CT-Based Radiomics Signatures for Predicting the Risk Categorization of Thymic Epithelial Tumors

Using optimized CT type to predict histological classifications of thymic epithelial tumors: a radiomics integrated analysis

OBJECTIVE

To develop and externally validate an integrated model that utilizes optimized radiomics features from non-contrast-enhanced CT (NE-CT) or contrast-enhanced CT (CE-CT), along with morphological features and clinical risk factors, to predict histological classifications of thymic epithelial tumors (TETs).

METHODS

A total of 182 patients with TET, classified as the low-risk group and the high-risk group based on histology, were divided into a training cohort (N = 122, center 1) and an external validation cohort (N = 60, center 2). Radiomics features were extracted from different CT types, followed by feature selection, including consistency, correlation, and importance tests, to generate Rad-scores for both NE-CT and CE-CT. The integrated model was developed by combining the optimal Rad-score, morphological features, and clinical risk factors using multivariate logistic regression. Model performance was assessed by the area under the receiver operating characteristic curve (AUC) and compared by Delong test. A nomogram was used to visually present the integrated model.

RESULTS

A total of 851 radiomics features were extracted, with NE-CT and CE-CT Rad-scores consisting of four and five features, respectively. The AUCs of the CE-CT Rad-score were higher than those of the NE-CT Rad-score in both the training cohort (0.783 vs 0.749) and the external validation cohort (0.775 vs 0.723, p = 0.361). The integrated model, combining five morphological features and the CE-CT Rad-score, achieved AUCs of 0.814 and 0.802 in the training and external validation cohorts, respectively.

CONCLUSION

The integrated model, incorporating radiomics features from CE-CT and morphological features, can help to identify the histological classifications of TETs.

CRITICAL RELEVANCE STATEMENT

This study developed an integrated model based on radiomics features from contrast-enhanced CT and morphological features, demonstrating that the integrated model has impressive predictive capability in distinguishing histological classifications of thymic epithelial tumors through external validation.

KEY POINTS

Radiomics features extracted from CT more effectively represented thymic epithelial tumor (TET) heterogeneity than morphological features. The radiomics model using contrast-enhanced CT outperformed that using non-contrast-enhanced CT in identifying histological classifications of TET. The integrated model, combining radiomics and morphological features, exhibited the highest performance in predicting TET histological classifications.

Clinical significance of positron emission tomography-computed tomography in the classification of thymic tumors

OBJECTIVES

This study aimed to explore the possibility of positron emission tomography/computed tomography (PET-CT) in identifying histological classification of thymic tumours.

METHODS

Patients diagnosed as thymic tumours and accepted PET-CT scans were included. Thymic tumours were classified into three subgroups: low-risk thymoma (A, AB and B1), high-risk thymoma (B2, B3) and thymic carcinoma (TC). Logistic regression analysis was performed to identify potential factors differentiating the classification of thymic tumours. The receiver operating characteristic curve was applied to assess the diagnosis efficiency and the cut-off value.

RESULTS

From 2015 to 2023, a total of 176 patients, including 75 cases of low-risk thymoma, 60 cases of high-risk thymoma and 41 cases of TC, were included. The logistic regression models suggested maximum standardized uptake value (SUVmax) as a potential factor differentiating the three subgroups. Moreover, the receiver operating characteristic curve identified the SUVmax in differentiating low-risk thymoma vs high-risk thymoma (area under the curve [AUC]: 0.845, 95% CI: 0.776-0.913, specificity: 0.907, sensitivity: 0.716), low-risk thymoma vs TC (AUC: 0.976, 95% CI: 0.953-0.999, specificity: 0.933, sensitivity: 0.951) and high-risk thymoma vs TC (AUC: 0.84, 95% CI: 0.761-0.92, specificity: 0.865, sensitivity: 0.703), respectively. SUVmax was also an independent factor identifying thymic tumours with or without lymph node metastasis. The cut-off of 10 in SUVmax could well identify lymph node metastasis with the positive predict value of 0.684 and negative predict value of 0.981.

