Optimizing the radiomics-machine-learning model based on non-contrast enhanced CT for the simplified risk categorization of thymic epithelial tumors: A large cohort retrospective study

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.

Radiomics in thymic epithelial tumors: a scoping review of current status and advances

BACKGROUND

This scoping review aims to evaluate the current status and recent advances in the use of radiomics for the diagnosis, risk stratification, and staging of thymic epithelial tumors (TETs). The review also explores radiomics' potential in predicting the risk of myasthenia gravis (MG), an associated autoimmune condition in TETs patients.

METHODS

A comprehensive literature search was conducted using PubMed and Web of Science to identify studies published since 2012 on the application of radiomics in managing TETs. The studies were assessed for their methodologies, including imaging protocols, feature extraction techniques, and model performance metrics. The Radiomics Quality Score (RQS) was used to evaluate study quality.

RESULTS

A total of 23 studies, including 4701 patients, were analyzed. Radiomics-based models showed high accuracy in distinguishing TETs from other mediastinal masses, predicting risk subtypes, and improving the accuracy of TNM and Masaoka-Koga (MK) staging. Additionally, radiomics demonstrated potential in predicting the risk of MG in thymoma patients. However, all studies were retrospective, and only 6 studies included external validation, with an average RQS of 13.87, accounting for 38.52% of the maximum score.

CONCLUSION

Radiomics shows great potential in advancing the diagnosis, risk stratification, and staging of TETs. However, its clinical implementation requires overcoming challenges in standardization, validation, and interpretability. Future research should focus on multi-center prospective studies, external validation, and integrating multi-modal imaging and molecular biomarkers to improve risk assessment and treatment strategies.

Multi-dimensional interpretable deep learning-radiomics based on intra-tumoral and spatial habitat for preoperative prediction of thymic epithelial tumours risk categorisation

BACKGROUND AND PURPOSE

This study aims to develop and compare combined models based on enhanced CT-based radiomics, multi-dimensional deep learning, clinical-conventional imaging and spatial habitat analysis to achieve accurate prediction of thymoma risk classification.

MATERIALS AND METHODS

205 consecutive patients with thymoma confirmed by surgical pathology were recruited from three medical centers. Venous phase enhanced CT images were used to delineate the tumor, and radiomics, 2D and 3D deep learning models based on the whole tumor were established and feature extraction was performed. The tumors were divided into different sub-regions by K-means clustering method and the corresponding features were obtained. The clinical-conventional imaging data of the patients were collected and evaluated, and the univariate and multivariate analysis were used for screening. The above types of features were fused with each other to construct a variety of combined models. Quantitative indicators such as area under the receiver operating characteristic (ROC) curve (AUC) were calculated to evaluate the performance of the model.

RESULTS

The AUC of RDLCSM developed based on LightGBM classifier was 0.953 in the training cohort, 0.930 in the internal validation cohort, 0.924 and 0.903 in the two external validation cohorts, respectively. RDLCSM performs better than RDLM (AUC range: 0.831-0.890) and 2DLCSM (AUC range: 0.785-0.916) based on KNN. In addition, RDLCSM had the highest accuracy (0.818-0.882) and specificity (0.926-1.000).

INTERPRETATION

The RDLCSM, which combines whole-tumor radiomics, 2D and 3D deep learning, clinical-visual radiology, and subregional omics, can be used as a non-invasive tool to predict thymoma risk classification.

Externally validated and clinically useful machine learning algorithms to support patient-related decision-making in oncology: a scoping review

BACKGROUND

This scoping review systematically maps externally validated machine learning (ML)-based models in cancer patient care, quantifying their performance, and clinical utility, and examining relationships between models, cancer types, and clinical decisions. By synthesizing evidence, this study identifies, strengths, limitations, and areas requiring further research.

