Combined Radiomics Model Research Articles

CT-based Intra-thrombus and Peri-thrombus Radiomics for Prediction of Prognosis After Endovascular Thrombectomy: A Retrospective Study Across Two Centers.

Complications from endovascular thrombectomy (EVT) can negatively affect clinical outcomes, making the development of a more precise and objective prediction model essential. This research aimed to assess the effectiveness of radiomic features derived from pre-surgical CT scans in predicting the prognosis post- EVT in acute ischemic stroke patients. This investigation included 336 acute ischemic stroke patients from two medical centers, spanning from March 2018 to March 2024. The participants were split into a training cohort of 161 patients and a validation cohort of 175 patients. Patient outcomes were rated with the mRS: 0-2 for good, 3-6 for poor. A total of 428 radiomic features were derived from intra-thrombus and peri-thrombus regions in non-contrast CT and CT angiography images. Feature selection was conducted using a least absolute shrinkage and selection operator regression model. The efficacy of eight different supervised learning models was assessed using the area under the curve (AUC) of the receiver operating characteristic curve. Among all models tested in the validation cohort, the logistic regression algorithm for combined model achieved the highest AUC (0.87, with a 95% confidence interval of 0.81 to 0.92), outperforming other algorithms. The combined use of radiomic features from both the intra-thrombus and peri-thrombus regions significantly enhanced diagnostic accuracy over models using features from a single region (0.81 vs 0.70, 0.77), highlighting the benefit of integrating data from both regions for improved prediction. The findings suggest that a combined radiomics model based on CT imaging serves as a potent approach to assessing the prognosis following EVT. The logistic regression model, in particular, proved to be both effective and stable, offering critical insights for the management of stroke. AUC=area under the curve; EVT=endovascular thrombectomy; KNN=k-nearest neighbors; LASSO=least absolute shrinkage and selection operator; LightGBM=Light Gradient Boosting Machine; LR=logistic regression; MLP=multi-layer perceptron; RF=random forest; SVM=support vector machine; XGBoost=extreme gradient boosting.

Prediction of feeding difficulties in neonates with hypoxic-ischemic encephalopathy using magnetic resonance imaging-derived radiomics features.

The mechanisms behind brain and spinal cord injuries in hypoxic-ischemic encephalopathy (HIE) and associated feeding difficulties are unclear, with previous magnetic resonance imaging (MRI) attempts yielding inconclusive results. We aim to evaluate an MRI radiomics model for predicting feeding difficulties in HIE infants. Additionally, we investigate changes in predictive capability after incorporating the duration of mechanical ventilation and the timing of MRI examination. Retrospective study with 151 HIE infants (January 2013 to December 2021), randomly divided into training and validation sets. Radiomics features extracted from basal ganglia-thalamus and brainstem in T1-weighted and T2-weighted MRI. Established single-modality, single-site, and multimodality/multisite models. Receiver operating characteristic analysis and area under the curve evaluated models. Decision curve analysis assessed changes in predictive capability. The combined radiomics model of the basal ganglia-thalamus and brainstem regions on the T2-weighted imaging demonstrated superior performance (area under the curve: 0.958 and 0.875 for training and validation, respectively). Combining scores with duration of mechanical ventilation and MRI examination time in a calibration plot model improved and stabilized performance, showing high fitting and clinical utility. Decision curve analysis favored the combined calibration plot model. The MRI-based radiomics model predicts feeding difficulties in HIE infants, with basal ganglia-thalamus and brainstem as relevant factors. The combined calibration plot model exhibits the highest clinical predictive efficacy.

Radiomics-based machine learning models for differentiating pathological subtypes in cervical cancer: a multicenter study.

This study was designed to determine the diagnostic performance of fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics-based machine learning (ML) in the classification of cervical adenocarcinoma (AC) and squamous cell carcinoma (SCC). Pretreatment 18F-FDG PET/CT data were retrospectively collected from patients who were diagnosed with locally advanced cervical cancer at two centers. Radiomics features were extracted and selected by the Pearson correlation coefficient and least absolute shrinkage and selection operator regression analysis. Six ML algorithms were then applied to establish models, and the best-performing classifier was selected based on accuracy, sensitivity, specificity, and area under the curve (AUC). The performance of different model was assessed and compared using the DeLong test. A total of 227 patients with locally advanced cervical cancer were enrolled in this study (N=136 for the training cohort, N=59 for the internal validation cohort, and N=32 for the external validation cohort). The PET radiomics model constructed based on the lightGBM algorithm had an accuracy of 0.915 and an AUC of 0.851 (95% confidence interval [CI], 0.715-0.986) in the internal validation cohort, which were higher than those of the CT radiomics model (accuracy: 0.661; AUC: 0.513 [95% CI, 0.339-0.688]). The DeLong test revealed no significant difference in AUC between the combined radiomics model and the PET radiomics model in either the training cohort (z=0.940, P=0.347) or the internal validation cohort (z=0.285, P=0.776). In the external validation cohort, the lightGBM-based PET radiomics model achieved good discrimination between SCC and AC (AUC = 0.730). The lightGBM-based PET radiomics model had great potential to predict the fine histological subtypes of locally advanced cervical cancer and might serve as a promising noninvasive approach for the diagnosis and management of locally advanced cervical cancer.

