Optimal Radiomic Features Research Articles

CT-based machine learning radiomics predicts CCR5 expression level and survival in ovarian cancer

ObjectiveWe aimed to evaluate the prognostic value of C-C motif chemokine receptor type 5 (CCR5) expression level for patients with ovarian cancer and to establish a radiomics model that can predict CCR5 expression level using The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) database.MethodsA total of 343 cases of ovarian cancer from the TCGA were used for the gene-based prognostic analysis. Fifty seven cases had preoperative computed tomography (CT) images stored in TCIA with genomic data in TCGA were used for radiomics feature extraction and model construction. 89 cases with both TCGA and TCIA clinical data were used for radiomics model evaluation. After feature extraction, a radiomics signature was constructed using the least absolute shrinkage and selection operator (LASSO) regression analysis. A prognostic scoring system incorporating radiomics signature based on CCR5 expression level and clinicopathologic risk factors was proposed for survival prediction.ResultsCCR5 was identified as a differentially expressed prognosis-related gene in tumor and normal sample, which were involved in the regulation of immune response and tumor invasion and metastasis. Four optimal radiomics features were selected to predict overall survival. The performance of the radiomics model for predicting the CCR5 expression level with 10-fold cross- validation achieved Area Under Curve (AUCs) of 0.770 and of 0.726, respectively, in the training and validation sets. A predictive nomogram was generated based on the total risk score of each patient, the AUCs of the time-dependent receiver operating characteristic (ROC) curve of the model was 0.8, 0.673 and 0.792 for 1-year, 3-year and 5-year, respectively. Along with clinical features, important imaging biomarkers could improve the overall survival accuracy of the prediction model.ConclusionThe expression levels of CCR5 can affect the prognosis of patients with ovarian cancer. CT-based radiomics could serve as a new tool for prognosis prediction.

A CT-Based Radiomics Nomogram Combined with Clinic-Radiological Characteristics for Preoperative Prediction of the Novel IASLC Grading of Invasive Pulmonary Adenocarcinoma

The novel International Association for the Study of Lung Cancer (IASLC) grading system of invasive lung adenocarcinoma (ADC) demonstrated a remarkable prognostic effect and enabled numerous patients to benefit from adjuvant chemotherapy. We sought to build a CT-based nomogram for preoperative prediction of the IASLC grading. This work retrospectively analyzed the CT images and clinical data of 303 patients with pathologically confirmed invasive ADC. The histological subtypes and radiological characteristics of the patients were re-evaluated. Radiomics features were extracted, and the optimal subset of features was established by ANOVA, spearman correlation analysis, and the least absolute shrinkage and selection operator (LASSO). Univariate and multivariate analyses identified the independent clinical and radiological variables. Finally, multivariate logistic regression analysis incorporated clinical, radiological, and optimal radiomics features into the nomogram. Receiver operating characteristic (ROC) curve, and accuracy were applied to assess the model's performance. Decision curve analysis (DCA), and calibration curve were applied to assess the clinical usefulness. Nine selected CT image features were used to develop the radiomics model. The accuracy, precision, sensitivity, and specificity of the radiomics model outperformed the clinic-radiological model in the training and testing sets. Integrating Radscore with independent radiological characteristics showed higher prediction performance than clinic-radiological characteristics alone in the training (AUC, 0.915 vs. 0.882; DeLong, p < 0.05) and testing (AUC, 0.838 vs. 0.782; DeLong, p < 0.05) sets. Good calibration and decision curve analysis demonstrated the clinical usefulness of the nomogram. Radiomics features effectively predict high-grade ADC. The combined nomogram may facilitate selecting patients who benefit from adjuvant treatment.

Development and validation of a combined model based on dual-sequence MRI radiomics for predicting the efficacy of high-intensity focused ultrasound ablation for hysteromyoma

