Ultrasound radiomics-based nomogram to predict the non-perfused volume ratio of breast fibroadenomas treated with ultrasound-guided high-intensity focused ultrasound: a multicenter study

Objectives To develop and assess nonenhanced MRI-based radiomics model for the preoperative prediction of nonperfused volume (NPV) ratio of uterine leiomyomas after high-intensity focused ultrasound (HIFU) treatment. Methods Two hundred and five patients with uterine leiomyomas treated by HIFU were enrolled and allocated to training (N =164) and testing cohorts (N = 41). Pyradiomics was used to extract radiomics features from T2-weighted images and apparent diffusion coefficient (ADC) map generated from diffusion-weighted imaging (DWI). The clinico-radiological model, radiomics model, and radiomics-clinical model which combined the selected radiomics features and clinical parameters were used to predict technical outcomes determined by NPV ratios where three classification groups were created (NPV ratio ≤ 50%, 50–80% or ≥ 80%). The receiver operating characteristic (ROC) curve, area under the curve (AUC), and calibration and decision curve analyses were performed to illustrate the prediction performance and clinical usefulness of model in the training and testing cohorts. Results The multi-parametric MRI-based radiomics model outperformed T2-weighted imaging (T2WI)-based radiomics model, which achieved an average AUC of 0.769 (95% confidence interval [CI], 0.701–0.842), and showed satisfactory prediction performance for NPV ratio classification. The radiomics-clinical model demonstrated best prediction performance for HIFU treatment outcome, with an average AUC of 0.802 (95% CI, 0.796–0.850) and an accuracy of 0.762 (95% CI, 0.698–0.815) in the testing cohort, compared to the clinico-radiological and radiomics models. The decision curve also indicated favorable clinical usefulness of the radiomics-clinical model. Conclusions Nonenhanced MRI-based radiomics has potential in the preoperative prediction of NPV ratio for HIFU ablation of uterine leiomyomas.

BackgroundPrediction of non-perfusion volume ratio (NPVR) is critical in selecting patients with uterine fibroids who will potentially benefit from ultrasound-guided high-intensity focused ultrasound (HIFU) treatment, as it reduces the risk of treatment failure. The purpose of this study is to construct an optimal model for predicting NPVR based on T2-weighted magnetic resonance imaging (T2MRI) radiomics features combined with clinical parameters by machine learning.Materials and methodsThis retrospective study was conducted among 223 patients diagnosed with uterine fibroids from two centers. The patients from one center were allocated to a training cohort (n = 122) and an internal test cohort (n = 46), and the data from the other center (n = 55) was used as an external test cohort. The least absolute shrinkage and selection operator (LASSO) algorithm was employed for feature selection in the training cohort. The support vector machine (SVM) was adopted to construct a radiomics model, a clinical model, and a radiomics–clinical model for NPVR prediction, respectively. The area under the curve (AUC) and the decision curve analysis (DCA) were performed to evaluate the predictive validity and the clinical usefulness of the model, respectively.ResultsA total of 851 radiomic features were extracted from T2MRI, of which seven radiomics features were screened for NPVR prediction-related radiomics features. The radiomics–clinical model combining radiomics features and clinical parameters showed the best predictive performance in both the internal (AUC = 0.824, 95% CI 0.693–0.954) and external (AUC = 0.773, 95% CI 0.647–0.902) test cohorts, and the DCA also suggested the radiomics–clinical model had the highest net benefit.ConclusionsThe radiomics–clinical model could be applied to the NPVR prediction of patients with uterine fibroids treated by HIFU to provide an objective and effective method for selecting potential patients who would benefit from the treatment mostly.

This study aimed to develop a model to predict KRAS mutations in colorectal cancer according to radiomic signatures based on CT and clinical risk factors. This retrospective study included 172 patients with colorectal cancer. All patients were randomized at a 7:3 ratio into a training cohort (n = 121, 38.8% positive for KRAS mutation) and a validation cohort (n = 51, 39.2% positive for KRAS mutation). Radiomics features were extracted from single-slice and full-volume regions of interest on the portal-venous CT images. The least absolute shrinkage and selection operator (LASSO) algorithm was adopted to construct a radiomics signature, and logistic regression was applied to select the significant variables to develop the clinical-radiomics model. The predictive performance was evaluated by receiver operating characteristic curve (ROC) analysis, calibration curve analysis, and decision curve analysis (DCA). 1018 radiomics features were extracted from single-slice and full-volume ROIs. Eight features were retained to construct 2D (two-dimensional, 2D) radiomics model. Similarly, eight features were retained to construct 3D (three-dimensional, 3D) radiomics model. The area under the curve (AUC) values of the test cohort were 0.75 and 0.84, respectively. Delong test showed that the integrated nomogram (AUC = 0.92 in the test cohort) had better clinical predictive efficiency than 2D radiomics (p-value < 0.05) model and 3D radiomics model (p-value < 0.05). The 2D and 3D radiomics models can both predict KRAS mutations. And, the integrated nomogram can be better applied to predict KRAS mutation status in colorectal cancer. CT-based radiomics showed satisfactory diagnostic significance for the KRAS status in colorectal cancer, the clinical-combined model may be applied in the individual pre-operative prediction of KRAS mutation.