Diagnostic value of Gd-EOB-DTPA-enhanced MRI radiomics models for dual-phenotype hepatocellular carcinoma

Objective: To develop and validate clinical and radiomics models based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI of dual-phenotype hepatocellular carcinoma (DPHCC) for preoperative differential diagnosis. Methods: Two hundred and fifty inpatients of hepatocellular carcinoma (HCC) confirmed by postoperative pathology, who underwent Gd-EOB-DTPA-enhanced MRI were retrospectively included. A total of 172 inpatients (72 DPHCC and 100 non-DPHCC) were included in Institution 1 (the First Affiliated Hospital of Soochow University) as a training cohort (between January 2020 and July 2023) and 78 inpatients (44 DPHCC and 34 non-DPHCC) were included in Institution 2 (the Third People's Hospital of Nantong) as an external validation cohort(between January 2019 and July 2023). The regions of interest of the tumor were delineated layer by layer in noncontrast phase, arterial phase (AP), portal venous phase (PP) and hepatobiliary phase (HBP) images. The software of FAE was used to extract the radiomics features of the images. Pearson correlation analysis and recursive feature elimination were used for feature selection. Each phase and combined radiomics models were established using logistic regression, linear discriminant analysis and support vector machine. Receiver operating characteristic curve and the areas under the curve (AUC) were used to evaluate and select the dominant radiomics model. The dominant radiomics model was combined with clinically independent predictors to construct a clinical radiomics model. Delong test was used to compare the performance of the models. Results: The age of the training cohort was (59.6±10.4) years, in which there were 135 men (78.5%). In the external validation cohort, the age was (57.8±9.2) years, including 56 men (71.8%). The maximum diameters of the lesions [M (Q1, Q3), 4.7 (2.6, 7.5) vs 2.7 (1.8, 4.4) cm, P<0.001] and the proportion of the multiple lesions (39.5% vs 16.7%, P<0.001) in the training cohort were higher than those in the external validation cohort. In the training group, the proportion of patients with hepatitis B virus (HBV) infection in the DPHCC subgroup (66.7%,48/172) was higher than that in non-DPHCC subgroup (49.0%,49/78,P=0.021). In the external validation cohort, the AUC (95%CI) of the PP [0.835 (0.733-0.937)] and combined radiomics models [0.786 (0.681-0.891)] were significantly higher than that of noncontrast phase [0.451 (0.319-0.584)], AP [0.566 (0.435-0.696)] and HBP models [0.496 (0.363-0.629)] (all P<0.05). There was no significant difference in AUC between PP radiomics model and combined radiomics model (P=0.189). The AUC between the radiomics models and clinical-radiomics models, which were brought into clinically independent variable HBV, showed no significant difference (all P>0.05). Conclusion: Gd-EOB-DTPA-enhanced MRI radiomics model based on portal venous phase may be available for discriminating DPHCC from non-DPHCC before operation.

Preoperative prediction of MGMT promoter methylation in glioblastoma based on multiregional and multi-sequence MRI radiomics analysis

O6-methylguanine-DNA methyltransferase (MGMT) has been demonstrated to be an important prognostic and predictive marker in glioblastoma (GBM). To establish a reliable radiomics model based on MRI data to predict the MGMT promoter methylation status of GBM. A total of 183 patients with glioblastoma were included in this retrospective study. The visually accessible Rembrandt images (VASARI) features were extracted for each patient, and a total of 14676 multi-region features were extracted from enhanced, necrotic, “non-enhanced, and edematous” areas on their multiparametric MRI. Twelve individual radiomics models were constructed based on the radiomics features from different subregions and different sequences. Four single-sequence models, three single-region models and the combined radiomics model combining all individual models were constructed. Finally, the predictive performance of adding clinical factors and VASARI characteristics was evaluated. The ComRad model combining all individual radiomics models exhibited the best performance in test set 1 and test set 2, with the area under the receiver operating characteristic curve (AUC) of 0.839 (0.709–0.963) and 0.739 (0.581–0.897), respectively. The results indicated that the radiomics model combining multi-region and multi-parametric MRI features has exhibited promising performance in predicting MGMT methylation status in GBM. The Modeling scheme that combining all individual radiomics models showed best performance among all constructed moels.

CT-Based Radiomics Models for Differentiation of Benign and Malignant Thyroid Nodules: A Multicenter Development and Validation Study.

