Construction and Validation of a Nomogram Based on Radiomics and Clinical Features for Discerning Malignant Soft Tissue Tumors.

Comparative Analysis of Nomogram and Machine Learning Models for Predicting Axillary Lymph Node Metastasis in Early-Stage Breast Cancer: A Study on Clinically and Ultrasound-Negative Axillary Cases Across Two Centers

To evaluate the diagnostic performance of a model combining gray-scale ultrasound (US) radiomic features and clinical data in distinguishing benign from malignant breast masses classified as Breast Imaging Reporting and Data System (BI-RADS) category 4. In this retrospective study, 149 women with pathologically confirmed breast masses were included and randomly divided into a training cohort (n=104) and a validation cohort (n=45). A total of 1,046 radiomic features were extracted from US images. Feature selection was performed using Pearson correlation analysis followed by least absolute shrinkage and selection operator (LASSO) regression. Three K-nearest neighbor (KNN) classifiers were developed: a clinical model, an ultrasound radiomics (USR) model, and a combined clinical-USR model. Model performance was assessed using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). Seven radiomic features and two clinical variables were selected for model construction. In the training cohort, the combined clinical-USR model achieved an AUC of 0.927, with an accuracy of 89.0%, sensitivity of 88.9%, and specificity of 89.8%. In the validation cohort, the AUC of 0.826, with an accuracy of 80.0%, sensitivity of 83.3%, and specificity of 66.7%. The standalone USR model yielded AUCs of 0.902 and 0.883 in the training and validation cohorts, respectively, while the clinical model showed lower AUCs of 0.876 and 0.794. Decision curve analysis (DCA) indicated that the combined model provided a greater net clinical benefit than the clinical model alone. The integration of ultrasound radiomic features with clinical data improves diagnostic performance in differentiating benign from malignant BI-RADS 4 breast masses. The combined model holds potential for aiding clinical decision-making but requires further validation in larger, independent datasets.

Multi-region nomogram for predicting central lymph node metastasis in papillary thyroid carcinoma using multimodal imaging: A multicenter study.

BackgroundTo evaluate the clinical utility of ultrasound radiomics in predicting parotid lymph node metastasis (PLNM) in nasopharyngeal carcinoma (NPC) patients.MethodsGrayscale ultrasound (US) images of parotid gland nodules were segmented, and radiomics features were extracted. An support vector machine (SVM) model was built using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm for feature selection. Different SVM models were built based on clinical characteristics, radiomics features, and a combination of these features. Performance of the models was assessed using the area under the curve (AUCs), sensitivity and specificity.ResultsAmong 406 patients (192 PLNM, 214 benign), a total of 406 nodules were included in this study. Thirty-one radiomics features were selected as significant using the LASSO algorithm from the 474 extracted radiomics features. In the clinical model, NPC patients with suspicious parotid gland nodules of irregular shape, poorly defined margins, long/short axis ratio (LSR) <1, and posterior acoustic enhancement (PAE) were significant variables for PLNM (p<0.05). In the validation dataset, the AUC were 0.916 (95% CI: 0.876–0.983) in the clinical model, 0.830 (95% CI: 0.784–0.872) in the single radiomics model, and 0.928 (95% CI: 0.792–0.945) in the combined model. The calibration curve of the different models and decision curve analysis (DCA) demonstrated the diagnostic performance of the combined model.ConclusionThe combined model using ultrasound radiomics has clinical utility in identifying useful US features and enhancing the diagnostic accuracy of ultrasound for detecting PLNM in patients with NPC.

Henoch-Schönlein purpura nephritis (HSPN) is one of the most common kidney diseases in children. The current diagnosis and classification of HSPN depend on pathological biopsy, which is seriously limited by its invasive and high-risk nature. The aim of the study was to explore the potential of radiomics model for evaluating the histopathological classification of HSPN based on the ultrasound (US) images. A total of 440 patients with Henoch-Schönlein purpura nephritis proved by biopsy were analyzed retrospectively. They were grouped according to two histopathological categories: those without glomerular crescent formation (ISKDC grades I-II) and those with glomerular crescent formation (ISKDC grades III-V). The patients were randomly assigned to either a training cohort (n = 308) or a validation cohort (n = 132) with a ratio of 7:3. The sonologist manually drew the regions of interest (ROI) on the ultrasound images of the right kidney including the cortex and medulla. Then, the ultrasound radiomics features were extracted using the Pyradiomics package. The dimensions of radiomics features were reduced by Spearman correlation coefficients and least absolute shrinkage and selection operator (LASSO) method. Finally, three radiomics models using k-nearest neighbor (KNN), logistic regression (LR), and support vector machine (SVM) were established, respectively. The predictive performance of such classifiers was assessed with receiver operating characteristic (ROC) curve. 105 radiomics features were extracted from derived US images of each patient and 14 features were ultimately selected for the machine learning analysis. Three machine learning models including k-nearest neighbor (KNN), logistic regression (LR), and support vector machine (SVM) were established for HSPN classification. Of the three classifiers, the SVM classifier performed the best in the validation cohort [area under the curve (AUC) =0.870 (95% CI, 0.795-0.944), sensitivity = 0.706, specificity = 0.950]. The US-based radiomics had good predictive value for HSPN classification, which can be served as a noninvasive tool to evaluate the severity of renal pathology and crescentic formation in children with HSPN.

