorporating both the lymph node and a 1-mm peripheral extension yielded the best predictive performance. Furthermore, a comprehensive integrated model was established by incorporating clinical and pathological characteristics, which effectively enhanced the prediction of ALNM.

BackgroundTo develop a predictive nomogram for breast cancer lympho-vascular invasion (LVI), based on digital breast tomography (DBT) data obtained from intra- and peri-tumoral regions.MethodsOne hundred ninety-two breast cancer patients were enrolled in this retrospective study from 2 institutions, in which Institution 1 served as the basis for training (n = 113) and testing (n = 49) sets, while Institution 2 served as the external validation set (n = 30). Tumor regions of interest (ROI) were manually-delineated on DBT images, in which peri-tumoral ROI was defined as 1 mm around intra-tumoral ROI. Radiomics features were extracted, and logistic regression was used to construct intra-, peri-, and intra- + peri-tumoral radiomics models. Patient clinical data was analyzed by both uni- and multi-variable logistic regression analyses to identify independent risk factors for the non-radiomics clinical imaging model, and the combination of both the most optimal radiomics and clinical imaging models comprised the comprehensive model. The best-performing model out of the 3 types (radiomics, clinical imaging, comprehensive) was identified using receiver operating characteristic (ROC) curve analysis, and used to construct the predictive nomogram.ResultsThe most optimal radiomics model was the intra- + peri-tumoral model, and 3 independent risk factors for LVI, maximum tumor diameter (odds ratio [OR] = 1.486, 95% confidence interval [CI] = 1.082–2.041, P = 0.014), suspicious malignant calcification (OR = 2.898, 95% CI = 1.232 ~ 6.815, P = 0.015), and axillary lymph node (ALN) metastasis (OR = 3.615, 95% CI = 1.642–7.962, P < 0.001) were identified by the clinical imaging model. Furthermore, the comprehensive model was the most accurate in predicting LVI occurrence, with areas under the curve (AUCs) of 0.889, 0.916, and 0.862, for, respectively, the training, testing and external validation sets, compared to radiomics (0.858, 0.849, 0.844) and clinical imaging (0.743, 0.759, 0.732). The resulting nomogram, incorporating radiomics from the intra- + peri-tumoral model, as well as maximum tumor diameter, suspicious malignant calcification, and ALN metastasis, had great correspondence with actual LVI diagnoses under the calibration curve, and was of high clinical utility under decision curve analysis.ConclusionsThe predictive nomogram, derived from both radiomics and clinical imaging features, was highly accurate in identifying future LVI occurrence in breast cancer, demonstrating its potential as an assistive tool for clinicians to devise individualized treatment regimes.

Cervical cancer is a leading cause of death from malignant tumors in women, and accurate evaluation of occult lymph node metastasis (OLNM) is crucial for optimal treatment. This study aimed to develop several predictive models—including Clinical model, Radiomics models (RD), Deep Learning models (DL), Radiomics–Deep Learning fusion models (RD-DL), and a Clinical–RD-DL combined model—for assessing the risk of OLNM in cervical cancer patients.The study included 130 patients from Center 1 (training set) and 55 from Center 2 (test set). Clinical data and imaging sequences (T1, T2, and DWI) were used to extract features for model construction. Model performance was assessed using the DeLong test, and SHAP analysis was used to examine feature contributions. Results showed that both the RD-combined (AUC = 0.803) and DL-combined (AUC = 0.818) models outperformed single-sequence models as well as the standalone Clinical model (AUC = 0.702). The RD-DL model yielded the highest performance, achieving an AUC of 0.981 in the training set and 0.903 in the test set. Notably, integrating clinical variables did not further improve predictive performance; the Clinical–RD-DL model performed comparably to the RD-DL model. SHAP analysis showed that deep learning features had the greatest impact on model predictions. Both RD and DL models effectively predict OLNM, with the RD-DL model offering superior performance. These findings provide a rapid, non-invasive clinical prediction method.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-13781-y.