BACKGROUND. CT is increasingly detecting thyroid nodules. Prior studies indicated a potential role of CT-based radiomics models in characterizing thyroid nodules, although these studies lacked external validation. OBJECTIVE. The purpose of this study was to develop and validate a CT-based radiomics model for the differentiation of benign and malignant thyroid nodules. METHODS. This retrospective study included 378 patients (mean age, 46.3 ± 13.9 [SD] years; 86 men, 292 women) with 408 resected thyroid nodules (145 benign, 263 malignant) from two centers (center 1: 293 nodules, January 2018 to December 2022; center 2: 115 nodules, January 2020 to December 2022) who underwent preoperative multiphase neck CT (noncontrast, arterial, and venous phases). Nodules from center 1 were divided into training (n = 206) and internal validation (n = 87) sets; all nodules from center 2 formed an external validation set. Radiologists assessed nodules for morphologic CT features. Nodules were manually segmented on all phases, and radiomic features were extracted. Conventional (clinical and morphologic CT), noncontrast CT radiomics, arterial phase CT radiomics, venous phase CT radiomics, multiphase CT radiomics, and combined (clinical, morphologic CT, and multiphase CT radiomics) models were established using feature selection methods and evaluated by ROC curve analysis, calibration-curve analysis, and decision-curve analysis. RESULTS. The combined model included patient age, three morphologic features (cystic change, "edge interruption" sign, abnormal cervical lymph nodes), and 28 radiomic features (from all three phases). In the external validation set, the combined model had an AUC of 0.923, and, at an optimal threshold derived in the training set, sensitivity of 84.0%, specificity of 94.1%, and accuracy of 87.0%. In the external validation set, the AUC was significantly higher for the combined model than for the conventional model (0.827), noncontrast CT radiomics model (0.847), arterial phase CT radiomics model (0.826), venous phase CT radiomics model (0.773), and multiphase CT radiomics model (0.824) (all p < .05). In the external validation set, the calibration curves indicated the lowest (i.e., best) Brier score for the combined model; in the decision-curve analysis, the combined model had the highest net benefit for most of the range of threshold probabilities. CONCLUSION. A combined model incorporating clinical, morphologic CT, and multiphase CT radiomics features exhibited robust performance in differentiating benign and malignant thyroid nodules. CLINICAL IMPACT. The combined radiomics model may help guide further management for thyroid nodules detected on CT.

Associations between radiomic phenotypes and genomic mechanisms in HBV-associated cholangiocarcinoma.

e16249 Background: Despite the epidemiological association between cholangiocarcinoma (CCA) and HBV infection, little is known about the relevant oncogenic biomarkers for advancing cancer research and improving future patient therapy. Radiomics-based non-invasive biomarkers are promising to facilitate the translation of therapeutically related molecular subtypes for treatment allocation of patients with HBV-infected CCA. Methods: In this study, we included 55 CCA patients with whole-genome multi-omics data, proteomic data with matched magnetic resonance imaging (MRI) data from institute 1. A total of 431 patients with histopathological confirmed CCA (143 HBV-positive and 288 HBV-negative patients) were retrospectively enrolled from three institutes, and patients were allocated to the training (n = 302) and validation (n = 129) cohorts from different institutes or time period (7:3). Utilizing linear regression and gene set enrichment analysis, we identified statistically significant associations between radiomic imaging and various genomic features in HBV-positive or HBV-negative CCA patients. Additionally, we employed a random forest classifier based on radiomic features to predict the status of HBV infection, HBV-related gene mutations and protein expression profiling, and tested on an internal and an external CCA cohort (n = 53). Results: The analysis revealed significant and widespread associations between genomic features (somatic mutations, transcriptional activities and copy number variations) and radiomic features characterizing HBV infection status. Our results show that quantitative image features are capable of distinguishing several molecular phenotypes. We obtained significant predictive performance for HBV+ (AUC = 0.73), CA-199(AUC = 0.77) and NeuroInvasion (AUC = 0.71), activation of ESRP1(AUC = 0.79) and mutation of HNRNPUL2/MUC4 (AUC = 0.73). We externally validated the HBV prediction model (AUC = 0.76) on the internal and external cohort. The sensitivity, specificity, and accuracy were all &gt; 70%. The radiomic signature succeeded to stratify patients into distinct survival outcomes according to HBV status, and remained an independent prognostic factor in multivariable analysis (DFS, P &lt; 0.0001; OS, P = 0.029). Integrating the radiomic signature with clinicopathological-radiographic factors further improved prediction performance. A nomogram incorporating significant pathological predictors (HBV, CA-125, CA-199, Neuro invasion, peritoneal invasion, pT stage, pN stage, and differentiation, grade) and radiomics signatures displayed good prediction performance in estimating OS with AUC values of 0.895, 0.935, and 0.907 at 1, 3, and 5 years, respectively. Conclusions: This deep learning-driven combined radiomics model may provide as a useful tool to preoperatively predict HBV infection and improve therapeutic management of ICC patients.

