Predicting meningioma grades and pathologic marker expression via deep learning

Development and Validation of a Machine Learning Radiomics Model based on Multiparametric MRI for Predicting Progesterone Receptor Expression in Meningioma: A Multicenter Study

RATIONALE AND OBJECTIVES

This study aimed to develop and validate a machine learning-based prediction model for preoperatively predicting progesterone receptor (PR) expression in meningioma patients using multiparametric magnetic resonance imaging (MRI).

MATERIALS AND METHODS

The study retrospectively enrolled 739 patients with pathologically confirmed meningioma from three medical centers, dividing them into four cohorts: training (n = 294), internal test (n = 126), external test 1 (n = 217), and external test 2 (n = 102). Radiomics characteristics were derived from T2-weighted and contrast-enhanced T1-weighted MRI images, followed by feature selection. A machine learning-based combined model was developed by incorporating radiomics scores (rad-scores) from the optimal radiomics model along with clinical predictors. The Shapley additive explanation (SHAP) method was employed to visually represent the process of making predictions. The prognostic value of the model was evaluated using Kaplan-Meier analysis.

RESULTS

Among the 739 patients, 299 (40.5%) had negative PR expression confirmed by pathology. Twelve radiomics features derived from multiparametric MRI were selected to build the radiomics model. Tumor location and enhancement pattern were identified as key clinical predictors and were combined with rad-scores to create a combined model utilizing the extreme gradient boosting (XGBoost) algorithm. The combined model demonstrated strong accuracy and robustness, with area under the curve values of 0.907, 0.827, 0.846, and 0.807 across training, internal test, external test 1, and external test 2 cohorts, respectively. The recurrence-free survival analysis indicated that the combined model was able to effectively categorize patients based on recurrence outcomes.

CONCLUSION

The XGBoost combined model, utilizing multiparametric MRI, shows promise for predicting PR expression in meningioma patients.

MRI-derived radiomics models for prediction of Ki-67 index status in meningioma: a systematic review and meta-analysis

PURPOSE

The Ki-67 marker reflects tumor proliferation and correlates with meningioma prognosis. Here we aim to evaluate the performance of MRI-derived radiomics for Ki-67 index prediction in meningiomas.

METHODS

After a comprehensive search in Web of Science, PubMed, Embase, and Scopus, data extraction and risk of bias assessment was performed. Pooled sensitivity, specificity, positive likelihood ratios (PLR), negative likelihood ratios (NLR), and diagnostic odds ratio (DOR) were computed. The summary receiver operating characteristic (sROC) curve was generated and area under the curve (AUC) was calculated. Separate meta-analyses were conducted for radiomics models and combined models. Heterogeneity was evaluated using the I2 statistic, and subgroup analysis was performed to identify potential sources of heterogeneity. Sensitivity analysis was carried out to detect possible outliers.

RESULTS

Seven studies were included, with six studies analyzed for radiomics model and four for combined model. For radiomics model, the pooled sensitivity, specificity, PLR, NLR, DOR, and AUC were 67 %, 82 %, 8.61, 3.54, 0.43, and 0.79, respectively. For combined model, pooled sensitivity, specificity, PLR, NLR, DOR, and AUC were 78 %, 78 %, 12.19, 3.47, 0.30, and 0.79, respectively. Sensitivity analysis identified no outliers. In radiomics model, potential sources of heterogeneity included mean age and the application of N4ITK bias correction. For combined model, heterogeneity was influenced by mean age, application of N4ITK bias correction, and the use of external validation.

CONCLUSION

Radiomics shows promising ability to predict the Ki-67 index status in meningioma patients, potentially enhancing clinical decision-making and management strategies.

Pathological diagnosis of central nervous system tumours in adults: what's new?

In the course of the last decade, the pathological diagnosis of many tumours of the central nervous system (CNS) has transitioned from a purely histological to a combined histological and molecular approach, resulting in a more precise 'histomolecular diagnosis'. Unfortunately, translation of this refinement in CNS tumour diagnostics into more effective treatment strategies is lagging behind. There is hope though that incorporating the assessment of predictive markers in the pathological evaluation of CNS tumours will help to improve this situation. The present review discusses some novel aspects with regard to the pathological diagnosis of the most common CNS tumours in adults. After a brief update on recognition of clinically meaningful subgroups in adult-type diffuse gliomas and the value of assessing predictive markers in these tumours, more detailed information is provided on predictive markers of (potential) relevance for immunotherapy especially for glioblastomas, IDH-wildtype. Furthermore, recommendations for improved grading of meningiomas by using molecular markers are briefly summarised, and an overview is given on (predictive) markers of interest in metastatic CNS tumours. In the last part of this review, some 'emerging new CNS tumour types' that may occur especially in adults are presented in a table. Hopefully, this review provides useful information on 'what's new' for practising pathologists diagnosing CNS tumours in adults.

Preoperative diagnosis of meningioma sinus invasion based on MRI radiomics and deep learning: a multicenter study

OBJECTIVE

Exploring the construction of a fusion model that combines radiomics and deep learning (DL) features is of great significance for the precise preoperative diagnosis of meningioma sinus invasion.