CONCLUSIONS

SUVmax is a reliable factor in distinguishing different histological subgroups and identifying lymph node metastasis in thymic tumours.

Risk stratification of thymic epithelial tumors based on peritumor CT radiomics and semantic features

OBJECTIVES

To develop and validate nomograms combining radiomics and semantic features to identify the invasiveness and histopathological risk stratification of thymic epithelial tumors (TET) using contrast-enhanced CT.

METHODS

This retrospective multi-center study included 224 consecutive cases. For each case, 6764 intratumor and peritumor radiomics features and 31 semantic features were collected. Multi-feature selections and decision tree models were performed on radiomics features and semantic features separately to select the most important features for Masaoka-Koga staging and WHO classification. The selected features were then combined to create nomograms for the two systems. The performance of the radiomics model, semantic model, and combined model was evaluated using the area under the receiver operating characteristic curves (AUCs).

RESULTS

One hundred eighty-seven cases (56.5 years ± 12.3, 101 men) were included, with 62 cases as the external test set. For Masaoka-Koga staging, the combined model, which incorporated five peritumor radiomics features and four semantic features, showed an AUC of 0.958 (95% CI: 0.912-1.000) in distinguishing between early-stage (stage I/II) and advanced-stage (III/IV) TET in the external test set. For WHO classification, the combined model incorporating five peritumor radiomics features and two semantic features showed an AUC of 0.857 (0.760-0.955) in differentiating low-risk (type A/AB/B1) and high-risk (B2/B3/C) TET. The combined models showed the most effective predictive performance, while the semantic models exhibited comparable performance to the radiomics models in both systems (p > 0.05).

CONCLUSION

The nomograms combining peritumor radiomics features and semantic features could help in increasing the accuracy of grading invasiveness and risk stratification of TET.

CRITICAL RELEVANCE STATEMENT

Peripheral invasion and histopathological type are major determinants of treatment and prognosis of TET. The integration of peritumoral radiomics features and semantic features into nomograms may enhance the accuracy of grading invasiveness and risk stratification of TET.

KEY POINTS

Peritumor region of TET may suggest histopathological and invasive risk. Peritumor radiomic and semantic features allow classification by Masaoka-Koga staging (AUC: 0.958). Peritumor radiomic and semantic features enable the classification of histopathological risk (AUC: 0.857).

Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images

OBJECTIVES

This study aims to develop an innovative, deep model for thymoma risk stratification using preoperative CT images. Current algorithms predominantly focus on radiomic features or 2D deep features and require manual tumor segmentation by radiologists, limiting their practical applicability.

METHODS

The deep model was trained and tested on a dataset comprising CT images from 147 patients (82 female; mean age, 54 years ± 10) who underwent surgical resection and received subsequent pathological confirmation. The eligible participants were divided into a training cohort (117 patients) and a testing cohort (30 patients) based on the CT scan time. The model consists of two stages: 3D tumor segmentation and risk stratification. The radiomic model and deep model (2D) were constructed for comparative analysis. Model performance was evaluated through dice coefficient, area under the curve (AUC), and accuracy.

RESULTS

In both the training and testing cohorts, the deep model demonstrated better performance in differentiating thymoma risk, boasting AUCs of 0.998 and 0.893 respectively. This was compared to the radiomic model (AUCs of 0.773 and 0.769) and deep model (2D) (AUCs of 0.981 and 0.760). Notably, the deep model was capable of simultaneously identifying lesions, segmenting the region of interest (ROI), and differentiating the risk of thymoma on arterial phase CT images. Its diagnostic prowess outperformed that of the baseline model.

CONCLUSIONS

The deep model has the potential to serve as an innovative decision-making tool, assisting on clinical prognosis evaluation and the discernment of suitable treatments for different thymoma pathological subtypes.

KEY POINTS

• This study incorporated both tumor segmentation and risk stratification. • The deep model, using clinical and 3D deep features, effectively predicted thymoma risk. • The deep model improved AUCs by 16.1pt and 17.5pt compared to radiomic model and deep model (2D) respectively.