Objectives To determine the value of dual-sequence magnetic resonance imaging (MRI)-based radiomics in predicting the efficacy of high-intensity focused ultrasound (HIFU) ablation for hysteromyoma. Methods A total of 142 patients with 172 hysteromyomas (95 hysteromyomas from the sufficient ablation group, and 77 hysteromyomas from the insufficient ablation group) were enrolled in the study. The clinical–radiological model was constructed with independent clinical–radiological risk factors, the radiomics model was constructed based on the optimal radiomics features of hysteromyoma from dual sequences, and the two groups of features were incorporated to construct the combined model. A fivefold cross validation procedure was adopted to validate these models. A nomogram was constructed, applying the combined model in the training cohort. The models were assessed with receiver operating characteristic (ROC) curves and integrated discrimination improvement (IDI). An independent test cohort comprising 40 patients was used to evaluate the performance of the optimal model. Results Among the three models, the average areas under the ROC curves (AUC) of the radiomics model and combined model were 0.803 (95% confidence interval (CI): 0.726–0.881) and 0.841 (95% CI: 0.772–0.909), which were better than the clinical–radiological model in the training cohort. The IDI showed that the combined model had the best prediction accuracy. The combined model also showed good discrimination in both the validation cohort (AUC = 0.834) and the independent test cohort (AUC = 0.801). Conclusion The combined model based on the dual-sequence MRI radiomics is the most promising tool from our study to assist clinicians in predicting HIFU ablation efficacy.

Radiomics-based signature of breast cancer on preoperative contrast-enhanced MRI to predict axillary metastasis.

Aim: This study aimed to predict axillary metastasis using radiology features in dynamic contrast-enhanced MRI. Methods: This study included 243 breast lesions confirmed as malignant based on axillary status. Most outcome-predictive features were selected using four machine-learning algorithms. Receiver operating characteristic analysis was used to reflect diagnostic performance. Results: Least absolute shrinkage and selection operator was used to dimensionally reduce 1137 radiomics features to threefeatures. Three optimal radiomics features were used to model construction. The logistic regression model achieved an accuracy of 97% and 85% in the training and test groups. Clinical utility was evaluated using decision curve analysis. Conclusion: The novel combination of radiomics analysis and machine-learning algorithm could predict axillary metastasis and prevent invasive manipulation.

A Nomogram Based on CT Radiomics and Clinical Risk Factors for Prediction of Prognosis of Hypertensive Intracerebral Hemorrhage.

To develop and validate a clinical-radiomics nomogram based on clinical risk factors and CT radiomics feature to predict hypertensive intracerebral hemorrhage (HICH) prognosis. A total of 195 patients with HICH treated in our hospital from January 2018 to January 2022 were retrospectively enrolled and randomly divided into two cohorts for training (n = 138) and validation (n = 57) according to the ratio of 7 : 3. All CT radiomics features were extracted from intrahematomal, perihematomal, and combined intra- and perihematomal regions by using free open-source software called 3D slicer. The least absolute shrinkage and selection operator method was used to select the optimal radiomics features, and the radiomics score (Rad-score) was calculated. The relationship between Rad-score, clinical risk factors, and the HICH prognosis was analyzed by univariate and multivariate logistic regression analyses, and the clinical-radiomics nomogram was built. The area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used to evaluate the performance of the clinical-radiomics nomogram in predicting the prognosis of HICH. A total of 1702 radiomics features were extracted from the CT images of each patient for analysis. By univariate and stepwise multivariate logistic regression analyses, age, sex, RBC, serum glucose, D-dimer level, hematoma volume, and midline shift were clinical risk factors for the prognosis of HICH. Rad-score and clinical risk factors developed the clinical-radiomics nomogram. The nomogram showed the highest predictive efficiency in the training cohort (AUC = 0.95, 95% confidence interval (CI), 0.92 to 0.98) and the validation cohort (AUC = 0.90, 95% CI, 0.82 to 0.98). The calibration curve indicated that the clinical-radiomics nomogram had good calibration. DCA showed that the nomogram had high applicability in clinical practice. The clinical-radiomics nomogram incorporated with the radiomics features and clinical risk factors has good potential in predicting the prognosis of HICH.

A Predictive Clinical-Radiomics Nomogram for Differentiating Tuberculous Spondylitis from Pyogenic Spondylitis Using CT and Clinical Risk Factors.