Predicting Survival Using Whole-Liver MRI Radiomics in Patients with Hepatocellular Carcinoma After TACE Refractoriness.

To develop a model based on whole-liver radiomics features of pre-treatment enhanced MRI for predicting the prognosis of hepatocellular carcinoma (HCC) patients undergoing continued transarterial chemoembolization (TACE) after TACE-resistance. Data from 111 TACE-resistant HCC patients between January2014 and March2018 were retrospectively collected. At a ratio of 7:3, patients were randomly assigned to developing and validation cohorts. The whole-liver were manually segmented, and the radiomics signature was extracted. The tumor and liver radiomics score (TLrad-score) was calculated. Models were trained by machine learning algorithms and their predictive efficacies were compared. Tumor stage, tumor burden, body mass index, alpha-fetoprotein, and vascular invasion were revealed as independent risk factors for survival. The model trained by Random Forest algorithms based on tumor burden, whole-liver radiomics signature, and clinical features had the highest predictive efficacy, with c-index values of 0.85 and 0.80 and areas under the ROC curve of 0.96 and 0.83 in the developing cohort and validation cohort, respectively. In the high-rad-score group (TLrad-score > - 0.34), the median overall survival (mOS) was significantly shorter than in the low-rad-score group (17m vs. 37m, p < 0.001). A shorter mOS was observed in patients with high tumor burden compared to those with low tumor burden (14m vs. 29m, p = 0.007). The combined radiomics model from whole-liver signatures may effectively predict survival for HCC patients continuing TACE after TACE refractoriness. The TLrad-score and tumor burden are potential prognostic markers for TACE therapy following TACE-resistance.

Predicting Microwave Ablation Early Efficacy in Pulmonary Malignancies via Δ Radiomics Models.

This study aimed to explore the value of preoperative and postoperative computed tomography (CT)-based radiomic signatures and Δ radiomic signatures for evaluating the early efficacy of microwave ablation (MWA) for pulmonary malignancies. In total, 115 patients with pulmonary malignancies who underwent MWA treatment were categorized into response and nonresponse groups according to relevant guidelines and consensus. Quantitative image features of the largest pulmonary malignancies were extracted from CT noncontrast scan images preoperatively (time point 0, TP0) and immediately postoperatively (time point 1, TP1). Critical features were selected from TP0 and TP1 and as Δ radiomics signatures for building radiomics models. In addition, a combined radiomics model (C-RO) was developed by integrating radiomics parameters with clinical risk factors. Prediction performance was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). The radiomics model using Δ features outperformed the radiomics model using TP0 and TP1 features, with training and validation AUCs of 0.892, 0.808, and 0.787, and 0.705, 0.825, and 0.778, respectively. By combining the TP0, TP1, and Δ features, the logistic regression model exhibited the best performance, with training and validation AUCs of 0.945 and 0.744, respectively. The DCA confirmed the clinical utility of the Δ radiomics model. A combined prediction model, including TP0, TP1, and Δ radiometric features, can be used to evaluate the early efficacy of MWA in pulmonary malignancies.

Prediction of histopathologic grades of bladder cancer with radiomics based on MRI: Comparison with traditional MRI

PurposeTo compare biparametric magnetic resonance imaging (bp-MRI) radiomics signatures and traditional MRI model for the preoperative prediction of bladder cancer (BCa) grade. Materials and methodsThis retrospective study included 255 consecutive patients with pathologically confirmed 113 low-grade and 142 high-grade BCa. The traditional MRI nomogram model was developed using univariate and multivariate logistic regression by the mean apparent diffusion coefficient (ADC), vesical imaging reporting and data system, tumor size, and the number of tumors. Volumes of interest were manually drawn on T2-weighted imaging (T2WI) and ADC maps by 2 radiologists. Using one-way analysis of variance, correlation, and least absolute shrinkage and selection operator methods to select features. Then, a logistic regression classifier was used to develop the radiomics signatures. Receiver operating characteristic (ROC) analysis was used to compare the diagnostic abilities of the radiomics and traditional MRI models by the DeLong test. Finally, decision curve analysis was performed by estimating the clinical usefulness of the 2 models. ResultsThe area under the ROC curves (AUCs) of the traditional MRI model were 0.841 in the training cohort and 0.806 in the validation cohort. The AUCs of the 3 groups of radiomics model [ADC, T2WI, bp-MRI (ADC and T2WI)] were 0.888, 0.875, and 0.899 in the training cohort and 0.863, 0.805, and 0.867 in the validation cohort, respectively. The combined radiomics model achieved higher AUCs than the traditional MRI model. decision curve analysis indicated that the radiomics model had higher net benefits than the traditional MRI model. ConclusionThe bp-MRI radiomics model may help distinguish high-grade and low-grade BCa and outperforming the traditional MRI model. Multicenter validation is needed to acquire high-level evidence for its clinical application.