MATERIALS AND METHODS

This study retrospectively collected data from 601 patients with meningioma confirmed by surgical pathology. For each patient, 3948 radiomics features, 12,288 VGG features, 6144 ResNet features, and 3072 DenseNet features were extracted from MRI images. Thus, univariate logistic regression, correlation analysis, and the Boruta algorithm were applied for further feature dimension reduction, selecting radiomics and DL features highly associated with meningioma sinus invasion. Finally, diagnosis models were constructed using the random forest (RF) algorithm. Additionally, the diagnostic performance of different models was evaluated using receiver operating characteristic (ROC) curves, and AUC values of different models were compared using the DeLong test.

RESULTS

Ultimately, 21 features highly associated with meningioma sinus invasion were selected, including 6 radiomics features, 2 VGG features, 7 ResNet features, and 6 DenseNet features. Based on these features, five models were constructed: the radiomics model, VGG model, ResNet model, DenseNet model, and DL-radiomics (DLR) fusion model. This fusion model demonstrated superior diagnostic performance, with AUC values of 0.818, 0.814, and 0.769 in the training set, internal validation set, and independent external validation set, respectively. Furthermore, the results of the DeLong test indicated that there were significant differences between the fusion model and both the radiomics model and the VGG model (p < 0.05).

CONCLUSIONS

The fusion model combining radiomics and DL features exhibits superior diagnostic performance in preoperative diagnosis of meningioma sinus invasion. It is expected to become a powerful tool for clinical surgical plan selection and patient prognosis assessment.

Performance of Radiomics-based machine learning and deep learning-based methods in the prediction of tumor grade in meningioma: a systematic review and meta-analysis

Currently, the World Health Organization (WHO) grade of meningiomas is determined based on the biopsy results. Therefore, accurate non-invasive preoperative grading could significantly improve treatment planning and patient outcomes. Considering recent advances in machine learning (ML) and deep learning (DL), this meta-analysis aimed to evaluate the performance of these models in predicting the WHO meningioma grade using imaging data. A systematic search was performed in PubMed/MEDLINE, Embase, and the Cochrane Library for studies published up to April 1, 2024, and reporting the performance metrics of the ML models in predicting of WHO meningioma grade using imaging studies. Pooled area under the receiver operating characteristics curve (AUROC), specificity, and sensitivity were estimated. Subgroup and meta-regression analyses were performed based on a number of potential influencing variables. A total of 32 studies with 15,365 patients were included in the present study. The overall pooled sensitivity, specificity, and AUROC of ML methods for prediction of tumor grade in meningioma were 85% (95% CI, 79-89%), 87% (95% CI, 81-91%), and 93% (95% CI, 90-95%), respectively. Both the type of validation and study cohort (training or test) were significantly associated with model performance. However, no significant association was found between the sample size or the type of ML method and model performance. The ML predictive models show a high overall performance in predicting the WHO meningioma grade using imaging data. Further studies on the performance of DL algorithms in larger datasets using external validation are needed.

A multi-modal deep learning model for prediction of Ki-67 for meningiomas using pretreatment MR images

This study developed and validated a deep learning network using baseline magnetic resonance imaging (MRI) to predict Ki-67 status in meningioma patients. A total of 1239 patients were retrospectively recruited from three hospitals between January 2010 and December 2023, forming training, internal validation, and two external validation cohorts. A representation learning framework was utilized for modeling, and performance was assessed against existing methods. Furthermore, Kaplan-Meier survival analysis was conducted to investigate whether the model could be used for tumor growth prediction. The model achieved superior results, with areas under the curve (AUCs) of 0.797 for internal testing and 0.808 for generalization, alongside 0.756 and 0.727 for 3- and 5-year tumor growth predictions, respectively. The prediction was significantly associated with the growth of asymptomatic small meningiomas. Overall, the model provides an effective tool for early prediction of Ki-67 and tumor volume growth, aiding in individualized patient management.

Application of Artificial Intelligence in Prediction of Ki-67 Index in Meningiomas: A Systematic Review and Meta-Analysis

BACKGROUND

The Ki-67 index is a histopathological marker that has been reported to be a crucial factor in the biological behavior and prognosis of meningiomas. Several studies have developed artificial intelligence (AI) models to predict the Ki-67 based on radiomics. In this study, we aimed to perform a systematic review and meta-analysis of AI models that predicted the Ki-67 index in meningioma.

METHODS

Literature records were retrieved on April 27, 2024, using the relevant key terms without filters in PubMed, Embase, Scopus, and Web of Science. Records were screened according to the eligibility criteria, and the data from included studies were extracted. The quality assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. The meta-analysis, sensitivity analysis, and meta-regression were conducted using R software.