The study aimed to develop and validate a nomogram model with clinical risk factors and radiomic features for differentiating tuberculous spondylitis (TS) from pyogenic spondylitis (PS). A total of 254 patients with TS (n = 141) or PS (n = 113) were randomly divided into training (n = 180) and validation (n = 74) groups. In addition, 43 patients (TS = 22 and PS = 21) were collected to construct a test cohort. t-test analysis, de-redundancy analysis, and minimum absolute shrinkage and selection operator (lasso) algorithm were utilized on the training set to obtain the optimal radiomics features from computed tomography (CT) for constructing the radiomics model and determine the radiomics score (Rad-score). Eight clinical risk predictors were identified to develop the clinical model. Combined with clinical risk predictors and Rad-scores, a nomogram model was constructed using multivariate logistic regression analysis. A total of 1781 features were extracted, and 12 optimal radiomic features were utilized to construct the radiomic model and determine the Rad-score. The combined clinical radiomics model revealed good discrimination performance in both the training cohort and the validation cohort (AUC =0.891 and 0.830) and was superior to the clinical (AUC =0.807 and 0.785) and radiomics (AUC =0.796 and 0.811) models. The calibration curve and DCA also depicted that the nomogram had better clinical efficacy. The discriminative performance of the model is well validated in the test cohort (AUC=0.877). The clinical radiomic nomogram could serve as a promising predictive tool for differentiating TS from PS, which could be helpful for clinical decision-making.

Predicting IDH Mutation Status in Low-Grade Gliomas Based on Optimal Radiomic Features Combined with Multi-Sequence Magnetic Resonance Imaging.

The IDH somatic mutation status is an important basis for the diagnosis and classification of gliomas. We proposed a "6-Step" general radiomics model to noninvasively predict the IDH mutation status by simultaneously tuning combined multi-sequence MRI and optimizing the full radiomics processing pipeline. Radiomic features (n = 3776) were extracted from multi-sequence MRI (T1, T2, FLAIR, and T1Gd) in low-grade gliomas (LGGs), and a total of 45,360 radiomics pipeline were investigated according to different settings. The predictive ability of the general radiomics model was evaluated with regards to accuracy, stability, and efficiency. Based on numerous experiments, we finally reached an optimal pipeline for classifying IDH mutation status, namely the T2+FLAIR combined multi-sequence with the wavelet image filter, mean data normalization, PCC dimension reduction, RFE feature selection, and SVM classifier. The mean and standard deviation of AUC, accuracy, sensitivity, and specificity were 0.873 ± 0.05, 0.876 ± 0.09, 0.875 ± 0.11, and 0.877 ± 0.15, respectively. Furthermore, 14 radiomic features that best distinguished the IDH mutation status of the T2+FLAIR multi-sequence were analyzed, and the gray level co-occurrence matrix (GLCM) features were shown to be of high importance. Apart from the promising prediction of the molecular subtypes, this study also provided a general tool for radiomics investigation.

Application of enhanced computed tomography-based radiomics nomogram analysis to differentiate metastatic ovarian tumors from epithelial ovarian tumors.

To investigate the value of nomogram analysis based on conventional features and radiomics features of computed tomography (CT) venous phase to differentiate metastatic ovarian tumors (MOTs) from epithelial ovarian tumors (EOTs). A dataset involving 286 patients pathologically confirmed with EOTs (training cohort: 133 cases, validation cohort: 68 cases) and MOTs (training cohort: 54 cases, validation cohort: 31 cases) is assembled in this study. Radiomics features are extracted from the venous phase of CT images. Logistic regression is employed to build models based on conventional features (model 1), radiomics features (model 2), and the combination of model 1 and model 2 (model 3). Diagnostic performance is assessed and compared. Additionally, a nomogram is plotted for model 3, and decision curve analysis is applied for clinical use. Age, abdominal metastasis, para-aortic lymph node metastasis, location, and septation are chosen to build Model 1. Ten optimal radiomics features are ultimately selected and radiomics score (rad-score) is calculated to build Model 2. Nomogram score is calculated to build model 3 that shows optimal diagnostic performance in both the training (AUC = 0.952) and validation cohorts (AUC = 0.720), followed by model 1 (AUC = 0.872 for training cohort and AUC = 0.709 for validation cohort) and model 2 (AUC = 0.833 for training cohort and AUC = 0.620 for validation cohort). Additionally, Model 3 achieves accuracy, sensitivity, and specificity of 0.893, 0.880, and 0.926 in the training cohort and 0.737, 0.853, and 0.613 in the validation cohort. Model 3 demonstrates the best diagnostic performance for preoperative differentiation of MOTs from EOTs. Thus, nomogram analysis based on Model 3 may be used as a biomarker to differentiate MOTs from EOTs.