METHODS

The review followed the Joanna Briggs Institute's methodology, Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines, and the Population, Concept, and Context mnemonic. Searches were conducted across Embase, IEEE Xplore, PubMed, Scopus, and Web of Science (January 2014-September 2022), targeting English-language quantitative studies in Q1 journals (SciMago Journal and Country Ranking > 1) that used ML to evaluate clinical outcomes for human cancer patients with commonly available data. Eligible models required external validation, clinical utility assessment, and performance metric reporting. Studies involving genetics, synthetic patients, plants, or animals were excluded. Results were presented in tabular, graphical, and descriptive form.

RESULTS

From 4023 deduplicated abstracts and 636 full-text reviews, 56 studies (2018-2022) met the inclusion criteria, covering diverse cancer types and applications. Convolutional neural networks were most prevalent, demonstrating high performance, followed by gradient- and decision tree-based algorithms. Other algorithms, though underrepresented, showed promise. Lung and digestive system cancers were most frequently studied, focusing on diagnosis and outcome predictions. Most studies were retrospective and multi-institutional, primarily using image-based data, followed by text-based and hybrid approaches. Clinical utility assessments involved 499 clinicians and 12 tools, indicating improved clinician performance with AI assistance and superior performance to standard clinical systems.

DISCUSSION

Interest in ML-based clinical decision-making has grown in recent years alongside increased multi-institutional collaboration. However, small sample sizes likely impacted data quality and generalizability. Persistent challenges include limited international validation across ethnicities, inconsistent data sharing, disparities in validation metrics, and insufficient calibration reporting, hindering model comparison reliability.

CONCLUSION

Successful integration of ML in oncology decision-making requires standardized data and methodologies, larger sample sizes, greater transparency, and robust validation and clinical utility assessments.

OTHER

Financed by FCT-Fundação para a Ciência e a Tecnologia (Portugal, project LA/P/0063/2020, grant 2021.09040.BD) as part of CSS's Ph.D. This work was not registered.

Computed tomography radiomics-based combined model for predicting thymoma risk subgroups: a multicenter retrospective study

RATIONALE AND OBJECTIVES

Accurately distinguishing histological subtypes and risk categorization of thymomas is difficult. To differentiate the histologic risk categories of thymomas, we developed a combined radiomics model based on non-enhanced and contrast-enhanced computed tomography (CT) radiomics, clinical, and semantic features.

MATERIALS AND METHODS

In total, 360 patients with pathologically-confirmed thymomas who underwent CT examinations were retrospectively recruited from three centers. Patients were classified using improved pathological classification criteria as low-risk (LRT: types A and AB) or high-risk (HRT: types B1, B2, and B3). The training and external validation sets comprised 274 (from centers 1 and 2) and 86 (center 3) patients, respectively. A clinical-semantic model was built using clinical and semantic variables. Radiomics features were filtered using intraclass correlation coefficients, correlation analysis, and univariate logistic regression. An optimal radiomics model (Rad_score) was constructed using the AutoML algorithm, while a combined model was constructed by integrating Rad_score with clinical and semantic features. The predictive and clinical performances of the models were evaluated using receiver operating characteristic/calibration curve analyses and decision-curve analysis, respectively.

RESULTS

Radiomics and combined models (area under curve: training set, 0.867 and 0.884; external validation set, 0.792 and 0.766, respectively) exhibited performance superior to the clinical-semantic model. The combined model had higher accuracy than the radiomics model (0.79 vs. 0.78, p<0.001) in the entire cohort. The original_firstorder_median of venous phase had the highest relative importance among features in the radiomics model.

CONCLUSION

Radiomics and combined radiomics models may serve as noninvasive discrimination tools to differentiate thymoma risk classifications.

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).

Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences

The aim of this study was to develop a medical imaging and comprehensive stacked learning-based method for predicting high- and low-risk thymoma. A total of 126 patients with thymomas and 5 patients with thymic carcinoma treated at our institution, including 65 low-risk patients and 66 high-risk patients, were retrospectively recruited. Among them, 78 patients composed the training cohort, while the remaining 53 patients formed the validation cohort. We extracted 1702 features each from the patients' arterial-, venous-, and plain-phase images. Pairwise subtraction of these features yielded 1702 arterial-venous, arterial-plain, and venous-plain difference features each. The Mann‒Whitney U test and least absolute shrinkage and selection operator (LASSO) and SelectKBest methods were employed to select the best features from the training set. Six models were built with a stacked learning algorithm. By applying stacked ensemble learning, three machine learning algorithms (XGBoost, multilayer perceptron (MLP), and random forest) were combined by XGBoost to produce the the six basic imaging models. Then, the XGBoost algorithm was applied to the six basic imaging models to construct a combined radiomic model. Finally, the radiomic model was combined with clinical information to create a nomogram that could easily be used in clinical practice to predict the thymoma risk category. The areas under the curve (AUCs) of the combined radiomic model in the training and validation cohorts were 0.999 (95% CI 0.988-1.000) and 0.967 (95% CI 0.916-1.000), respectively, while those of the nomogram were 0.999 (95% CI 0.996-1.000) and 0.983 (95% CI 0.990-1.000). This study describes the application of CT-based radiomics in thymoma patients and proposes a nomogram for predicting the risk category for this disease, which could be advantageous for clinical decision-making for affected patients.

Deep learning-based radiomic nomogram to predict risk categorization of thymic epithelial tumors: A multicenter study

PURPOSE

The study was aimed to develop and evaluate a deep learning-based radiomics to predict the histological risk categorization of thymic epithelial tumors (TETs), which can be highly informative for patient treatment planning and prognostic assessment.

METHOD

A total of 681 patients with TETs from three independent hospitals were included and separated into derivation cohort and external test cohort. Handcrafted and deep learning features were extracted from preoperative contrast-enhanced CT images and selected to build three radiomics signatures (radiomics signature [Rad_Sig], deep learning signature [DL_Sig] and deep learning radiomics signature [DLR_Sig]) to predict risk categorization of TETs. A deep learning-based radiomic nomogram (DLRN) was then depicted to visualize the classification evaluation. The performance of predictive models was compared using the receiver operating characteristic and decision curve analysis (DCA).

RESULTS

Among three radiomics signatures, DLR_Sig demonstrated optimum performance with an AUC of 0.883 for the derivation cohort and 0.749 for the external test cohort. Combining DLR_Sig with age and gender, DLRN was depict and exhibited optimum performance among all radiomics models with an AUC of 0.965, accuracy of 0.911, sensitivity of 0.921 and specificity of 0.902 in the derivation cohort, and an AUC of 0.786, accuracy of 0.774, sensitivity of 0.778 and specificity of 0.771 in the external test cohort. The DCA showed that DLRN had greater clinical benefit than other radiomics signatures.

CONCLUSIONS

Our study developed and validated a DLRN to accurately predict the risk categorization of TETs, which has potential to facilitate individualized treatment and improve patient prognosis evaluation.

Risk factor analysis for major mediastinal vessel invasion in thymic epithelial tumors based on multi-slice CT Imaging

Objective

To explore the characteristics and risk factors for major mediastinal vessel invasion in different risk grades of thymic epithelial tumors (TETs) based on computed tomography (CT) imaging, and to develop prediction models of major mediastinal artery and vein invasion.

Methods

One hundred and twenty-two TET patients confirmed by histopathological analysis who underwent thorax CT were enrolled in this study. Clinical and CT data were retrospectively reviewed for these patients. According to the abutment degree between the tumor and major mediastinal vessels, the arterial invasion was divided into grade I, II, and III (< 25%, 25 - 49%, and ≥ 50%, respectively); the venous invasion was divided into grade I and II (< 50% and ≥ 50%). The degree of vessel invasion was compared among different defined subtypes or stages of TETs using the chi-square tests. The risk factors associated with TET vascular invasion were identified using multivariate logistic regression analysis.