Multimodal modeling with low-dose CT and clinical information for diagnostic artificial intelligence on mediastinal tumors: a preliminary study

BACKGROUND

Diagnosing mediastinal tumours, including incidental lesions, using low-dose CT (LDCT) performed for lung cancer screening, is challenging. It often requires additional invasive and costly tests for proper characterisation and surgical planning. This indicates the need for a more efficient and patient-centred approach, suggesting a gap in the existing diagnostic methods and the potential for artificial intelligence technologies to address this gap. This study aimed to create a multimodal hybrid transformer model using the Vision Transformer that leverages LDCT features and clinical data to improve surgical decision-making for patients with incidentally detected mediastinal tumours.

METHODS

This retrospective study analysed patients with mediastinal tumours between 2010 and 2021. Patients eligible for surgery (n=30) were considered 'positive,' whereas those without tumour enlargement (n=32) were considered 'negative.' We developed a hybrid model combining a convolutional neural network with a transformer to integrate imaging and clinical data. The dataset was split in a 5:3:2 ratio for training, validation and testing. The model's efficacy was evaluated using a receiver operating characteristic (ROC) analysis across 25 iterations of random assignments and compared against conventional radiomics models and models excluding clinical data.

RESULTS

The multimodal hybrid model demonstrated a mean area under the curve (AUC) of 0.90, significantly outperforming the non-clinical data model (AUC=0.86, p=0.04) and radiomics models (random forest AUC=0.81, p=0.008; logistic regression AUC=0.77, p=0.004).

CONCLUSION

Integrating clinical and LDCT data using a hybrid transformer model can improve surgical decision-making for mediastinal tumours, showing superiority over models lacking clinical data integration.

Lobulated tumor contour as a predictor of preoperative tumor invasion of the lung or pericardium in thymoma patients

PURPOSE

Preoperative investigations to detect invasion to neighboring organs are important for deciding on the most appropriate surgical approach for thymoma. We evaluated preoperative computed tomography (CT) findings in thymoma patients to identify the CT features associated with tumor invasion.

METHODS

Clinicopathologic information on 193 patients who underwent surgical resection for thymoma at Chiba University Hospital between 2002 and 2016 was collected retrospectively. The surgical pathology identified invasion of thymoma in 35 patients: in the lung (n = 18), pericardium (n = 11), or both (n = 6). Contact lengths between the tumor contour and lung (CLTL) or pericardium (CLTP) were measured at the maximum section of the tumor on axial CT. Univariate and multivariate analyses were performed to analyze the relationship between pathological invasion of the lung or pericardium and the clinicopathologic features.

RESULTS

The mean CLTL and CLTP were significantly longer in patients with invasion of the neighboring organs than in those without invasion. A lobulated tumor contour was identified in 95.6% of the patients with invasion of the neighboring organs. A multivariate analysis revealed that a lobulated tumor contour was significantly associated with both lung and pericardial invasion.

CONCLUSIONS

A lobulated tumor contour was significantly associated with lung and/or pericardial invasion in thymoma patients.

Development and validation of a contrast-enhanced CT-based radiomics nomogram for differentiating mass-like thymic hyperplasia and low-risk thymoma

PURPOSE

To explore the efficiency of a contrast-enhanced CT-based radiomics nomogram integrated with radiomics signature and clinically independent predictors to distinguish mass-like thymic hyperplasia (ml-TH) from low-risk thymoma (LRT) preoperatively.

METHODS

135 Patients with histopathology confirmed ml-TH (n = 65) and LRT (n = 70) were randomly divided into training set (n = 94) and validation set (n = 41) at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used to obtain the optimal features. Based on the selected features, four machine learning models, support vector machine (SVM), logistic regression (LR), extreme gradient boosting (XGBOOST), and random forest (RF) were constructed. Multivariate logistic regression was used to establish a radiomics nomogram containing clinically independent predictors and radiomics signature. Receiver operating characteristic (ROC), DeLong test, and calibration curves were used to detect the performance of the radiomics nomogram in training set and validation set.