Feasibility of ultrasound radiomics-based models for classification of hepatic echinococcosis

To investigate the feasibility of establishment of ultrasound radiomics-based models for classification of hepatic echinococcosis, so as to provide insights into precision ultrasound diagnosis of hepatic echinococcosis. The ultrasonographic images were retrospectively collected from 200 patients with hepatic echinococcosis in Shiqu County, Ganzi Tibetan Autonomous Prefecture, Sichuan Province in October 2014, and the regions of interest were plotted in ultrasonographic images of hepatic echinococcosis lesions. The ultrasound radiomics features of hepatic echinococcosis were extracted with 25 methods, and screened using pre-selection and the least absolute shrinkage and selection operator. Then, all ultrasonographic images were randomly assigned into the training and independent test sets according to the type of lesions at a ratio of 7:3. Machine learning models for classification of hepatic echinococcosis were created based on two classifiers, including kernel logistic regression (KLR) and medium Gaussian support vector machine (MGSVM). The receiver operating characteristic (ROC) curves were plotted, and the sensitivity, specificity and areas under the curves (AUC) of the created machine learning models for classification of hepatic echinococcosis were calculated. A total of 5 005 ultrasound radiomics features were extracted from 200 patients with hepatic echinococcosis using 25 methods, and 36 optimal radiomics features were screened through feature selection, based on which two machine learning models were created, including KLR and MGSVM. ROC curve analysis showed that MGS-VM presented a higher efficacy for hepatic echinococcosis classification than KLR in the training set, with a sensitivity of 0.82, a specificity of 0.78 and AUC of 0.88, while KLR presented a higher efficacy for hepatic echinococcosis classification than MGSVM in the independent test set, with a sensitivity of 0.82, a specificity of 0.72 and AUC of 0.86, respectively. Ultrasound radiomics-based machine learning models are feasible for hepatic echinococcosis classification.

Prediction of therapeutic response of unresectable hepatocellular carcinoma to hepatic arterial infusion chemotherapy based on pretherapeutic MRI radiomics and Albumin-Bilirubin score

PurposeTo construct and validate a combined nomogram model based on magnetic resonance imaging (MRI) radiomics and Albumin-Bilirubin (ALBI) score to predict therapeutic response in unresectable hepatocellular carcinoma (HCC) patients treated with hepatic arterial infusion chemotherapy (HAIC).MethodsThe retrospective study was conducted on 112 unresectable HCC patients who underwent pretherapeutic MRI examinations. Patients were randomly divided into training (n = 79) and validation cohorts (n = 33). A total of 396 radiomics features were extracted from the volume of interest of the primary lesion by the Artificial Kit software. The least absolute shrinkage and selection operator (LASSO) regression was applied to identify optimal radiomic features. After feature selection, three models, including the clinical, radiomics, and combined models, were developed to predict the non-response of unresectable HCC to HAIC treatment. The performance of these models was evaluated by the receiver operating characteristic curve. According to the most efficient model, a nomogram was established, and the performance of which was also assessed by calibration curve and decision curve analysis. Kaplan–Meier curve and log-rank test were performed to evaluate the Progression-free survival (PFS).ResultsUsing the LASSO regression, we ultimately selected three radiomics features from T2-weighted images to construct the radiomics score (Radscore). Only the ALBI score was an independent factor associated with non-response in the clinical model (P = 0.033). The combined model, which included the ALBI score and Radscore, achieved better performance in the prediction of non-response, with an AUC of 0.79 (95% CI 0.68–0.90) and 0.75 (95% CI 0.58–0.92) in the training and validation cohorts, respectively. The nomogram based on the combined model also had good discrimination and calibration (P = 0.519 for the training cohort and P = 0.389 for the validation cohort). The Kaplan–Meier analysis also demonstrate that the high-score patients had significantly shorter PFS than the low-score patients (P = 0.031) in the combined model, with median PFS 6.0 vs 9.0 months.ConclusionThe nomogram based on the combined model consisting of MRI radiomics and ALBI score could be used as a biomarker to predict the therapeutic response of unresectable HCC after HAIC.

Value of Presurgical 18F-FDG PET/CT Radiomics for Predicting Mediastinal Lymph Node Metastasis in Patients with Lung Adenocarcinoma.