Predicting microvascular invasion in small (≤ 5 cm) hepatocellular carcinomas using radiomics-based peritumoral analysis

ObjectiveWe assessed the predictive capacity of computed tomography (CT)-enhanced radiomics models in determining microvascular invasion (MVI) for isolated hepatocellular carcinoma (HCC) ≤ 5 cm within peritumoral margins of 5 and 10 mm.MethodsRadiomics software was used for feature extraction. We used the least absolute shrinkage and selection operator (LASSO) algorithm to establish an effective model to predict patients’ preoperative MVI status.ResultsThe area under the curve (AUC) values in the validation sets for the 5- and 10-mm radiomics models concerning arterial tumors were 0.759 and 0.637, respectively. In the portal vein phase, they were 0.626 and 0.693, respectively. Additionally, the combined radiomics model for arterial tumors and the peritumoral 5-mm margin had an AUC value of 0.820. The decision curve showed that the combined tumor and peritumoral radiomics model exhibited a somewhat superior benefit compared to the traditional model, while the fusion model demonstrated an even greater advantage, indicating its significant potential in clinical application.ConclusionThe 5-mm peritumoral arterial model had superior accuracy and sensitivity in predicting MVI. Moreover, the combined tumor and peritumoral radiomics model outperformed both the individual tumor and peritumoral radiomics models. The most effective combination was the arterial phase tumor and peritumor 5-mm margin combination. Using a fusion model that integrates tumor and peritumoral radiomics and clinical data can aid in the preoperative diagnosis of the MVI of isolated HCC ≤ 5 cm, indicating considerable practical value.Critical relevance statementThe radiomics model including a 5-mm peritumoral expansion is a promising noninvasive biomarker for preoperatively predicting microvascular invasion in patients diagnosed with a solitary HCC ≤ 5 cm.Key points• Radiomics features extracted at a 5-mm distance from the tumor could better predict hepatocellular carcinoma microvascular invasion.• Peritumoral radiomics can be used to capture tumor heterogeneity and predict microvascular invasion.• This radiomics model stands as a promising noninvasive biomarker for preoperatively predicting MVI in individuals.Graphical

Radiomics model based on intratumoral and peritumoral features for predicting major pathological response in non-small cell lung cancer receiving neoadjuvant immunochemotherapy.

To establish a radiomics model based on intratumoral and peritumoral features extracted from pre-treatment CT to predict the major pathological response (MPR) in patients with non-small cell lung cancer (NSCLC) receiving neoadjuvant immunochemotherapy. A total of 148 NSCLC patients who underwent neoadjuvant immunochemotherapy from two centers (SRRSH and ZCH) were retrospectively included. The SRRSH dataset (n=105) was used as the training and internal validation cohort. Radiomics features of intratumoral (T) and peritumoral regions (P1=0-5mm, P2=5-10mm, and P3=10-15mm) were extracted from pre-treatment CT. Intra- and inter- class correlation coefficients and least absolute shrinkage and selection operator were used to feature selection. Four single ROI models mentioned above and a combined radiomics (CR: T+P1+P2+P3) model were established by using machine learning algorithms. Clinical factors were selected to construct the combined radiomics-clinical (CRC) model, which was validated in the external center ZCH (n=43). The performance of the models was assessed by DeLong test, calibration curve and decision curve analysis. Histopathological type was the only independent clinical risk factor. The model CR with eight selected radiomics features demonstrated a good predictive performance in the internal validation (AUC=0.810) and significantly improved than the model T (AUC=0.810 vs 0.619, p<0.05). The model CRC yielded the best predictive capability (AUC=0.814) and obtained satisfactory performance in the independent external test set (AUC=0.768, 95% CI: 0.62-0.91). We established a CRC model that incorporates intratumoral and peritumoral features and histopathological type, providing an effective approach for selecting NSCLC patients suitable for neoadjuvant immunochemotherapy.

Prediction of Lymphovascular Space Invision in Endometrial Cancer based on Multi-parameter MRI Radiomics Model.