Results

Based on logistic regression analysis, male patients (β = 1.549; odds ratio, 4.824) and the pericardium or pleural invasion (β = 2.209; odds ratio, 9.110) were independent predictors of 25% artery invasion, and the midline location (β = 2.504; odds ratio, 12.234) and mediastinal lymphadenopathy (β = 2.490; odds ratio, 12.06) were independent predictors of 50% artery invasion. As for 50% venous invasion, the risk factors include midline location (β = 2.303; odds ratio, 10.0), maximum tumor diameter larger than 5.9 cm (β = 4.038; odds ratio, 56.736), and pericardial or pleural effusion (β = 1.460; odds ratio, 4.306). The multivariate logistic model obtained relatively high predicting efficacy, and the area under the curve (AUC), sensitivity, and specificity were 0.944, 84.6%, and 91.7% for predicting 50% artery invasion, and 0.913, 81.8%, and 86.0% for 50% venous invasion in TET patients, respectively.

Conclusion

Several CT features can be used as independent predictors of ≥50% artery or venous invasion. A multivariate logistic regression model based on CT features is helpful in predicting the vascular invasion grades in patients with TET.

Diagnostic performance of radiomics model for preoperative risk categorization in thymic epithelial tumors: a systematic review and meta-analysis

BACKGROUND

Incidental thymus region masses during thoracic examinations are not uncommon. The clinician's decision-making for treatment largely depends on imaging findings. Due to the lack of specific indicators, it may be of great value to explore the role of radiomics in risk categorization of the thymic epithelial tumors (TETs).

METHODS

Four databases (PubMed, Web of Science, EMBASE and the Cochrane Library) were screened to identify eligible articles reporting radiomics models of diagnostic performance for risk categorization in TETs patients. The quality assessment of diagnostic accuracy studies 2 (QUADAS-2) and radiomics quality score (RQS) were used for methodological quality assessment. The pooled area under the receiver operating characteristic curve (AUC), sensitivity and specificity with their 95% confidence intervals were calculated.

RESULTS

A total of 2134 patients in 13 studies were included in this meta-analysis. The pooled AUC of 11 studies reporting high/low-risk histologic subtypes was 0.855 (95% CI, 0.817-0.893), while the pooled AUC of 4 studies differentiating stage classification was 0.826 (95% CI, 0.817-0.893). Meta-regression revealed no source of significant heterogeneity. Subgroup analysis demonstrated that the best diagnostic imaging was contrast enhanced computer tomography (CECT) with largest pooled AUC (0.873, 95% CI 0.832-0.914). Publication bias was found to be no significance by Deeks' funnel plot.

CONCLUSIONS

This present study shows promise for preoperative selection of high-risk TETs patients based on radiomics signatures with current available evidence. However, methodological quality in further studies still needs to be improved for feasibility confirmation and clinical application of radiomics-based models in predicting risk categorization of the thymic epithelial tumors.

Integrating CT-based radiomic model with clinical features improves long-term prognostication in high-risk prostate cancer

Objective

High-risk prostate cancer (PCa) is often treated by prostate-only radiotherapy (PORT) owing to its favourable toxicity profile compared to whole-pelvic radiotherapy. Unfortunately, more than 50% patients still developed disease progression following PORT. Conventional clinical factors may be unable to identify at-risk subgroups in the era of precision medicine. In this study, we aimed to investigate the prognostic value of pre-treatment planning computed tomography (pCT)-based radiomic features and clinical attributes to predict 5-year progression-free survival (PFS) in high-risk PCa patients following PORT.

Materials and methods

A total of 176 biopsy-confirmed PCa patients who were treated at the Hong Kong Princess Margaret Hospital were retrospectively screened for eligibility. Clinical data and pCT of one hundred eligible high-risk PCa patients were analysed. Radiomic features were extracted from the gross-tumour-volume (GTV) with and without applying Laplacian-of-Gaussian (LoG) filter. The entire patient cohort was temporally stratified into a training and an independent validation cohort in a ratio of 3:1. Radiomics (R), clinical (C) and radiomic-clinical (RC) combined models were developed by Ridge regression through 5-fold cross-validation with 100 iterations on the training cohort. A model score was calculated for each model based on the included features. Model classification performance on 5-year PFS was evaluated in the independent validation cohort by average area-under-curve (AUC) of receiver-operating-characteristics (ROC) curve and precision-recall curve (PRC). Delong's test was used for model comparison.