Objective: The aim of this study was to develop a 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic model for predicting mediastinal lymph node metastasis (LNM) in presurgical patients with lung adenocarcinoma. Methods: The study enrolled 320 patients with lung adenocarcinoma (288 internal and 32 external cases) and extracted 190 radiomic features using the LIFEx package. Optimal radiomic features to build a radiomic model were selected using the least absolute shrinkage and selection operator algorithm. Logistic regression was used to build the clinical and complex (combined radiomic and clinical variables) models. Results: Ten radiomic features were selected. In the training group, the area under the receiver operating characteristic curve of the complex model was significantly higher than that of the radiomic and clinical models [0.924 (95% CI: 0.887-0.961) vs. 0.863 (95% CI: 0.814-0.912; p = 0.001) and 0.838 (95% CI: 0.783-0.894; p = 0.000), respectively]. The sensitivity, specificity, accuracy, and positive and negative predictive values of the radiomic model were 0.857, 0.790, 0.811, and 0.651 and 0.924, respectively, which were better than that of visual evaluation (0.539, 0.724, 0.667, and 0.472 and 0.775, respectively) and PET semiquantitative analyses (0.619, 0.732, 0.697, and 0.513 and 0.808, respectively). Conclusions: 18F-FDG PET/CT radiomics showed good predictive performance for LNM and improved the N-stage accuracy of lung adenocarcinoma.

The value of a nomogram based on clinical data and contrast enhanced CT radiomics in the preoperative prediction of Epstein-Barr virus-associated gastric carcinoma

Objective: To explore the value of a nomogram based on clinical data and enhanced CT radiomics in the prediction of Epstein-Barr virus-associated gastric carcinoma(EBVaGC). Methods: The data of 136 patients, including 100 males and 36 females, aged [M (Q1, Q3)] 65 (53, 71) years, with gastric cancer confirmed by surgery and pathology were retrospectively analyzed. According to Epstein-Barr virus-encoded small RNA (EBER) in situ hybridization, those patients were divided into Epstein-Barr virus (EBV) positive group (n=32) and EBV negative group (n=104). All patients underwent multi-phase enhanced CT scanning before surgery and randomly assigned to the training group (n=95) and validation group (n=41) in a ratio of 7︰3. MaZda software was used to extract radiomics features of enhanced CT images. The intra-group correlation coefficient (ICC), variance analysis and minimum absolute shrinkage and selection algorithm (LASSO) regression were used to reduce the dimensionality of the radiomics features, and then the radiomics score (Radscore) was calculated. The nomogram model was based on combined clinical data, morphological features and Radscore. The predictive power of the nomogram was evaluated according to the area under the receiver operating characteristic curve (AUC), and the net clinical benefit of the nomogram was evaluated by the decision curve and calibration curves were drawn according to the data of the training group and the validation group to analyze the consistency of the nomogram model. Results: After selection, six optimal radiomics features were obtained, including Mean, Skewness, S(1, 0) Sum entropy, S(1, 1) Contrast, 99% percentile and S(2, 2)Angular second moment. Radscore of EBV positive group were higher than that of the EBV negative group (training group: 3.78±0.83 vs 2.80±0.98; validation group: 3.81±0.47 vs 2.94±0.95) (both P<0.05) both in the training group and validation group. The AUC of the radiomics model in training group and validation group were 0.773(95%CI:0.612-0.962)and 0.792(95%CI:0.597-0.927)respectively,and the sensitivity and specificity were 63.6% and 93.1%, 70.0% and 87.1%, respectively. The AUC of the nomogram model based on clinical data and radiomics in the training group and the validation group were 0.883(95%CI:0.644-0.984) and 0.851(95%CI:0.715-0.996), respectively. The nomogram model showed superior predictive performance (both P<0.05). Conclusion: The nomogram model based on clinical data and radiomics has better efficacy in the prediction of Epstein-Barr virus associated gastric cancer.

Prognostic Value of the Radiomics-Based Model in the Disease-Free Survival of Pretreatment Uveal Melanoma: An Initial Result.