Application of a Comprehensive Model Based on CT Radiomics and Clinical Features for Postoperative Recurrence Risk Prediction in Non-small Cell Lung Cancer

To explore and compare the potential value of radiomics models based on contrast-enhanced computed tomography (CT) for noninvasive preoperative prediction of lymphovascular invasion (LVI) in laryngeal squamous cell carcinoma (LSCC). This multicenter diagnostic study retrospectively enrolled LSCC patients from three tertiary hospitals who underwent surgical treatment. Standardized preprocessing was performed on the CT images, followed by region-of-interest (ROI) segmentation and extraction of traditional radiomics features and deep learning features. Features were selected using least absolute shrinkage and selection operator (LASSO) regression. Traditional radiomics models and deep learning radiomics models (DLR) were established using logistic regression, random forest, and multilayer perceptron algorithms, respectively. A transformer-based hybrid model was developed by integrating radiomics and deep learning features. The predictive performance of the three types of models was evaluated and compared using the area under the curve (AUC), decision curve analysis (DCA), sample probability distribution histograms, confusion matrices, calibration curves, net reclassification index (NRI), and integrated discrimination improvement (IDI). A total of 1,024 patients were allocated to the training set (center1, n=291), internal validation set (n=126), and external test sets (center 2, n=437; center 3, n=170). Three radiomics models and three DLR models were constructed, and the optimal performance was observed in the DLR_ Random Forest model (AUC: 0.812-0.867). The transformer hybrid model demonstrated superior predictive performance, with AUC values of 0.881, 0.843, 0.833, and 0.836 in the training, internal validation, and external test sets, respectively. Decision curve analysis indicated a higher net benefit for the transformer model, along with an improved NRI and IDI. Radiomics models based on CT images exhibit potential for noninvasive prediction of LVI in LSCC, with the transformer hybrid model achieving the highest diagnostic performance. This approach may provide clinicians with a preoperative decision support tool to optimize treatment strategies for patients with LSCC.

Introduction: Prognosis prediction is essential to improve therapeutic strategies and to achieve better clinical outcomes in colorectal cancer (CRC) patients. Radiomics based on high-throughput mining of quantitative medical imaging is an emerging field in recent years. However, the relationship among prognosis, radiomics features, and gene expression remains unknown.Methods: We retrospectively analyzed 141 patients (from study 1) diagnosed with CRC from February 2018 to October 2019 and randomly divided them into training (N = 99) and testing (N = 42) cohorts. Radiomics features in venous phase image were extracted from preoperative computed tomography (CT) images. Gene expression was detected by RNA-sequencing on tumor tissues. The least absolute shrinkage and selection operator (LASSO) regression model was used for selecting imaging features and building the radiomics model. A total of 45 CRC patients (study 2) with immunohistochemical (IHC) staining of CXCL8 diagnosed with CRC from January 2014 to October 2018 were included in the independent testing cohort. A clinical model was validated for prognosis prediction in prognostic testing cohort (163 CRC patients from 2014 to 2018, study 3). We performed a combined radiomics model that was composed of radiomics score, tumor stage, and CXCL8-derived radiomics model to make comparison with the clinical model.Results: In our study, we identified the CXCL8 as a hub gene in affecting prognosis, which is mainly through regulating cytokine–cytokine receptor interaction and neutrophil migration pathway. The radiomics model incorporated 12 radiomics features screened by LASSO according to CXCL8 expression in the training cohort and showed good performance in testing and IHC testing cohorts. Finally, the CXCL8-derived radiomics model combined with tumor stage performed high ability in predicting the prognosis of CRC patients in the prognostic testing cohort, with an area under the curve (AUC) of 0.774 [95% confidence interval (CI): 0.674–0.874]. Kaplan–Meier analysis of the overall survival probability in CRC patients stratified by combined model revealed that high-risk patients have a poor prognosis compared with low-risk patients (Log-rank P < 0.0001).Conclusion: We demonstrated that the radiomics model reflected by CXCL8 combined with tumor stage information is a reliable approach to predict the prognosis in CRC patients and has a potential ability in assisting clinical decision-making.