Follicular thyroid carcinoma (FTC) is the second most common thyroid cancer. Preoperative differentiation between benign and malignant follicular tumors remains challenging using ultrasound and fine needle aspiration biopsy (FNAB). Radiomics quantitatively evaluates diseases by extracting and analyzing features from medical images. This study aimed to assess the diagnostic value of ultrasound radiomics in distinguishing follicular thyroid carcinoma (FTC) from follicular thyroid adenoma (FTA) among TI-RADS 4a nodules. A retrospective analysis was conducted on the ultrasound images from 144 patients with TI-RADS 4a follicular thyroid neoplasms who underwent their first surgery in our hospital from January 2018 to June 2024. First, ultrasonographic characteristics (US) were analyzed from ultrasound images and diagnostic reports to build a US model. Second, ultrasound radiomics features were extracted from ultrasound images by the software of 3D-Slicer. According to the postoperative pathological results, the patients were divided into FTC group and FTA group. Following the principle of random allocation, the ratio of the training group (n = 86) to the validation group (n = 58) was 6:4. The ultrasound radiomics features were selected by the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm in order to build a radiomics model. Finally, a combined model integrating ultrasonographic characteristics and radiomics features (combined-model) was developed. All models including US model, radiomics model and combined-model were built through multi-factor logistic regression analysis to differentiate and diagnose follicular thyroid neoplasms. The receiver operating characteristic curve (ROC), precision, recall and F1-Score were used to evaluate the efficacy of the models. One hundred forty-four patients with TI-RADS 4a follicular thyroid neoplasms were divided into FTC group (41 cases) and FTA group (103 cases) based on postoperative pathological results. A total of 858 ultrasound radiomics features were extracted from the ultrasound images. After screening, six optimal radiomics features were obtained. Among the three models, the combined-model demonstrated best performance in differentiating FTC from FTA, with the area under the curve (AUC) of 0.839 (95% CI: 0.663-1.000) in the validation group. The F1-Score reflected a balance between precision and recall, with overall performance being superior. Combined model of ultrasonographic characteristics and radiomics may be useful to distinguish FTC from FTA.

To retrospectively assess the effectiveness of deep learning (DL) model, based on breast magnetic resonance imaging (MRI), in predicting preoperative lymphovascular invasion (LVI) status in patients diagnosed with invasive breast cancer who have negative axillary lymph nodes (LNs). Data was gathered from 280 patients, including 148 with LVI-positive and 141 with LVI-negative lesions. These patients had undergone preoperative breast MRI and were histopathologically confirmed to have invasive breast cancer without axillary LN metastasis. The cohort was randomly split into training and validation groups in a 7:3 ratio. Radiomics features for each lesion were extracted from the first post-contrast dynamic contrast-enhanced (DCE)-MRI. The Least Absolute Shrinkage and Selection Operator (LASSO) regression method and logistic regression analyses were employed to identify significant radiomic features and clinicoradiological variables. These models were established using four machine learning (ML) algorithms and one DL algorithm. The predictive performance of the models (radiomics, clinicoradiological, and combination) was assessed through discrimination and compared using the DeLong test. Four clinicoradiological parameters and 10 radiomic features were selected by LASSO for model development. The Multilayer Perceptron (MLP) model, constructed using both radiomic and clinicoradiological features, demonstrated excellent performance in predicting LVI, achieving a high area under the curve (AUC) of 0.835 for validation. The DL model (MLP-radiomic) achieved the highest accuracy (AUC = 0.896), followed by DL model (MLP-combination) with an AUC of 0.835. Both DL models were significantly superior to the ML model (RF-clinical) with an AUC of 0.720. The DL model (MLP), which integrates radiomic features with clinicoradiological information, effectively aids in the preoperative determination of LVI status in patients with invasive breast cancer and negative axillary LNs. This is beneficial for making informed clinical decisions.