The aim of this study was to develop a pretreatment magnetic resonance imaging (MRI)-based radiomics model for disease-free survival (DFS) prediction in patients with uveal melanoma (UM). We randomly assigned 85 patients with UM into 2 cohorts: training (n = 60) and validation (n = 25). The radiomics model was built from significant features that were selected from the training cohort by applying a least absolute shrinkage and selection operator to pretreatment MRI scans. Least absolute shrinkage and selection operator regression and the Cox proportional hazard model were used to construct a radiomics score (rad-score). Patients were divided into a low- or a high-risk group based on the median of the rad-score. The Kaplan-Meier analysis was used to evaluate the association between the rad-score and DFS. A nomogram incorporating the rad-score and MRI features was plotted to individually estimate DFS. The model's discrimination power was assessed using the concordance index. The radiomics model with 15 optimal radiomics features based on MRI performed well in stratifying patients into the high- or a low-risk group of DFS in both the training and validation cohorts (log-rank test, P = 0.009 and P = 0.02, respectively). Age, basal diameter, and height were selected as significant clinical and MRI features. The nomogram showed good predictive performance with concordance indices of 0.741 (95% confidence interval, 0.637-0.845) and 0.912 (95% confidence interval, 0.847-0.977) in the training and validation cohorts, respectively. Calibration curves demonstrated good agreement. The developed clinical-radiomics model may be a powerful predictor of the DFS of patients with UM, thereby providing evidence for preoperative risk stratification.

Differentiating Primary Tumors for Brain Metastasis with Integrated Radiomics from Multiple Imaging Modalities

Objectives To differentiate the primary site of brain metastases (BMs) is of high clinical value for the successful management of patients with BM. The purpose of this study is to investigate a combined radiomics model with computer tomography (CT) and magnetic resonance imaging (MRI) images in differentiating BMs originated from lung and breast cancer. Methods Pretreatment cerebral contrast enhanced CT and T1-weighted MRI images of 78 patients with 179 BMs from primary lung and breast cancer were retrospectively analyzed. Radiomic features were extracted from contoured BM lesions and selected using the Mann–Whitney U test and the least absolute shrinkage and selection operator (LASSO) logistic regression. Binary logistic regression (BLR) and support vector machine (SVM) models were built and evaluated based on selected radiomic features from CT alone, MRI alone, and combined images to differentiate BMs originated from lung and breast cancer. Results A total of 10 and 6 optimal radiomic features were screened out of 1288 CT and 1197 MRI features, respectively. The mean area under the curves (AUCs) of the BLR and SVM models using fivefolds cross-validation were 0.703 vs. 0.751, 0.718 vs. 0.754, and 0.781 vs. 0.803 in the training dataset and 0.708 vs. 0.763, 0.715 vs. 0.717, and 0.771 vs. 0.805 in the testing dataset for models with CT alone, MRI alone, and combined CT and MRI radiomic features, respectively. Conclusions Radiomics model based on combined CT and MRI features is feasible and accurate in the differentiation of the primary site of BMs from lung and breast cancer.

A comparative study for the evaluation of CT-based conventional, radiomic, combined conventional and radiomic, and delta-radiomic features, and the prediction of the invasiveness of lung adenocarcinoma manifesting as ground-glass nodules

To investigate and compare the performance of conventional, radiomic, combined, and delta-radiomic features to predict the invasiveness of lung adenocarcinoma manifesting as ground-glass nodules (GGNs). The present retrospective study included 216 GGNs confirmed surgically as pulmonary adenocarcinomas. All the thin-section computed tomography (CT) images were imported into the software of the United Imaging Intelligence research portal, and radiomic features were extracted with three-dimensional (3D) regions of interest. Least Absolute Shrinkage and Selection Operator was used to select the optimal radiomic features. Four models were constructed, including conventional, radiomic, combined conventional and radiomic, and delta-radiomic models. The receiver operating characteristic curves were built to evaluate the validity of these. The type, long diameter, shape, margin, vacuole, air bronchus, vascular convergence, and pleural traction exhibited significant differences between pre-invasive lesions (PILs)/minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IA) groups were selected for conventional model building. Nine radiomic features were selected to build the radiomic model. The four models indicated optimal performance (AUC>0.7). The radiomic and combined models exhibited the highest diagnostic efficiency, and their AUC were 0.89 and 0.88 in the training set, and 0.87 and 0.88 in the validation set, respectively. The delta-radiomic model indicated that the AUC was 0.83 in the training set, and 0.76 in the validation set. Finally, the conventional model exhibited an AUC in the training and validation sets of 0.78 and 0.76. The radiomic model and combined model, in particular, and the delta-radiomic model all demonstrated improved diagnostic efficiency in differentiating IA from PIL/MIA than that of the conventional model.