This retrospective study collected the clinicopathological and imaging data of 218 patients with EC in Yuncheng Central Hospital from March 2018 to May 2022. The patients were randomly divided into training group (n=152) and validation group (n= 66) according to the ratio of 7: 3. Based on the ADC, CE-sag, CE-tra, DWI, T2WI-sag-fs, T2WI-tra sequence images of each patient, the region of interest was manually segmented and the features were extracted. The four-step dimensionality reduction method based on max-relevance and min-redundancy (MRMR) and least absolute shrinkage and selection operator (LASSO) regression was used for feature selection and radiomics model construction. Independent predictors of clinicopathological features were screened by multivariate logistic regression analysis. The imaging model based on ADC, CE-sag, CE-tra, DWI, T2WI-sag-fs, T2WI-tra single sequence and combined sequence and the fusion model with clinicopathological features were constructed, and the nomogram was made. ROC curve, correction curve and decision analysis curve were used to evaluate the efficacy and clinical benefits of the nomogram. There was no significant difference in general clinical data between the training and validation groups (P > 0.05). After screening the extracted features, 16 radiomics features were obtained, which were all related to LVSI in EC patients (P &#60; 0.05). The area under the ROC curve (AUC) of the six independent sequence radiomics models in the training group was 0.807, 0.794, 0.826, 0.794, 0.828, 0.824, respectively. The AUC corresponding to the radiomics model constructed by the combined sequence was 0.884, and the diagnostic efficiency was the best, which was verified in the validation group. The AUC of the nomogram constructed by the combined radiomics model and age maximum tumor diameter(MTD), lymph node enlargement (LNE) in the training group and the validation group were 0.914 and 0.912, respectively. The correction curve shows that the nomogram has good correction performance. The decision curve suggests that taking radiomics nomogram to predict LVSI net benefit when the risk threshold is > 10% is better than considering all patients as LVSI+ or LVSI-. The combined model based on multi-parametric MRI radiomics features and clinical features has good predictive value for LVSI status in EC patients.</p>.

Diffusion Tensor and Kurtosis MRI-Based Radiomics Analysis of Kidney Injury in Type 2 Diabetes.

Diffusion tensor imaging (DTI) and diffusion kurtosis imaging (DKI) can provide quantitative parameters that show promise for evaluation of diabetic kidney disease (DKD). The combination of radiomics with DTI and DKI may hold potential clinical value in detecting DKD. To investigate radiomics models of DKI and DTI for predicting DKD in type 2 diabetes mellitus (T2DM) and evaluate their performance in automated renal parenchyma segmentation. Prospective. One hundred and sixty-three T2DM patients (87 DKD; 63 females; 27-80 years), randomly divided into training cohort (N = 114) and validation cohort (N = 49). 1.5-T, diffusion spectrum imaging (DSI) with 9 different b-values. The images of DSI were processed to generate DKI and DTI parameter maps, including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD). The Swin UNETR model was trained with 5-fold cross-validation using 100 samples for renal parenchyma segmentation. Subsequently, radiomics features were automatically extracted from each parameter map. The performance of the radiomics models on the validation cohort was evaluated by utilizing the receiver operating characteristic (ROC) curve. Mann-Whitney U test, Chi-squared test, Pearson correlation coefficient, least absolute shrinkage and selection operator (LASSO), dice similarity coefficient (DSC), decision curve analysis (DCA), area under the curve (AUC), and DeLong's test. The threshold for statistical significance was set at P < 0.05. The DKI_MD achieved the best segmentation performance (DSC, 0.925 ± 0.011). A combined radiomics model (DTI_FA, DTI_MD, DKI_FA, DKI_MD, and DKI_RD) showed the best performance (AUC, 0.918; 95% confidence interval [CI]: 0.820-0.991). When the threshold probability was greater than 20%, the combined model provided the greatest net benefit. Among the single parameter maps, the DTI_FA exhibited superior diagnostic performance (AUC, 887; 95% CI: 0.779-0.972). The radiomics signature constructed based on DKI and DTI may be used as an accurate and non-invasive tool to identify T2DM and DKD. 2 TECHNICAL EFFICACY: Stage 2.

MRI radiomics-based decision support tool for a personalized classification of cervical disc degeneration: a two-center study.

Objectives: To develop and validate an MRI radiomics-based decision support tool for the automated grading of cervical disc degeneration. Methods: The retrospective study included 2,610 cervical disc samples of 435 patients from two hospitals. The cervical magnetic resonance imaging (MRI) analysis of patients confirmed cervical disc degeneration grades using the Pfirrmann grading system. A training set (1,830 samples of 305 patients) and an independent test set (780 samples of 130 patients) were divided for the construction and validation of the machine learning model, respectively. We provided a fine-tuned MedSAM model for automated cervical disc segmentation. Then, we extracted 924 radiomic features from each segmented disc in T1 and T2 MRI modalities. All features were processed and selected using minimum redundancy maximum relevance (mRMR) and multiple machine learning algorithms. Meanwhile, the radiomics models of various machine learning algorithms and MRI images were constructed and compared. Finally, the combined radiomics model was constructed in the training set and validated in the test set. Radiomic feature mapping was provided for auxiliary diagnosis. Results: Of the 2,610 cervical disc samples, 794 (30.4%) were classified as low grade and 1,816 (69.6%) were classified as high grade. The fine-tuned MedSAM model achieved good segmentation performance, with the mean Dice coefficient of 0.93. Higher-order texture features contributed to the dominant force in the diagnostic task (80%). Among various machine learning models, random forest performed better than the other algorithms (p < 0.01), and the T2 MRI radiomics model showed better results than T1 MRI in the diagnostic performance (p < 0.05). The final combined radiomics model had an area under the receiver operating characteristic curve (AUC) of 0.95, an accuracy of 89.51%, a precision of 87.07%, a recall of 98.83%, and an F1 score of 0.93 in the test set, which were all better than those of other models (p < 0.05). Conclusion: The radiomics-based decision support tool using T1 and T2 MRI modalities can be used for cervical disc degeneration grading, facilitating individualized management.