RESULTS

In the validation set, the area under the curve (AUC) value of LR (0.857; 95% CI: 0.741, 0.973) was the highest of the four machine learning models. Radiomics nomogram containing radiomics signature and clinically independent predictors (including age, shape, and net enhancement degree) had better calibration and identification in the training set (AUC: 0.959; 95% CI: 0.922, 0.996) and validation set (AUC: 0.895; 95% CI: 0.795, 0.996).

CONCLUSION

We constructed a contrast-enhanced CT-based radiomics nomogram containing clinically independent predictors and radiomics signature as a noninvasive preoperative prediction method to distinguish ml-TH from LRT. The radiomics nomogram we constructed has potential for preoperative clinical decision making.

Development and Validation of Multi-Omics Thymoma Risk Classification Model Based on Transfer Learning

The paper aims to develop prediction model that integrates clinical, radiomics, and deep features using transfer learning to stratifying between high and low risk of thymoma. Our study enrolled 150 patients with thymoma (76 low-risk and 74 high-risk) who underwent surgical resection and pathologically confirmed in Shengjing Hospital of China Medical University from January 2018 to December 2020. The training cohort consisted of 120 patients (80%) and the test cohort consisted of 30 patients (20%). The 2590 radiomics and 192 deep features from non-enhanced, arterial, and venous phase CT images were extracted and ANOVA, Pearson correlation coefficient, PCA, and LASSO were used to select the most significant features. A fusion model that integrated clinical, radiomics, and deep features was developed with SVM classifiers to predict the risk level of thymoma, and accuracy, sensitivity, specificity, ROC curves, and AUC were applied to evaluate the classification model. In both the training and test cohorts, the fusion model demonstrated better performance in stratifying high and low risk of thymoma. It had AUCs of 0.99 and 0.95, and an accuracy of 0.93 and 0.83, respectively. This was compared to the clinical model (AUCs of 0.70 and 0.51, accuracy of 0.68 and 0.47), the radiomics model (AUCs of 0.97 and 0.82, accuracy of 0.93 and 0.80), and the deep model (AUCs of 0.94 and 0.85, accuracy of 0.88 and 0.80). The fusion model integrating clinical, radiomics and deep features based on transfer learning was efficient for noninvasively stratifying high risk and low risk of thymoma. The models could help to determine surgery strategy for thymoma cancer.

The predictive value of a computed tomography-based radiomics model for the surgical separability of thymic epithelial tumors from the superior vena cava and the left innominate vein

Background

The aim of this study was to develop a radiomics machine learning model based on computed tomography (CT) that can predict whether thymic epithelial tumors (TETs) can be separated from veins during surgery and to compare the accuracy of the radiomics model to that of radiologists.

Methods

Patients who underwent thymectomy at our hospital from 2009 to 2017 were included in the screening process. After the selection of patients according to the inclusion and exclusion criteria, the cohort was randomly divided into training and testing groups, and CT images of these patients were collected. Subsequently, two-dimensional (2D) and three-dimensional (3D) regions of interest were labelled using ITK-SNAP 3.8.0 software, and Radiomics features were extracted using Python software (Python Software Foundation) and selected through the least absolute shrinkage and selection operator (LASSO) regression model. To construct the classifier, a support vector machine (SVM) was employed, and a nomogram was created using logistic regression to predict vascular inseparable TETs based on the radiomics score (radscore) and image features. To assess the accuracy of these models, area under receiver operating characteristic (ROC) curves of these models were calculated, and differences among the models were identified using the Delong test.