BackgroundA single institution retrospective analysis of 124 non‐small cell lung carcinoma (NSCLC) patients was performed to identify whether disease‐free survival (DFS) achieves incremental values when radiomic and genomic data are combined with clinical information.MethodsUsing the least absolute shrinkage and selection operator (LASSO) Cox regression method, radiomic and genetic features were reduced in number for selection of the most useful prognostic feature. We created four models using only baseline clinical data, clinical data with selected genetic features, clinical data with selected radiomic features, and clinical data with selected genetic and radiomic features together. Multivariate Cox proportional hazards analysis was performed to determine predictors of DFS. Receiver operating characteristic (ROC) calculation was made to compare the discriminative performance for DFS prediction by four constructed models at the five‐year time point.ResultsOn precontrast scan, improved discrimination performance was obtained in a merging of selected radiomics and genetics (AUC = 0.8638), compared with clinical data only (AUC = 0.7990), selected genetic features (AUC = 0.8497), and selected radiomic features (AUC = 0.8355). On post‐contrast scan, discrimination performance was improved (AUC = 0.8672) compared with the clinical variables (AUC = 0.7913), and selected genetic features (AUC = 0.8376) and selected radiomic features (AUC = 0.8399) were considered.ConclusionsThe combination of selected radiomic and genomic features improved stratification of NSCLC patients upon survival. Thus, integrating clinicopathologic model with radiomic and genomic features may lead to improved prognostic accuracy compared to conventional clinicopathological data alone.Key pointsSignificant findings of the studyReceiver operating characteristic (ROC) calculation was made to compare the discriminative performance for disease‐free survival (DFS). The discriminative performance for DFS was better when combining radiomic and genetic features compared to clinical data only, selected genetic features, and selected radiomic features.What this study addsThe combination of selected radiomic and genomic features improved stratification of NSCLC patients upon survival. Thus, integrating a clinicopathological model with radiomic and genomic features may lead to improved prognostic accuracy compared to conventional clinicopathological data alone.

BackgroundProstate cancer (PCa) is a common malignant tumor in older men, and bone metastasis is its most frequent form. Once bone metastasis occurs, survival drops sharply. The Gleason score is the standard tool for judging how aggressive the cancer is; men with high-risk disease face higher chances of treatment failure and death. Therefore, early detection and prediction of bone metastasis and high Gleason scores by magnetic resonance imaging (MRI) are clinically important. In this study, we analyzed clinical and MRI data from 168 PCa patients to evaluate the role of clinical features and MRI-based radiomics in predicting bone metastasis and high-grade Gleason scores.MethodsThis retrospective study included 168 patients with pathologically confirmed PCa from Zhongshan Hospital of Traditional Chinese Medicine. Clinical and pathological data, as well as MRI images, were collected. Radiomics and clinical features were extracted and divided into training and testing sets using a random ratio. Feature selection was performed using t-tests and least absolute shrinkage and selection operator (LASSO) regression to reduce dimensionality and identify effective features. Machine learning algorithms were constructed based on two datasets: one combining clinical information with radiomics features, and the other using radiomics features alone. Model performance was assessed using metrics such as accuracy, area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).ResultsPatients with bone metastasis and high-grade Gleason Scores had significantly higher levels of total prostate-specific antigen (tPSA) and free prostate-specific antigen (fPSA) compared to those without bone metastasis and with low-grade Gleason scores (P<0.05). In the testing set, the best-performing model for predicting bone metastasis was the Extreme Gradient Boosting (XGBoost) model that used clinical features combined with radiomics features, with an AUC of 0.875, which was superior to the AUC of 0.732 for radiomics features alone. For predicting high-grade Gleason scores, the XGBoost model using clinical features combined with radiomics features also performed best, with an AUC of 0.830, outperforming the AUC of 0.778 for radiomics features alone. The most significant clinical feature identified was fPSA, while the most significant radiomics features were log-sigma-5-0-mm-3D_glszm_ZoneEntropy for bone metastasis and wavelet-HLH_gldm_HighGrayLevelEmphasis for high-grade Gleason scores respectively.ConclusionsWe proposed a predictive model that integrated clinical features and radiomics features obtained from prostate MRI, offering a non-invasive and radiation-free approach to predict bone metastasis and high-grade Gleason scores in PCa.