Development and Validation of a CT-Based Radiomics Nomogram in Patients With Anterior Mediastinal Mass: Individualized Options for Preoperative Patients

BackgroundTo improve the preoperative diagnostic accuracy and reduce the non-therapeutic thymectomy rate, we established a comprehensive predictive nomogram based on radiomics data and computed tomography (CT) features and further explored its potential use in clinical decision-making for anterior mediastinal masses (AMMs).MethodsA total of 280 patients, including 280 with unenhanced CT (UECT) and 241 with contrast-enhanced CT (CECT) scans, all of whom had undergone thymectomy for AMM with confirmed histopathology, were enrolled in this study. A total of 1,288 radiomics features were extracted from each labeled mass. The least absolute shrinkage and selection operator model was used to select the optimal radiomics features in the training set to construct the radscore. Multivariate logistic regression analysis was conducted to establish a combined clinical radiographic radscore model, and an individualized prediction nomogram was developed.ResultsIn the UECT dataset, radscore and the UECT ratio were selected for the nomogram. The combined model achieved higher accuracy (AUC: 0.870) than the clinical model (AUC: 0.752) for the prediction of therapeutic thymectomy probability. In the CECT dataset, the clinical and combined models achieved higher accuracy (AUC: 0.851 and 0.836, respectively) than the radscore model (AUC: 0.618) for the prediction of therapeutic thymectomy probability.ConclusionsIn patients who underwent UECT only, a nomogram integrating the radscore and the UECT ratio achieved good accuracy in predicting therapeutic thymectomy in AMMs. However, the use of radiomics in patients with CECT scans did not improve prediction performance; therefore, a clinical model is recommended.

MRI-based radiomics analysis in differentiating solid non-small-cell from small-cell lung carcinoma: a pilot study

To investigate the ability of a T2-weighted (W) magnetic resonance imaging (MRI)-based radiomics signature to differentiate solid non-small-cell lung carcinoma (NSCLC) from small-cell lung carcinoma (SCLC). The present retrospective study enrolled 152 eligible patients (NSCLC=125, SCLC=27). All patients underwent MRI using a 3 T scanner and radiomics features were extracted from T2W MRI. The least absolute shrinkage and selection operator (LASSO) logistic regression model was used to identify the optimal radiomics features for the construction of a radiomics model to differentiate solid NSCLC from SCLC. Threefold cross validation repeated 10 times was used for model training and evaluation. The conventional MRI morphology features of the lesions were also evaluated. The performance of the conventional MRI morphological features, and the radiomics signature model and nomogram model (combining radiomics signature with conventional MRI morphological features) was evaluated using receiver operating characteristic (ROC) curve analysis. Five optimal features were chosen to build a radiomics signature. There was no significant difference in age, gender, and the largest diameter. The radiomics signature and conventional MRI morphological features (only pleural indentation and lymph node enlargement) were independent predictive factors for differentiating solid NSCLC from SCLC. The area under the ROC curves (AUCs) for MRI morphological features, and the radiomics model, and nomogram model was 0.69, 0.85, and 0.90 (ROC), respectively. The T2W MRI-based radiomics signature is a potential non-invasive approach for distinguishing solid NSCLC from SCLC.

Radiomics for identifying lung adenocarcinomas with predominant lepidic growth manifesting as large pure ground-glass nodules on CT images.

PurposeTo explore the value of radiomics in the identification of lung adenocarcinomas with predominant lepidic growth in pure ground-glass nodules (pGGNs) larger than 10 mm.MethodsWe retrospectively analyzed CT images of 204 patients with large pGGNs (≥ 10 mm) pathologically diagnosed as minimally invasive adenocarcinomas (MIAs), lepidic predominant adenocarcinomas (LPAs), and non-lepidic predominant adenocarcinomas (NLPAs). All pGGNs in the two groups (MIA/LPA and NLPA) were randomly divided into training and test cohorts. Forty-seven patients from another center formed the external validation cohort. Baseline features, including clinical data and CT morphological and quantitative parameters, were collected to establish a baseline model. The radiomics model was built with the optimal radiomics features. The combined model was developed using the rad_score and independent baseline predictors. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test. The differential diagnosis performance of the models was compared with three radiologists (with 20+, 10+, and 3 years of experience) in the test cohort.ResultsThe radiomics (training AUC: 0.833; test AUC: 0.804; and external validation AUC: 0.792) and combined (AUC: 0.849, 0.820, and 0.775, respectively) models performed better for discriminating than the baseline model (AUC: 0.756, 0.762, and 0.725, respectively) developed by tumor location and mean CT value of the whole nodule. The DeLong test showed that the AUCs of the combined and radiomics models were significantly increased in the training cohort. The highest AUC value of the radiologists was 0.600.ConclusionThe application of CT radiomics improved the identification performance of lung adenocarcinomas with predominant lepidic growth appearing as pGGNs larger than 10 mm.