Objective: To investigate the clinical value of the prediction models constructed by CT based imaging features and radiomics for World Health Organization/International Society of Urological Pathology (WHO/ISUP) grading in pre-operative patients with T1 clear cell renal cell carcinoma (ccRCC). Methods: Ninety patients with ccRCC diagnosed at Hangzhou Hospital of Traditional Chinese Medicine from January 2016 to December 2023 were enrolled as the training set, and 43 patients diagnosed at the Sir Run Run Shaw Hospital from January 2017 to December 2018 were enrolled as the external validation set. According to the WHO/ISUP grading system, grades Ⅰ and Ⅱ were defined as the low grade group, and grades Ⅲ and Ⅳ were defined as the high grade group. In the training set, 64 patients were in the low grade group and 26 patients in the high grade group. In the external validation set, 33 patients were in the low grade group and 10 patients in the high grade group. The multivariate logistic regression was used to establish an imaging factor model based on CT imaging features in the training set. The 3-dimensional regions of interest were manually contoured at the cortical phase of enhanced CT, and the radiomics features were extracted. Linear correlation between features and L1 regularization were used for feature selection, and then linear support vector classification was used to construct the radiomics model. After that, a combined diagnostic model of nomogram combining the radiomics score and imaging factors was constructed using multivariate logistic regression analysis. The receiver operating characteristic (ROC) curve was used to evaluate the effectiveness of each model. The Delong test was used for comparison of the areas under the ROC curve. Results: The imaging factor model, the radiomics model, and the combined diagnostic model of nomogram were successfully constructed to predict the WHO/ ISUP grading in stage T1 ccRCC. The AUC value of the imaging factor model in the training and validation sets was 0.742 (95% CI: 0.623-0.860) and 0.664 (95% CI: 0.448-0.879), respectively. The AUC values of the radiomics model in the two sets were 0.914 (95% CI: 0.844-0.983) and 0.879 (95% CI: 0.718-1.000), and of the combined diagnostic model of nomogram in the two sets were 0.929 (95% CI: 0.858-0.999) and 0.882 (95% CI: 0.710-1.000), respectively. The AUCs of the radiomics model and combined diagnostic model of nomogram were significantly higher than that of the imaging factor model (both P＜0.05). There was no statistical difference in the AUCs between the combined diagnostic model of nomogram and the radiomics model (both P＞0.05). Conclusion: The CT-based radiomics model and combined diagnostic model of nomogram incorporating radiomics signature and imaging features showed favorable predictive efficacy for the preoperative prediction of WHO/ISUP grading in stage T1 ccRCC.

ObjectivesTo establish an MRI-based radiomics model for predicting the microvascular invasion (MVI) status of cHCC-CCA and to investigate biological processes underlying the radiomics model.MethodsThe study consisted of a retrospective dataset (82 in the training set, 36 in the validation set) and a prospective dataset (25 patients in the test set) from two hospitals. Based on the training set, logistic regression analyses were employed to develop the clinical-imaging model, while radiomic features were extracted to construct a radiomics model. The diagnosis performance was further validated in the validation and test sets. Prognostic aspects of the radiomics model were investigated using the Kaplan–Meier method and log-rank test. Differential gene expression analysis and gene ontology (GO) analysis were conducted to explore biological processes underlying the radiomics model based on RNA sequencing data.ResultsOne hundred forty-three patients (mean age, 56.4 ± 10.5; 114 men) were enrolled, in which 73 (51.0%) were confirmed as MVI-positive. The radiomics model exhibited good performance in predicting MVI status, with the area under the curve of 0.935, 0.873, and 0.779 in training, validation, and test sets, respectively. Overall survival (OS) was significantly different between the predicted MVI-negative and MVI-positive groups (median OS: 25 vs 18 months, p = 0.008). Radiogenomic analysis revealed associations between the radiomics model and biological processes involved in regulating the immune response.ConclusionA robust MRI-based radiomics model was established for predicting MVI status in cHCC-CCA, in which potential prognostic value and underlying biological processes that regulate immune response were demonstrated.Critical relevance statementMVI is a significant manifestation of tumor invasiveness, and the MR-based radiomics model established in our study will facilitate risk stratification. Furthermore, underlying biological processes demonstrated in the radiomics model will offer valuable insights for guiding immunotherapy strategies.Key PointsMVI is of prognostic significance in cHCC-CCA, but lacks reliable preoperative assessment.The MRI-based radiomics model predicts MVI status effectively in cHCC-CCA.The MRI-based radiomics model demonstrated prognostic value and underlying biological processes.The radiomics model could guide immunotherapy and risk stratification in cHCC-CCA.Graphical