PurposeTo evaluate and compare the predictive performance of machine learning methods using clinical-semantic, radiomic, and combined features in distinguishing squamous cell carcinoma (SCC) from adenocarcinoma (ADC) in non-small cell lung cancer (NSCLC).MethodsA total of 399 patients with pathologically confirmed NSCLC were retrospectively enrolled in 2017, and randomly divided into a training set (n=279) and a validation set (n=120). Clinical factors, semantic features, and radiomics features were collected and screened via the minimum redundancy maximum relevance (mRMR) method and least absolute shrinkage and selection operator (LASSO). We investigated 3 models constructed with 4 classifiers for histologic subtype prediction. The models were trained on the training cohort and their performance was evaluated on the independent validation cohort using accuracy, sensitivity, specificity, F1 score, precision and area under the receiver operating characteristic curve (AUC).ResultsAfter feature selection, 10 representative features were finalized, comprising 4 clinical-semantic and 6 radiomic features. In the validation cohort, the support vector machine (SVM) classifier demonstrated promising predictive performance. When integrating clinical-semantic and radiomic features, the combined model (AUC = 0.871) showed potential in distinguishing NSCLC pathological subtypes, outperforming models based solely on clinical-semantic (AUC = 0.594) or radiomic features (AUC = 0.713). It achieved an accuracy of 0.892, a sensitivity of 0.758, a specificity of 0.943, a F1 score of 0.794, and a precision of 0.833. However, the AUC differences were not statistically significant, highlighting the need for further multi-center prospective validation.ConclusionIn this study, the SVM-based combined model, which integrated clinical-semantic and radiomic features, demonstrated promising performance among the four classifiers-based combined models in distinguishing between ADC and SCC. However, due to the study’s single-center, retrospective design and the lack of statistically significant differences in AUC for some models, the findings should be interpreted with caution. These results show potential but require future multi-center prospective validation before clinical application.

Radiomics and Deep Learning Model for Benign and Malignant Soft Tissue Tumors Differentiation of Extremities and Trunk.

ObjectiveThis study aimed to investigate the feasibility and potential value of predictive models for human epidermal growth factor receptor 2 (HER2)-positive status in breast cancer (BC) based on radiomics features from conventional ultrasound images and machine learning models.MethodsUltrasound images of 437 patients with surgically and pathologically confirmed BC were retrospectively analyzed, including 144 HER2-positive and 293 HER2-negative cases, which were used as a training and validation dataset. Key features highly correlated with HER2-positive status were identified and selected using the least absolute shrinkage and selection operator (LASSO), t-test, and principal component analysis (PCA). After the selection of relevant features, the dataset was randomly split into five equal parts for five-fold cross-validation to identify the optimal machine learning method and hyperparameters. A predictive model was then developed based on ultrasound imaging and radiomics features. After feature selection and model development, an additional cohort of 88 patients from other hospitals was utilized as an external validation dataset. The model’s internal validation performance was assessed through receiver operating characteristic (ROC) curve analysis, and metrics including area under the curve (AUC), sensitivity, and specificity were calculated. The generalizability of the model was further evaluated using the external validation.ResultsFive radiomics features were found to correlate with HER2-positive status in BC and used for model construction. Among the machine learning models generated, the best predictive model achieved area under the ROC curve values of 0.893 (95% confidence interval [CI], 0.860–0.920) in the training and validation dataset and 0.854 (95% CI, 0.775–0.927) in the external validation dataset.ConclusionMachine learning models based on ultrasound radiomics features have potential clinical value for predicting HER2-positive status in BC.