Results

In this retrospective study, 204 patients with TETs were included, among whom 21 were diagnosed with surgical vascularly inseparable TETs. The area under ROC curve (AUC) of the 2D model, 3D model, 2D + 3D model, and radiologist diagnoses were 0.94, 0.92, 0.95, and 0.87 in the training cohort and 0.95, 0.92, 0.98, and 0.78 in testing cohort, respectively. The Delong test revealed a significant improvement in the performance of the radiomics models compared to radiologists' diagnoses. The logistic regression selected 3 image features, namely maximum diameter of the tumor, degree of abutment of vessel circumference >50%, and absence of the mediastinal fat layer or space between the tumor and surrounding structures. These features, along with the radscore, were included to develop a nomogram. The AUCs of this nomogram were 0.99 in both the training set and testing set, and the Delong test did not find a significant difference between ROC plots of the nomogram and radiomics models.

Conclusions

The proposed radiomics model could accurately predict surgical vascularly inseparable TETs preoperatively and was shown to have a higher predictive value than the radiologists.

Machine learning-based radiomic computed tomography phenotyping of thymic epithelial tumors: Predicting pathological and survival outcomes

OBJECTIVE

For patients with thymic epithelial tumors, accurately predicting clinicopathological outcomes remains challenging. We aimed to investigate the performance of machine learning-based radiomic computed tomography phenotyping for predicting pathological (World Health Organization [WHO] type and TNM stage) and survival outcomes (overall and progression-free survival) in patients with thymic epithelial tumors.

METHODS

This retrospective study included patients with thymic epithelial tumors between January 2001 and January 2022. The radiomic features were extracted from preoperative unenhanced computed tomography images. After strict feature selection, random forest and random survival forest models were fitted to predict pathological and survival outcomes, respectively. The model performance was assessed by the area under the curve (AUC) and validated internally by the bootstrap method.

RESULTS

In total, 124 patients with a median age of 61 years were included. The radiomics random forest models of WHO type and TNM stage showed satisfactory performance with an AUC_WHO of 0.898 (95% CI, 0.753-1.000) and an AUC_TNM of 0.766 (95% CI, 0.642-0.886). For overall survival and progression-free survival prediction, the radiomics random survival forest models showed good performance (integrated AUCs, 0.923; 95% CI, 0.691-1.000 and 0.702; 95% CI, 0.513-0.875, respectively), and the integrated AUCs increased to 0.935 (95% CI, 0.705-1.000) and 0.811 (95% CI, 0.647-0.942), respectively, when combined with clinicopathological features.

CONCLUSIONS

Machine learning-based radiomic computed tomography phenotyping might allow for the satisfactory prediction of pathological and survival outcomes and further improve prognostic performance when integrated with clinicopathological features in patients with thymic epithelial tumors.

Machine-learning classifiers based on non-enhanced computed tomography radiomics to differentiate anterior mediastinal cysts from thymomas and low-risk from high-risk thymomas: A multi-center study

Background

This study aimed to investigate the diagnostic value of machine-learning (ML) models with multiple classifiers based on non-enhanced CT Radiomics features for differentiating anterior mediastinal cysts (AMCs) from thymomas, and high-risk from low risk thymomas.

Methods

In total, 201 patients with AMCs and thymomas from three centers were included and divided into two groups: AMCs vs. thymomas, and high-risk vs low-risk thymomas. A radiomics model (RM) was built with 73 radiomics features that were extracted from the three-dimensional images of each patient. A combined model (CM) was built with clinical features and subjective CT finding features combined with radiomics features. For the RM and CM in each group, five selection methods were adopted to select suitable features for the classifier, and seven ML classifiers were employed to build discriminative models. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of each combination.

Results

Several classifiers combined with suitable selection methods demonstrated good diagnostic performance with areas under the curves (AUCs) of 0.876 and 0.922 for the RM and CM in group 1 and 0.747 and 0.783 for the RM and CM in group 2, respectively. The combination of support vector machine (SVM) as the feature-selection method and Gradient Boosting Decision Tree (GBDT) as the classification algorithm represented the best comprehensive discriminative ability in both group. Comparatively, assessments by radiologists achieved a middle AUCs of 0.656 and 0.626 in the two groups, which were lower than the AUCs of the RM and CM. Most CMs exhibited higher AUC value compared to RMs in both groups, among them only a few CMs demonstrated better performance with significant difference in group 1.