Radiomics Analysis of Computed Tomography for Prediction of Thyroid Capsule Invasion in Papillary Thyroid Carcinoma: A Multi-Classifier and Two-Center Study.

ObjectiveTo investigate the application of computed tomography (CT)-based radiomics model for prediction of thyroid capsule invasion (TCI) in papillary thyroid carcinoma (PTC).MethodsThis retrospective study recruited 412 consecutive PTC patients from two independent institutions and randomly assigned to training (n=265), internal test (n=114) and external test (n=33) cohorts. Radiomics features were extracted from non-contrast (NC) and artery phase (AP) CT scans. We also calculated delta radiomics features, which are defined as the absolute differences between the extracted radiomics features. One-way analysis of variance and least absolute shrinkage and selection operator were used to select optimal radiomics features. Then, six supervised machine learning radiomics models (k-nearest neighbor, logistic regression, decision tree, linear support vector machine [L-SVM], Gaussian-SVM, and polynomial-SVM) were constructed. Univariate was used to select clinicoradiological risk factors. Combined models including optimal radiomics features and clinicoradiological risk factors were constructed by these six classifiers. The prediction performance was evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).ResultsIn the internal test cohort, the best combined model (L-SVM, AUC=0.820 [95% CI 0.758–0.888]) performed better than the best radiomics model (L-SVM, AUC = 0.733 [95% CI 0.654–0.812]) and the clinical model (AUC = 0.709 [95% CI 0.649–0.783]). Combined-L-SVM model combines 23 radiomics features and 1 clinicoradiological risk factor (CT-reported TCI). In the external test cohort, the AUC was 0.776 (0.625–0.904) in the combined-L-SVM model, showing that the model is stable. DCA demonstrated that the combined model was clinically useful.ConclusionsOur combined model based on machine learning incorporated with CT radiomics features and the clinicoradiological risk factor shows good predictive ability for TCI in PTC.

Prediction Breast Molecular Typing of Invasive Ductal Carcinoma Based on Dynamic Contrast Enhancement Magnetic Resonance Imaging Radiomics Characteristics: A Feasibility Study.

ObjectiveTo investigate the feasibility of radiomics in predicting molecular subtype of breast invasive ductal carcinoma (IDC) based on dynamic contrast enhancement magnetic resonance imaging (DCE-MRI).MethodsA total of 303 cases with pathologically confirmed IDC from January 2018 to March 2021 were enrolled in this study, including 223 cases from Fudan University Shanghai Cancer Center (training/test set) and 80 cases from Shaoxing Central Hospital (validation set). All the cases were classified as HR+/Luminal, HER2-enriched, and TNBC according to immunohistochemistry. DCE-MRI original images were treated by semi-automated segmentation to initially extract original and wavelet-transformed radiomic features. The extended logistic regression with least absolute shrinkage and selection operator (LASSO) penalty was applied to identify the optimal radiomic features, which were then used to establish predictive models combined with significant clinical risk factors. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis were adopted to evaluate the effectiveness and clinical benefit of the models established.ResultsOf the 223 cases from Fudan University Shanghai Cancer Center, HR+/Luminal cancers were diagnosed in 116 cases (52.02%), HER2-enriched in 71 cases (31.84%), and TNBC in 36 cases (16.14%). Based on the training set, 788 radiomic features were extracted in total and 8 optimal features were further identified, including 2 first-order features, 1 gray-level run length matrix (GLRLM), 4 gray-level co-occurrence matrices (GLCM), and 1 3D shape feature. Three multi-class classification models were constructed by extended logistic regression: clinical model (age, menopause, tumor location, Ki-67, histological grade, and lymph node metastasis), radiomic model, and combined model. The macro-average areas under the ROC curve (macro-AUC) for the three models were 0.71, 0.81, and 0.84 in the training set, 0.73, 0.81, and 0.84 in the test set, and 0.76, 0.82, and 0.83 in the validation set, respectively.ConclusionThe DCE-MRI-based radiomic features are significant biomarkers for distinguishing molecular subtypes of breast cancer noninvasively. Notably, the classification performance could be improved with the fusion analysis of multi-modal features.