To study the feasibility of use of radiomic features extracted from axillary lymph nodes for diagnosis of their metastatic status in patients with breast cancer. A total of 176 axillary lymph nodes of patients with breast cancer, consisting of 87 metastatic axillary lymph nodes (ALNM) and 89 negative axillary lymph nodes proven by surgery, were retrospectively reviewed from the database of our cancer center. For each selected axillary lymph node, 106 radiomic features based on preoperative pharmacokinetic modeling dynamic contrast enhanced magnetic resonance imaging (PK-DCE-MRI) and 5 conventional image features were obtained. The least absolute shrinkage and selection operator (LASSO) regression was used to select useful radiomic features. Logistic regression was used to develop diagnostic models for ALNM. Delong test was used to compare the diagnostic performance of different models. The 106 radiomic features were reduced to 4 ALNM diagnosis-related features by LASSO. Four diagnostic models including conventional model, pharmacokinetic model, radiomic model, and a combined model (integrating the Rad-score in the radiomic model with the conventional image features) were developed and validated. Delong test showed that the combined model had the best diagnostic performance: area under the curve (AUC), 0.972 (95% CI [0.947-0.997]) in the training cohort and 0.979 (95% CI [0.952-1]) in the validation cohort. The diagnostic performance of the combined model and the radiomic model were better than that of pharmacokinetic model and conventional model (P<0.05). Radiomic features extracted from PK-DCE-MRI images of axillary lymph nodes showed promising application for diagnosis of ALNM in patients with breast cancer.

ObjectiveTo study the feasibility of use of radiomic features extracted from axillary lymph nodes for diagnosis of their metastatic status in patients with breast cancer.Materials and methodsA total of 176 axillary lymph nodes of patients with breast cancer, consisting of 87 metastatic axillary lymph nodes (ALNM) and 89 negative axillary lymph nodes proven by surgery, were retrospectively reviewed from the database of our cancer center. For each selected axillary lymph node, 106 radiomic features based on preoperative pharmacokinetic modeling dynamic contrast enhanced magnetic resonance imaging (PK-DCE-MRI) and 5 conventional image features were obtained. The least absolute shrinkage and selection operator (LASSO) regression was used to select useful radiomic features. Logistic regression was used to develop diagnostic models for ALNM. Delong test was used to compare the diagnostic performance of different models.ResultsThe 106 radiomic features were reduced to 4 ALNM diagnosis–related features by LASSO. Four diagnostic models including conventional model, pharmacokinetic model, radiomic model, and a combined model (integrating the Rad-score in the radiomic model with the conventional image features) were developed and validated. Delong test showed that the combined model had the best diagnostic performance: area under the curve (AUC), 0.972 (95% CI [0.947–0.997]) in the training cohort and 0.979 (95% CI [0.952–1]) in the validation cohort. The diagnostic performance of the combined model and the radiomic model were better than that of pharmacokinetic model and conventional model (P<0.05).ConclusionRadiomic features extracted from PK-DCE-MRI images of axillary lymph nodes showed promising application for diagnosis of ALNM in patients with breast cancer.

Aims/Background Medullary thyroid carcinoma (MTC) is a rare thyroid malignancy with a high mortality rate. Early detection of cervical lymph node metastasis (LNM) is critical for improving prognosis for patients with MTC. This study aimed to investigate the predictive utility of ultrasound-based radiomics for preoperative prediction of cervical LNM in MTC patients. Methods The clinical, ultrasound, and pathological information of 193 patients with MTC were retrospectively examined. Radiomics features were obtained from the ultrasound images using PyRadiomics. The selected patients were randomly divided into training (n = 135) and validation (n = 58) cohorts. In the training dataset, radiomics features were selected using the least absolute shrinkage and selection operator (LASSO) regression, and the univariate and multivariate logistic regression tests were employed to identify the clinical independent predictors of cervical LNM. Three models were created: radiomics, clinical, and combined models, with the latter presented as a nomogram. The area under the curve (AUC) was calculated to evaluate the models' predictive performance. The differences in AUCs between the combined and approach-specific models were compared using the DeLong test. The clinical usefulness of the models was evaluated using decision curve analysis (DCA). Results Nineteen radiomics features were chosen, and the AUCs of the developed radiomics model in the training and validation datasets were 0.881 and 0.859, respectively. Tumour diameter, calcitonin (Ctn) level, tumour margin, and sonographers' suspicion of cervical LNM based on ultrasound findings were clinical independent predictors for cervical LNM. The AUCs of the clinical model built using these predictors were 0.800 and 0.805 in the training and validation datasets, whereas the combined model had much-improved AUCs, measuring 0.925 for the training dataset and 0.918 for the validation test. The DeLong test indicated a significant AUC difference between the combined and clinical models (training dataset p < 0.001, validation dataset p = 0.027), but the difference between the combined and radiomics models was significant only in the training dataset (training dataset p = 0.021, validation dataset p = 0.066). Furthermore, based on the DCA results, the combined model features the largest clinical net benefit. Conclusion The nomogram, the combined model merging the ultrasound-based radiomics with clinical independent predictors, effectively predicts preoperative cervical LNM in MTC patients, outperforming the radiomics and clinical models.