Conclusion

Our ML models demonstrated good performance for differentiation of AMCs from thymomas and low-risk from high-risk thymomas. ML based on non-enhanced CT radiomics may serve as a novel preoperative tool.

Thoracic Imaging in China: Yesterday, Today, and Tomorrow

Thoracic imaging has been revolutionized through advances in technology and research around the world, and so has China. Thoracic imaging in China has progressed from anatomic observation to quantitative and functional evaluation, from using traditional approaches to using artificial intelligence. This article will review the past, present, and future of thoracic imaging in China, in an attempt to establish new accepted strategies moving forward.

Application of a combined radiomics nomogram based on CE-CT in the preoperative prediction of thymomas risk categorization

OBJECTIVE

This study aimed to establish a combined radiomics nomogram to preoperatively predict the risk categorization of thymomas by using contrast-enhanced computed tomography (CE-CT) images.

MATERIALS AND METHODS

The clinical, pathological, and CT data of 110 patients with thymoma (50 patients with low-risk thymomas and 60 patients with high-risk thymomas) collected in our Hospital from July 2017 to March 2022 were retrospectively analyzed. The study subjects were randomly divided into the training set (n = 77) and validation set (n = 33) in a 7:3 ratio. Radiomics features were extracted from the CT images, and the least absolute shrinkage and selection operator (LASSO) algorithm was performed to select 13 representative features. Five models, including logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), and gradient boosting decision tree (GBDT) were constructed to predict thymoma risks based on these features. A combined radiomics nomogram was further established based on the clinical factors and radiomics scores. The performance of the models was evaluated using receiver operating characteristic (ROC) curve, DeLong tests, and decision curve analysis.

RESULTS

Maximum tumor diameter and boundary were selected to build the clinical factors model. Thirteen features were acquired by LASSO algorithm screening as the optimal features for machine learning model construction. The LR model exhibited the highest AUC value (0.819) among the five machine learning models in the validation set. Furthermore, the radiomics nomogram combining the selected clinical variables and radiomics signature predicted the categorization of thymomas at different risks more effectively (the training set, AUC = 0.923; the validation set, AUC = 0.870). Finally, the calibration curve and DCA were utilized to confirm the clinical value of this combined radiomics nomogram.

CONCLUSION

We demonstrated the clinical diagnostic value of machine learning models based on CT semantic features and the selected clinical variables, providing a non-invasive, appropriate, and accurate method for preoperative prediction of thymomas risk categorization.

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

Background

To 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).

Methods

A 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.

Results

In 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.

Conclusions

In 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.

Computed Tomography-Based Radiomics for Differentiation of Thymic Epithelial Tumors and Lymphomas in Anterior Mediastinum

Objective

To investigate the differential diagnostic performance of computed tomography (CT)-based radiomics in thymic epithelial tumors (TETs) and lymphomas in anterior mediastinum.

Methods

There were 149 patients with TETs and 93 patients with lymphomas enrolled. These patients were assigned to a training set (n = 171) and an external validation set (n = 71). Dedicated radiomics prototype software was used to segment lesions on preoperative chest enhanced CT images and extract features. The multivariable logistic regression algorithm was used to construct three models according to clinico-radiologic features, radiomics features, and combined features, respectively. Performance of the three models was compared by using the area under the receiver operating characteristic curves (AUCs). Decision curve analysis was used to evaluate clinical utility of the three models.

Results

For clinico-radiologic model, radiomics signature model, and combined model, the AUCs were 0.860, 0.965, 0.975 and 0.843, 0.961, 0.955 in the training cohort and the test cohort, respectively (all P<0.05). The accuracies of each model were 0.836, 0.895, 0.918 and 0.845, 0.901, 0.859 in the two cohorts, respectively (all P<0.05). Compared with the clinico-radiologic model, better diagnostic performances were found in the radiomics signature model and the combined model.