“”We employed radiomics and clinical features to develop and validate a preoperative prediction model to estimate the omental metastases status of locally advanced gastric cancer (LAGC). A total of 460 patients (training cohort, n = 250; test cohort, n = 106; validation cohort, n = 104) with LAGC who were confirmed T3/T4 stage by postoperative pathology were continuously collected retrospectively, including clinical data and preoperative arterial phase computed tomography images (APCT). Dedicated radiomics prototype software was used to segment the lesions and extract features from the preoperative APCT images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the extracted radiomics features, and a radiomics score model was constructed. Finally, a prediction model of omental metastases status and a nomogram were constructed combining the radiomics scores and selected clinical features. An area under the curve (AUC) of the receiver operating characteristic curve (ROC) was used to validate the capability of the prediction model and nomogram in the training cohort. Calibration curves and decision curve analysis (DCA) were used to evaluate the prediction model and nomogram. The prediction model was internally validated by the test cohort. In addition, 104 patients from another hospital's clinical and imaging data were gathered for external validation. In the training cohort, the combined prediction (CP) model (AUC 0.871, 95% CI 0.798–0.945) of the radiomics scores combined with the clinical features, compared with clinical features prediction (CFP) model (AUC 0.795, 95% CI 0.710–0.879) and radiomics scores prediction (RSP) model (AUC 0.805, 95% CI 0.730–0.879), had the better predictive ability. The Hosmer–Lemeshow test of the CP model showed that the prediction model did not deviate from the perfect fitting (p = 0.893). In the DCA, the clinical net benefit of the CP model was higher than that of the CFP model and RSP model. In the test and validation cohorts, the AUC values of the CP model were 0.836 (95% CI 0.726–0.945) and 0.779 (95% CI 0.634–0.923), respectively. The preoperative APCT-based clinical-radiomics nomogram showed good performance in predicting omental metastases status in LAGC, which may contribute to clinical decision-making.

ObjectiveTo investigate whether radiomics based on ultrasound images can predict lymphovascular invasion (LVI) of rectal cancer (RC) before surgery.MethodsA total of 203 patients with RC were enrolled retrospectively, and they were divided into a training set (143 patients) and a validation set (60 patients). We extracted the radiomic features from the largest gray ultrasound image of the RC lesion. The intraclass correlation coefficient (ICC) was applied to test the repeatability of the radiomic features. The least absolute shrinkage and selection operator (LASSO) was used to reduce the data dimension and select significant features. Logistic regression (LR) analysis was applied to establish the radiomics model. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the comprehensive performance of the model.ResultsAmong the 203 patients, 33 (16.7%) were LVI positive and 170 (83.7%) were LVI negative. A total of 5350 (90.1%) radiomic features with ICC values of ≥ 0.75 were reported, which were subsequently subjected to hypothesis testing and LASSO regression dimension reduction analysis. Finally, 15 selected features were used to construct the radiomics model. The area under the curve (AUC) of the training set was 0.849, and the AUC of the validation set was 0.781. The calibration curve indicated that the radiomics model had good calibration, and DCA demonstrated that the model had clinical benefits.ConclusionThe proposed endorectal ultrasound-based radiomics model has the potential to predict LVI preoperatively in RC.

To develop and validate a radiomic prediction model using initial noncontrast computed tomography (CT) at admission to predict in-hospital mortality in patients with traumatic brain injury (TBI). A total of 379 TBI patients from three cohorts were categorized into training, internal validation, and external validation sets. After filtering the unstable features with the minimum redundancy maximum relevance approach, the CT-based radiomics signature was selected by using the least absolute shrinkage and selection operator (LASSO) approach. A personalized predictive nomogram incorporating the radiomic signature and clinical features was developed using a multivariate logistic model to predict in-hospital mortality in patients with TBI. The calibration, discrimination, and clinical usefulness of the radiomics signature and nomogram were evaluated. The radiomic signature consisting of 12 features had areas under the curve (AUCs) of 0.734, 0.716, and 0.706 in the prediction of in-hospital mortality in the internal and two external validation cohorts. The personalized predictive nomogram integrating the radiomic and clinical features demonstrated significant calibration and discrimination with AUCs of 0.843, 0.811, and 0.834 in the internal and two external validation cohorts. Based on decision curve analysis (DCA), both the radiomic features and nomogram were found to be clinically significant and useful. This predictive nomogram incorporating the CT-based radiomic signature and clinical features had maximum accuracy and played an optimized role in the early prediction of in-hospital mortality. The results of this study provide vital insights for the early warning of death in TBI patients.