Results

The RC combined model which contains 6 predictive features (tumour flatness, root-mean-square on fine LoG-filtered image, prostate-specific antigen serum concentration, Gleason score, Roach score and GTV volume) was the best-performing model (AUC = 0.797, 95%CI = 0.768-0.826), which significantly outperformed the R-model (AUC = 0.795, 95%CI = 0.774-0.816) and C-model (AUC = 0.625, 95%CI = 0.585-0.665) in the independent validation cohort. Besides, only the RC model score significantly classified patients in both cohorts into progression and progression-free groups regarding their 5-year PFS (p< 0.05).

Conclusion

Combining pCT-based radiomic and clinical attributes provided superior prognostication value regarding 5-year PFS in high-risk PCa patients following PORT. A large multi-centre study will potentially aid clinicians in implementing personalised treatment for this vulnerable subgroup in the future.

Practical Model for Residual/Recurrent Cervical Intraepithelial Lesions in Patients with Negative Margins after Cold-Knife Conization

Objective: This study aimed to identify reliable risk factors for residual/recurrent cervical intraepithelial lesions in patients with negative margins after cold-knife conization. Methods: A total of 2352 women with HSILs (high-grade squamous intraepithelial lesions) with negative margins who underwent cold-knife conization between January 2014 and December 2020 were included; in total, 1411 women were assigned to the development cohort, and 941 women were assigned to the validation cohort. Multivariate logistic regression was used to build four predictive models based on the different combinations of follow-up data (Model A: preoperative factors; Model B: first-follow-up data; Model C: second-follow-up data; Model D: data from both follow-ups). The accuracy, sensitivity, specificity, false-positive rate (FPR), false-negative rate (FNR), and area under the receiver operating characteristic curve (AUC) were evaluated on the validation cohort. The predictive power of risk factors was further validated using six machine learning algorithms. Results: Model D demonstrated the highest AUC of 0.91 (95% CI, 0.87 to 0.96) in the validation cohort, whereas Models A, B, and C achieved AUCs of 0.69 (95% CI, 0.59 to 0.78), 0.88 (95% CI, 0.80 to 0.95), and 0.89 (95% CI, 0.81 to 0.97) respectively. The six machine learning methods achieved consistent results. Kaplan-Meier (KM) survival curves demonstrated that our models could effectively stratify patients with all models (p < 0.05 for all models). Conclusion: Our model, which is based on preoperative and follow-up factors, can serve as a complementary screening procedure for the early detection or prediction of recurrence after cold-knife conization in HSIL patients.

Grading of soft tissues sarcomas using radiomics models: Choice of imaging methods and comparison with conventional visual analysis

Purpose

To determine which combination of imaging modalities/contrast, radiomics models, and how many features provides the best diagnostic performance for the differentiation between low- and high-grade soft tissue sarcomas (STS) using a radiomics approach.

Methods

MRI and CT from 39 patients with a histologically confirmed STS were prospectively analyzed. Images were evaluated both quantitatively by radiomics models and qualitatively by visual evaluation (used as reference) for grading (low-grade vs high-grade). In radiomics analysis, 120 radiomic features were extracted and contributed into three models: least absolute shrinkage and selection operator with logistic regression(LASSO-LR), recursive feature elimination and cross-validation (RFECV-SVC) and analysis of variance with SVC (ANOVA-SVC). Those were applied to different combinations of imaging modalities acquisition, with and without contrast medium administration, as well as selected number of features.

Results

Fat-saturated T2w (FS-T2w) MR images using RFECV-SVC radiomic models involving five features yielded the best results with mean sensitivity, specificity, and accuracy of 92% ± 10%, 78% ± 30%, and 89% ± 12%, respectively. The performance of radiomics was better than that of conventional analysis (67% accuracy) for STS grading. Combination of multiple contrast or imaging modalities did not increase the diagnostic performance.

Conclusion

FS-T2w MR images alone with a five-feature radiomics analysis usingh REFCV-SVC model may be able to provide sufficient diagnositic performance compared to conventional visual evaluation with multiple MRI contrast and CT imaging.