RESULTS

Our study included 6 studies. The mean Ki-67 ranged from 2.7 ± 2.97 to 4.8 ± 40.3. Of 6 studies, 5 utilized a machine learning method. The most used AI method was the least absolute shrinkage and selection operator. The area under the curve and accuracy ranged from 0.83 to 0.99 and 0.81 to 0.95, respectively. AI models demonstrated a pooled sensitivity of 87.5% (95% confidence interval [CI]: 75.2%, 94.2%), a specificity of 86.9% (95% CI: 75.8%, 93.4%), and a diagnostic odds ratio of 40.02 (95% CI: 13.5, 156.4). The summary receiver operating characteristic curve indicated an area under the curve of 0.931 for the prediction of Ki-67 index status in intracranial meningiomas.

CONCLUSIONS

AI models have demonstrated promising performance for predicting the Ki-67 index in meningiomas and can optimize the treatment strategy.

Analysis of the Predictability of Postoperative Meningioma Resection Status Based on Clinical Features

Background: Our aim was to investigate the predictability of postoperative meningioma resection status based on clinical features. Methods: We examined 23 clinical features to assess their effectiveness in distinguishing gross total resections (GTR) from subtotal resections (STR). We analyzed whether GTR/STR cases are better predictable if the classification is based on the Simpson grading or the postoperative operative tumor volume (POTV). Results: Using a study cohort comprising a total of 157 patients, multivariate models for the preoperative prediction of GTR/STR outcome in relation to Simpson grading and POTV were developed and subsequently compared. Including only two clinical features, our models showed a notable discriminatory power in predicting postoperative resection status. Our final model, a straightforward decision tree applicable in daily clinical practice, achieved a mean AUC of 0.885, a mean accuracy of 0.866, a mean sensitivity of 0.889, and a mean specificity of 0.772 based on independent test data. Conclusions: Such models can be a valuable tool both for surgical planning and for early planning of postoperative treatment, e.g., for additional radiotherapy/radiosurgery, potentially required in case of subtotal resections.

Research Progress of Artificial Intelligence in the Grading and Classification of Meningiomas

A meningioma is a common primary central nervous system tumor. The histological features of meningiomas vary significantly depending on the grade and subtype, leading to differences in treatment and prognosis. Therefore, early diagnosis, grading, and typing of meningiomas are crucial for developing comprehensive and individualized diagnosis and treatment plans. The advancement of artificial intelligence (AI) in medical imaging, particularly radiomics and deep learning (DL), has contributed to the increasing research on meningioma grading and classification. These techniques are fast and accurate, involve fully automated learning, are non-invasive and objective, enable the efficient and non-invasive prediction of meningioma grades and classifications, and provide valuable assistance in clinical treatment and prognosis. This article provides a summary and analysis of the research progress in radiomics and DL for meningioma grading and classification. It also highlights the existing research findings, limitations, and suggestions for future improvement, aiming to facilitate the future application of AI in the diagnosis and treatment of meningioma.

Radiomics-clinical nomogram for preoperative lymph node metastasis prediction in esophageal carcinoma

OBJECTIVES

This research aimed to develop a radiomics-clinical nomogram based on enhanced thin-section CT radiomics and clinical features for the purpose of predicting the presence or absence of metastasis in lymph nodes among patients with resectable esophageal squamous cell carcinoma (ESCC).

METHODS

This study examined the data of 256 patients with ESCC, including 140 cases with lymph node metastasis. Clinical information was gathered for each case, and radiomics features were derived from thin-section contrast-enhanced CT with the help of a 3D slicer. To validate risk factors that are independent of the clinical and radiomics models, least absolute shrinkage and selection operator logistic regression analysis was used. A nomogram pattern was constructed based on the radiomics features and clinical characteristics. The receiver operating characteristic curve and Brier Score were used to evaluate the model's discriminatory ability, the calibration plot to evaluate the model's calibration, and the decision curve analysis to evaluate the model's clinical utility. The confusion matrix was used to evaluate the applicability of the model. To evaluate the efficacy of the model, 1000 rounds of 5-fold cross-validation were conducted.

RESULTS

The clinical model identified esophageal wall thickness and clinical T (cT) stage as independent risk factors, whereas the radiomics pattern was built based on 4 radiomics features chosen at random. Area under the curve (AUC) values of 0.684 and 0.701 are observed for the radiomics approach and clinical model, respectively. The AUC of nomogram combining radiomics and clinical features was 0.711. The calibration plot showed good agreement between the incidence of lymph node metastasis predicted by the nomogram and the actual probability of occurrence. The nomogram model displayed acceptable levels of performance. After 1000 rounds of 5-fold cross-validation, the AUC and Brier score had median values of 0.702 (IQR: 0.65, 7.49) and 0.21 (IQR: 0.20, 0.23), respectively. High-risk patients (risk point >110) were found to have an increased risk of lymph node metastasis [odds ratio (OR) = 5.15, 95% CI, 2.95-8.99] based on the risk categorization.

CONCLUSION

A successful preoperative prediction performance for metastasis to the lymph nodes among patients with ESCC was demonstrated by the nomogram that incorporated CT radiomics, wall thickness, and cT stage.

ADVANCES IN KNOWLEDGE

This study demonstrates a novel radiomics-clinical nomogram for lymph node metastasis prediction in ESCC, which helps physicians determine lymph node status preoperatively.