Comprehensive integrated analysis of MR and DCE-MR radiomics models for prognostic prediction in nasopharyngeal carcinoma

Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investigate the role of DCR-MR in predicting progression-free survival (PFS) in patients with NPC using magnetic resonance (MR)- and DCE-MR-based radiomic models. A total of 434 patients with two MR scanning sequences were included. The MR- and DCE-MR-based radiomics models were developed based on 289 patients with only MR scanning sequences and 145 patients with four additional pharmacokinetic parameters (volume fraction of extravascular extracellular space (ve), volume fraction of plasma space (vp), volume transfer constant (Ktrans), and reverse reflux rate constant (kep) of DCE-MR. A combined model integrating MR and DCE-MR was constructed. Utilizing methods such as correlation analysis, least absolute shrinkage and selection operator regression, and multivariate Cox proportional hazards regression, we built the radiomics models. Finally, we calculated the net reclassification index and C-index to evaluate and compare the prognostic performance of the radiomics models. Kaplan-Meier survival curve analysis was performed to investigate the model’s ability to stratify risk in patients with NPC. The integration of MR and DCE-MR radiomic features significantly enhanced prognostic prediction performance compared to MR- and DCE-MR-based models, evidenced by a test set C-index of 0.808 vs 0.729 and 0.731, respectively. The combined radiomics model improved net reclassification by 22.9%–52.6% and could significantly stratify the risk levels of patients with NPC (p = 0.036). Furthermore, the MR-based radiomic feature maps achieved similar results to the DCE-MR pharmacokinetic parameters in terms of reflecting the underlying angiogenesis information in NPC. Compared to conventional MR-based radiomics models, the combined radiomics model integrating MR and DCE-MR showed promising results in delivering more accurate prognostic predictions and provided more clinical benefits in quantifying and monitoring phenotypic changes associated with NPC prognosis.

Development of a Clinicopathological-Radiomics Model for Predicting Progression and Recurrence in Meningioma Patients

Tumor progression and recurrence（P/R）after surgical resection are common in meningioma patients and can indicate poor prognosis. This study aimed to investigate the values of clinicopathological information and preoperative magnetic resonance imaging (MRI) radiomics in predicting P/R and progression-free survival (PFS) in meningioma patients. A total of 169 patients with pathologically confirmed meningioma were included in this study, 54 of whom experienced P/R. Clinicopathological information, including age, gender, Simpson grading, World Health Organization (WHO) grading, Ki-67 index, and radiotherapy history, as well as preoperative traditional radiographic findings and radiomics features for each MRI modality (T1-weighted, T2-weighted, and enhanced T1-weighted images) were initially extracted. After feature selection, the optimal performance was estimated among the models established using different feature sets. Finally, Cox survival analysis was further used to predict PFS. Ki-67 index, Simpson grading, WHO grading, and radiotherapy history were found to be independent predictors for P/R in the multivariate regression analysis. This clinicopathological model had an area under the curve (AUC) of 0.865 and 0.817 in the training and testing sets, respectively. The performance of the combined radiomics model reached 0.85 and 0.84, respectively. A clinicopathological-radiomics model was then established, which significantly improved the prediction of meningioma P/R (AUC=0.93 and 0.88, respectively). Finally, the risk ratio was estimated for each selected feature, and the C-index of 0.749 was obtained. Radiomics signatures of preoperative MRI have the ability to predict meningioma at the risk of P/R. By integrating clinicopathological information, the best performance was achieved.

Dual-modal radiomics for predicting cervical lymph node metastasis in papillary thyroid carcinoma.

Preoperative prediction of cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) is significant for surgical decision-making. This study aims to develop a dual-modal radiomics (DMR) model based on grayscale ultrasound (GSUS) and dual-energy computed tomography (DECT) for non-invasive CLNM in PTC. In this study, 348 patients with pathologically confirmed PTC at Jiangsu University Affiliated People's Hospital who completed preoperative ultrasound (US) and DECT examinations were enrolled and randomly assigned to training (n = 261) and test (n = 87) cohorts. The enrolled patients were divided into two groups based on pathology findings namely, CLNM (n = 179) and CLNM-Free (n = 169). Radiomics features were extracted from GSUS images (464 features) and DECT images (960 features), respectively. Pearson correlation coefficient (PCC) and the least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation were then used to select CLNM-related features. Based on the selected features, GSUS, DECT, and GSUS combined DECT radiomics models were constructed by using a Support Vector Machine (SVM) classifier. Three predictive models based on GSUS, DECT, and a combination of GSUS and DECT, yielded performance of areas under the curve (AUC) = 0.700 [95% confidence interval (CI), 0.662-0.706], 0.721 [95% CI, 0.683-0.727], and 0.760 [95% CI, 0.728-0.762] in the training dataset, and AUC = 0.643 [95% CI, 0.582-0.734], 0.680 [95% CI, 0.623-0.772], and 0.744 [95% CI, 0.686-0.784] in the test dataset, respectively. It shows that the predictive model combined GSUS and DECT outperforms both models using GSUS and DECT only. The newly developed combined radiomics model could more accurately predict CLNM in PTC patients and aid in better surgical planning.