To explore the utility of gray-scale ultrasound (GSUS) and mammography (MG) for radiomic analysis in distinguishing between breast adenosis and invasive ductal carcinoma (IDC). Data from 147 female patients with pathologically confirmed breast lesions (breast adenosis: 61 patients; IDC: 86 patients) between January 2018 and December 2022 were retrospectively collected. A training cohort of 113 patients (breast adenosis: 50 patients; IDC: 63 patients) diagnosed from January 2018 to December 2021 and a time-independent test cohort of 34 patients (breast adenosis: 11 patients; IDC: 23 patients) diagnosed from January 2022 to December 2022 were included. Radiomic features of lesions were extracted from MG and GSUS images. The least absolute shrinkage and selection operator (LASSO) regression was applied to select the most discriminant features, followed by logistic regression (LR) to construct clinical and radiomic models, as well as a combined model merging radiomic and clinical features. Model performance was assessed using receiver operating characteristic (ROC) analysis. In the training cohort, the area under the curve (AUC) for radiomic models based on MG features, GSUS features, and their combination were 0.974, 0.936, and 0.991, respectively. In the test cohort, the AUCs were 0.885, 0.876, and 0.949, respectively. The combined model, incorporating clinical and all radiomic features, and the MG plus GSUS radiomics model were found to exhibit significantly higher AUCs than the clinical model in both the training cohort and test cohort (p<0.05). No significant differences were observed between the combined model and the MG plus GSUS radiomics model in the training cohort and test cohort (p>0.05). The effectiveness of radiomic features derived from GSUS and MG in distinguishing between breast adenosis and IDC is demonstrated. Superior discriminatory efficacy is shown by the combined model, integrating both modalities.

To establish and validate a machine learning model using pretreatment multiparametric magnetic resonance imaging-based radiomics data with clinical data to predict radiation-induced temporal lobe injury (RTLI) in patients with nasopharyngeal carcinoma (NPC) after intensity-modulated radiotherapy (IMRT). Data from 230 patients with NPC who received IMRT (130 with RTLI and 130 without) were randomly divided into the training (n = 161) and validation cohort (n = 69) with a ratio of 7:3. Radiomics features were extracted from pretreatment apparent diffusion coefficient (ADC) map, T2-weighted imaging (T2WI), and CE-T1-weighted imaging (CE-T1WI). T-test, spearman rank correlation, and least absolute shrinkage and selection operator (LASSO) algorithm were employed to identify significant radiomics features. Clinical features were selected with univariate and multivariate analyses. Radiomics and clinical models were constructed using multiple machine learning classifiers, and a clinical-radiomics nomogram that combined clinical with radiomics features was developed. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were drawn to compare and verify the predictive performances of the clinical model, radiomics model, and clinical-radiomics nomogram. A total of 5064 radiomics features were extracted, from which 52 radiomics features were selected to construct the radiomics signature. The AUC of the radiomics signature based on multiparametric MRI was 0.980 in the training cohort and 0.969 in the validation cohort, outperforming the radiomics signature only based on T2WI and CE-T1WI (p < 0.05), which highlighted the significance of the DWI sequence in the prediction of temporal lobe injury. The area under the curve (AUC) of the clinical model was 0.895 in the training cohort and 0.905 in the validation cohort. The nomogram, which integrated radiomics and clinical features, demonstrated an impressive AUC value of 0.984 in the validation set; however, no statistically significant difference was observed compared to the radiomics model. The calibration curve and decision curve analysis of the nomogram demonstrated excellent predictive performance and clinical feasibility. The clinical-radiomics nomogram, integrating clinical features with radiomics features derived from pretreatment multiparametric MRI, exhibits compelling predictive performance for RTLI in patients diagnosed with NPC.

To establish an interpretable and non-invasive machine learning (ML) model using clinicoradiological predictors and magnetic resonance imaging (MRI) radiomics features to predict the consistency of pituitary macroadenomas (PMAs) preoperatively. Total 350 patients with PMA (272 from Xinqiao Hospital of Army Medical University and 78 from Daping Hospital of Army Medical University) were stratified and randomly divided into training and test cohorts in a 7:3 ratio. The tumor consistency was classified as soft or firm. Clinicoradiological predictors were examined utilizing univariate and multivariate regression analyses. Radiomics features were selected employing the minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithms. Logistic regression (LR) and random forest (RF) classifiers were applied to construct the models. Receiver operating characteristic (ROC) curves and decision curve analyses (DCA) were performed to compare and validate the predictive capacities of the models. A comparative study of the area under the curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE) was performed. The Shapley additive explanation (SHAP) was applied to investigate the optimal model's interpretability. The combined model predicted the PMAs' consistency more effectively than the clinicoradiological and radiomics models. Specifically, the LR-combined model displayed optimal prediction performance (test cohort: AUC = 0.913; ACC = 0.840). The SHAP-based explanation of the LR-combined model suggests that the wavelet-transformed and Laplacian of Gaussian (LoG) filter features extracted from T2WI and CE-T1WI occupy a dominant position. Meanwhile, the skewness of the original first-order features extracted from T2WI (T2WI_original_first-order_Skewness) demonstrated the most substantial contribution. An interpretable machine learning model incorporating clinicoradiological predictors and multiparametric MRI (mpMRI)-based radiomics features may predict PMAs consistency, enabling tailored and precise therapies for patients with PMA.