Conclusions

Radiomics signature model and combined model exhibit outstanding and comparable differential diagnostic performances between TETs and lymphomas. The CT-based radiomics analysis might serve as an effective tool for accurately differentiating TETs from lymphomas before treatment.

Contrast-enhanced CT-based radiomics model for differentiating risk subgroups of thymic epithelial tumors

Background

To validate a contrast-enhanced CT (CECT)-based radiomics model (RM) for differentiating various risk subgroups of thymic epithelial tumors (TETs).

Methods

A retrospective study was performed on 164 patients with TETs who underwent CECT scans before treatment. A total of 130 patients (approximately 79%, from 2012 to 2018) were designated as the training set, and 34 patients (approximately 21%, from 2019 to 2021) were designated as the testing set. The analysis of variance and least absolute shrinkage and selection operator algorithm methods were used to select the radiomics features. A logistic regression classifier was constructed to identify various subgroups of TETs. The predictive performance of RMs was evaluated based on receiver operating characteristic (ROC) curve analyses.

Results

Two RMs included 16 and 13 radiomics features to identify three risk subgroups of traditional risk grouping [low-risk thymomas (LRT: Types A, AB and B1), high-risk thymomas (HRT: Types B2 and B3), thymic carcinoma (TC)] and improved risk grouping [LRT* (Types A and AB), HRT* (Types B1, B2 and B3), TC], respectively. For traditional risk grouping, the areas under the ROC curves (AUCs) of LRT, HRT, and TC were 0.795, 0.851, and 0.860, respectively, the accuracy was 0.65 in the training set, the AUCs were 0.621, 0.754, and 0.500, respectively, and the accuracy was 0.47 in the testing set. For improved risk grouping, the AUCs of LRT*, HRT*, and TC were 0.855, 0.862, and 0.869, respectively, and the accuracy was 0.72 in the training set; the AUCs were 0.778, 0.716, and 0.879, respectively, and the accuracy was 0.62 in the testing set.

Conclusions

CECT-based RMs help to differentiate three risk subgroups of TETs, and RM established according to improved risk grouping performed better than traditional risk grouping.

CT-Based Radiomics Nomogram for Differentiation of Anterior Mediastinal Thymic Cyst From Thymic Epithelial Tumor

Objectives

This study aimed to distinguish preoperatively anterior mediastinal thymic cysts from thymic epithelial tumors via a computed tomography (CT)-based radiomics nomogram.

Methods

This study analyzed 74 samples of thymic cysts and 116 samples of thymic epithelial tumors as confirmed by pathology examination that were collected from January 2014 to December 2020. Among the patients, 151 cases (scanned at CT 1) were selected as the training cohort, and 39 cases (scanned at CT 2 and 3) served as the validation cohort. Radiomics features were extracted from pre-contrast CT images. Key features were selected by SelectKBest and least absolute shrinkage and selection operator and then used to build a radiomics signature (Rad-score). The radiomics nomogram developed herein via multivariate logistic regression analysis incorporated clinical factors, conventional CT findings, and Rad-score. Its performance in distinguishing the samples of thymic cysts from those of thymic epithelial tumors was assessed via discrimination, calibration curve, and decision curve analysis (DCA).

Results

The radiomics nomogram, which incorporated 16 radiomics features and 3 conventional CT findings, including lesion edge, lobulation, and CT value, performed better than Rad-score, conventional CT model, and the clinical judgment by radiologists in distinguishing thymic cysts from thymic epithelial tumors. The area under the receiver operating characteristic (ROC) curve of the nomogram was 0.980 [95% confidence interval (CI), 0.963–0.993] in the training cohort and 0.992 (95% CI, 0.969–1.000) in the validation cohort. The calibration curve and the results of DCA indicated that the nomogram has good consistency and valuable clinical utility.

Conclusion

The CT-based radiomics nomogram presented herein may serve as an effective and convenient tool for differentiating thymic cysts from thymic epithelial tumors. Thus, it may aid in clinical decision-making.