A Machine Learning-Based Unenhanced Radiomics Approach to Distinguishing Between Benign and Malignant Breast Lesions Using T2-Weighted and Diffusion-Weighted MRI.

Breast MRI has been recommended as supplemental screening tool to mammography and breast ultrasound of breast cancer by international guidelines, but its long examination time and use of contrast material remains concerning. To develop an unenhanced radiomics model with using non-gadolinium based sequences for detecting breast cancer based on T2-weighted (T2W) and diffusion-weighted (DW) MRI. Retrospective analysis followed by retrospective and prospective cohorts study. 1760 patients: Of these, 1293 for model construction (n = 775 for training and 518 for validation). The remaining patients for model testing in internal retrospective (n = 167), internal prospective (n = 188), and external retrospective (n = 112) cohorts. 3.0T MR scanners from two institution. T2WI, DWI, and first contrast-enhanced T1-weighted sequence. AUCs in distinguishing breast cancer were compared between combined model with gadolinium agent sequence and unenhanced model. Subsequently, the AUCs in testing cohorts of unenhanced model was compared with two radiologists' diagnosis for this research. Finally, patient subgroup analysis in testing cohorts was performed based on clinical subgroups and different types of malignancies. Mann-Whitney U test, Kruskal-Wallis H test, chi-square test, weighted kappa test, and DeLong's test. The unenhanced radiomics model performed best under Gaussian process (GP) classifiers (AUC: training, 0.893; validation, 0.848) compared to support vector machine (SVM) and logistic, showing favorable prediction in testing cohorts (AUCs, 0.818-0.840). The AUCs for the unenhanced radiomics model were not statistically different in five cohorts from those of the combined radiomics model (P, 0.317-0.816), as well as the two radiologists (P, 0.181-0.918). The unenhanced radiomics model was least successful in identifying ductal carcinoma in situ, whereas did not show statistical significance in other subgroups. An unenhanced radiomics model based on T2WI and DWI has comparable diagnostic accuracy to the combined model using the gadolinium agent. 4 TECHNICAL EFFICACY: Stage 2.

Study of radiochemotherapy decision-making for young high-risk low-grade glioma patients using a macroscopic and microscopic combined radiomics model.

As a few types of glioma, young high-risk low-grade gliomas (HRLGGs) have higher requirements for postoperative quality of life. Although adjuvant chemotherapy with delayed radiotherapy is the first treatment strategy for HRLGGs, not all HRLGGs benefit from it. Accurate assessment of chemosensitivity in HRLGGs is vital for making treatment choices. This study developed a multimodal fusion radiomics (MFR) model to support radiochemotherapy decision-making for HRLGGs. A MFR model combining macroscopic MRI and microscopic pathological images was proposed. Multiscale features including macroscopic tumor structure and microscopic histological layer and nuclear information were grabbed by unique paradigm, respectively. Then, these features were adaptively incorporated into the MFR model through attention mechanism to predict the chemosensitivity of temozolomide (TMZ) by means of objective response rate and progression free survival (PFS). Macroscopic tumor texture complexity and microscopic nuclear size showed significant statistical differences (p < 0.001) between sensitivity and insensitivity groups. The MFR model achieved stable prediction results, with an area under the curve of 0.950 (95% CI: 0.942-0.958), sensitivity of 0.833 (95% CI: 0.780-0.848), specificity of 0.929 (95% CI: 0.914-0.936), positive predictive value of 0.833 (95% CI: 0.811-0.860), and negative predictive value of 0.929 (95% CI: 0.914-0.934). The predictive efficacy of MFR was significantly higher than that of the reported molecular markers (p < 0.001). MFR was also demonstrated to be a predictor of PFS. A MFR model including radiomics and pathological features predicts accurately the response postoperative TMZ treatment. Our MFR model could identify young high-risk low-grade glioma patients who can have the most benefit from postoperative upfront temozolomide (TMZ) treatment. • Multimodal radiomics is proposed to support the radiochemotherapy of glioma. • Some macro and micro image markers related to tumor chemotherapy sensitivity are revealed. • The proposed model surpasses reported molecular markers, with a promising area under the curve (AUC) of 0.95.