The objective of the study is to assess the clinical value of machine learning radiomics based on contrast-enhanced computed tomography (CECT) images in preoperative prediction of perineural invasion (PNI) status in pancreatic ductal adenocarcinoma (PDAC). A total of 143 patients with PDAC were enrolled in this retrospective study (training group, n = 100; test group, n = 43). Radiomics features were extracted from CECT images and selected by the Mann-Whitney U-test, Pearson correlation coefficient, and least absolute shrinkage and selection operator (LASSO). The logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), and decision tree (DT) algorithms were trained to build radiomics models by radiomic features. Multivariate logistic regression was employed to identify independent predictors and establish clinical models. A combined model was constructed by integrating clinical and radiomics features. Model performances were assessed by receiver operating characteristic curves (ROCs) and decision curve analyses (DCAs). A total of 788 radiomics features were extracted from CECT images, of which 14 were identified as significant through the three-step selection process. Among the machine learning models, the SVM radiomics model exhibited the highest predictive performance in the test group, achieving an area under the curve (AUC) of 0.831, accuracy of 0.698, sensitivity of 0.677, and specificity of 0.750. After logistic regression screening, the clinical model was established using carbohydrate antigen 19-9 (CA199) levels as one independent predictor. In the test group, the clinical model demonstrated an AUC of 0.644, accuracy of 0.744, sensitivity of 0.871, and specificity of 0.417. The combined model showed improved performance compared to both the clinical and radiomics models in the test group, with an AUC of 0.844, accuracy of 0.767, sensitivity of 0.806, and specificity of 0.667. Subsequently, DCA of the combined model indicated optimal clinical value for predicting PNI status. Machine learning radiomics models can accurately predict PNI status in patients with pancreatic ductal adenocarcinoma. The combined model, which incorporates clinical and radiomics features, enhances preoperative diagnostic performance and aids in the selection of treatment methods.

Development and Validation of an Ultrasound-Based Clinical Radiomics Nomogram for Diagnosing Gouty Arthritis.

The noninvasive assessment of hepatic inflammatory activity (HIA) is crucial for making clinical decisions and monitoring therapeutic efficacy in chronic liver disease (CLD). To develop MRI-based radiomics models by extracting features from the whole liver and localized regions of the right liver lobe, compare the efficiency of two radiomics models, and further develop a radiomics nomogram for the assessment of HIA in CLD. Retrospective. In all, 137 consecutive patients. 1.5T/T2 -weighted imaging. All patients (nonsignificant HIA, n = 98; significant HIA, n = 39) were randomly divided into a training (n = 95) and a test cohort (n = 42). Radiomics features were extracted from the regions covering the whole liver (ROI-w) and localized regions of the right liver lobe (ROI-r). Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression analyses were used to select features and develop radiomics models. A combined model fusing the valuable radiomics features with clinical-radiological predictors was developed. Finally, a radiomics nomogram derived from the combined model was developed. Synthetic minority oversampling technique algorithm, LASSO, receiver operator characteristic curve, and calibration curve analysis were performed. The area under the curve (AUC), sensitivity, and specificity of the ROI-w radiomics model in assessing HIA were 0.858, 0.800, and 0.733, respectively. The ROI-r model were 0.844, 0.733, and 0.867, respectively. No differences were detected between the two radiomics models (P = 0.8329). The combined model fusing valuable ROI-w radiomics features, albumin, and periportal edema exhibited a promising performance (AUC, 0.911). The calibration curves showed good agreement between the actual observations and nomogram predictions. The MRI-based radiomics models had a powerful ability to evaluate HIA and the ROI-w radiomics model was comparable to the ROI-r model. Moreover, the radiomics nomogram could be a favorable method to individually estimate HIA in CLD. J. MAGN. RESON. IMAGING 2020;52:1668-1678.