BackgroundTo evaluate two-dimensional (2D) and three-dimensional (3D) computed tomography (CT) radiomics analysis for the T stage of esophageal squamous cell carcinoma (ESCC).Methods398 patients with pathologically confirmed ESCC were divided into training and testing sets. All patients underwent chest CT scans preoperatively. For each tumor, based on CT images, a 2D region of interest (ROI) was outlined on the largest cross-sectional area, and a 3D ROI was outlined layer by layer on each section of the tumor. The radiomics platform was used for feature extraction. For feature selection, stepwise logistic regression was used. The receiver operating characteristic (ROC) curve was used to assess the diagnostic performance of the 2D radiomics model versus the 3D radiomics model. The differences were compared using the DeLong test. The value of the clinical utility of the two radiomics models was evaluated.Results1595 radiomics features were extracted. After screening, two radiomics models were constructed. In the training set, the difference between the area under the curve (AUC) of the 2D radiomics model (AUC = 0.831) and the 3D radiomics model (AUC = 0.830) was not statistically significant (p = 0.973). In the testing set, the difference between the AUC of the 2D radiomics model (AUC = 0.807) and the 3D radiomics model (AUC = 0.797) was also not statistically significant (p = 0.748). A 2D model was equally useful as a 3D model in clinical situations.ConclusionThe performance of 2D radiomics model is comparable to that of 3D radiomics model in distinguishing between the T1-2 and T3-4 stages of ESCC. In addition, 2D radiomics model may be a more feasible option due to the shorter time required for segmenting the ROI.

To establish a combined model based on ultrasound radiomics combined with multimodal ultrasound and evaluate its value in diagnosing benign and malignant nodules classified as Chinese-Thyroid Imaging Report and Data System (C-TIRADS) 4A. Prospective collection of data from 446 patients with thyroid nodules classified as C-TIRADS 4A between December 2023 and August 2024. Based on the enrollment timeline, patients were divided into a training set (n=312) and a test set (n=134) in a 7:3 ratio. Using clinical information, multimodal ultrasound features, and radiomics features, a radiomics model was constructed using the Random Forest (RF) machine learning algorithm. Logistic regression was employed to develop the multimodal ultrasound model and the combined model. The predictive efficiency and accuracy of these models were evaluated using Receiver Operating Characteristic (ROC) curves, calibration curves, and Decision Curve Analysis (DCA). The diagnostic efficacy of junior physicians assisted by the ultrasound radiomics model was compared with that of senior physicians. DeLong's test was performed to compare the diagnostic performance of the models. Multivariate analysis revealed that age (≤51 years), Sound Touch Elastography mean stiffness (STE Mean), orientation (vertical), margin (blurred), and margin (irregular) were independent risk factors for papillary thyroid carcinoma, and the multimodal ultrasound model was established. Based on 17 ultrasound radiomics features, a radiomics model was constructed using the RF machine learning algorithm. The combined model was developed by combining the two aforementioned models. In the training set, the areas under the curve (AUC) of the multimodal ultrasound model, ultrasound radiomics model, and combined model were 0.852, 0.940 and 0.956, respectively. In the test set, the AUC were 0.804, 0.832 and 0.863, respectively. DeLong's test showed that the combined model performed best in the training set, and in the test set, the combined model outperformed the multimodal ultrasound model but showed no significant difference compared to the radiomics model. DCA indicated that the combined model achieved higher net benefits within a specific threshold probability range (0.15-0.90). The combined model exhibits robust diagnostic capability in distinguishing benign from malignant thyroid nodules classified as C-TIRADS 4A.

Brain-tumor interface-based MRI radiomics models to predict Ki-67 proliferation status of meningiomas: A multi-center study.

ObjectivesWe aimed to develop a combined model based on clinical and radiomic features to classify fracture age.MethodsWe included 1219 rib fractures from 239 patients from our center between March 2016 and September 2022. We created an external dataset using 120 rib fractures from 32 patients from another center between October 2019 and August 2023. According to tasks (fracture age between < 3 and ≥ 3 weeks, 3–12, and > 12 weeks), the internal dataset was randomly divided into training and internal test sets. A radiomic model was built using radiomic features. A combined model was constructed using clinical features and radiomic signatures by multivariate logistic regression, visualized as a nomogram. Internal and external test sets were used to validate model performance.ResultsFor classifying fracture age between < 3 and ≥ 3 weeks, the combined model had higher areas under the curve (AUCs) than the radiomic model in the training set (0.915 vs 0.900, p = 0.009), internal test (0.897 vs 0.854, p < 0.001), and external test sets (0.881 vs 0.811, p = 0.003). For classifying fracture age between 3–12 and > 12 weeks, the combined model had higher AUCs than the radiomic model in the training model (0.848 vs 0.837, p = 0.12) and internal test sets (0.818 vs 0.793, p < 0.003). In the external test set, the AUC of the nomogram-assisted radiologist was 0.966.ConclusionThe combined radiomic and clinical model showed good performance and has the potential to assist in the classification of rib fracture age. This will be beneficial for clinical practice and forensic decision-making.Critical relevance statementThis study describes the development of a combined radiomic and clinical model with good performance in the classification of the age of rib fractures, with potential clinical and forensic applications.Key points• Complex factors make it difficult to determine the age of a fracture.• Our model based on radiomic features performed well in classifying fracture age.• Associating the radiomic features with clinical features improved the model’s performance.Graphical