A radiomics nomogram for predicting the meningioma grade based on enhanced T1WI images

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.

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.

An MRI-Based Deep Transfer Learning Radiomics Nomogram to Predict Ki-67 Proliferation Index of Meningioma

The objective of this study was to predict Ki-67 proliferation index of meningioma by using a nomogram based on clinical, radiomics, and deep transfer learning (DTL) features. A total of 318 cases were enrolled in the study. The clinical, radiomics, and DTL features were selected to construct models. The calculation of radiomics and DTL score was completed by using selected features and correlation coefficient. The deep transfer learning radiomics (DTLR) nomogram was constructed by selected clinical features, radiomics score, and DTL score. The area under the receiver operator characteristic curve (AUC) was calculated. The models were compared by Delong test of AUCs and decision curve analysis (DCA). The features of sex, size, and peritumoral edema were selected to construct clinical model. Seven radiomics features and 15 DTL features were selected. The AUCs of clinical, radiomics, DTL model, and DTLR nomogram were 0.746, 0.75, 0.717, and 0.779 respectively. DTLR nomogram had the highest AUC of 0.779 (95% CI 0.6643-0.8943) with an accuracy rate of 0.734, a sensitivity value of 0.719, and a specificity value of 0.75 in test set. There was no significant difference in AUCs among four models in Delong test. The DTLR nomogram had a larger net benefit than other models across all the threshold probability. The DTLR nomogram had a satisfactory performance in Ki-67 prediction and could be a new evaluation method of meningioma which would be useful in the clinical decision-making.

The value of an apparent diffusion coefficient histogram model in predicting meningioma recurrence

OBJECTIVE

To investigate the predictive value of a model combining conventional MRI features and apparent diffusion coefficient (ADC) histogram parameters for meningioma recurrence.

MATERIALS AND METHODS

Seventy-two meningioma patients confirmed by surgical and pathological findings in our hospital (January 2017-June 2020) were retrospectively and divided into the recurrence and non-recurrence group. MaZda software was used to delineate the region of interest at the largest tumor level and generate histogram parameters. Univariate and multivariate logistic regression analysis were used to construct the nomogram for predicting recurrence. The predictive efficacy and diagnostic of this model were assessed by calibration and decision curve analysis, and receiver operating characteristic curve, respectively.

RESULTS

Maximum diameter, necrosis, enhancement uniformity, age, Simpson, tumor shape, and ADC first percentile (ADCp1) were significantly different between the two groups (p < 0.05), with the latter four being independent risk factors for recurrence. The model constructed combining the four factors had the best predictive efficacy, and the area under the curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 0.965(0.892-0.994), 90.3%, 92.6%, 88.9%, 83.3%, and 95.2%, respectively. The calibration curve showed good agreement between the model-predicted and actual probabilities of recurrence. The decision curve analysis indicated good clinical availability of the model.

CONCLUSION

This model based on conventional MRI features and ADC histogram parameters can directly and reliably predict meningioma recurrence, providing a guiding basis for selecting treatment options and individualized treatment.

Dual-Level Augmentation Radiomics Analysis for Multisequence MRI Meningioma Grading

BACKGROUND

Preoperative, noninvasive prediction of meningioma grade is important for therapeutic planning and decision making. In this study, we propose a dual-level augmentation strategy incorporating image-level augmentation (IA) and feature-level augmentation (FA) to tackle class imbalance and improve the predictive performance of radiomics for meningioma grading on Magnetic Resonance Imaging (MRI).

METHODS

This study recruited 160 consecutive patients with pathologically proven meningioma (129 low-grade (WHO grade I) tumors; 31 high-grade (WHO grade II and III) tumors) with preoperative multisequence MRI imaging. A dual-level augmentation strategy combining IA and FA was applied and evaluated in 100 repetitions in 3-, 5-, and 10-fold cross-validation.

RESULTS

The best area under the receiver operating characteristics curve of our method in 100 repetitions was ≥0.78 in all cross-validations. The corresponding cross-validation sensitivities (cross-validation specificity) were 0.72 (0.69), 0.76 (0.71), and 0.63 (0.82) in 3-, 5-, and 10-fold cross-validation, respectively. The proposed method achieved significantly better performance and distribution of results, outperforming single-level augmentation (IA or FA) or no augmentation in each cross-validation.

CONCLUSIONS

The dual-level augmentation strategy using IA and FA significantly improves the performance of the radiomics model for meningioma grading on MRI, allowing better radiomics-based preoperative stratification and individualized treatment.

Prediction of progesterone receptor expression in high-grade meningioma by using radiomics based on enhanced T1WI

AIM

To predict progesterone receptor (PR) expression of high-grade meningioma using radiomics based on enhanced T1-weighted imaging (WI).

MATERIALS AND METHODS

There were 157 cases of high-grade meningioma in the study. Seventy-eight cases had negative expression and 79 cases had positive expression. Spearman's rank correlation coefficient and least absolute shrinkage and selection operator (LASSO) regression were used to select the valuable features. The models were developed by naive Bayes (NB), random forest (RF), and support vector machine (SVM). Receiver operating characteristic (ROC) and decision curve analysis (DCA) analysis were used to assess the models.

RESULTS

Nine features were selected as the valuable features using Spearman's analysis and LASSO regression. The RF and NB models achieved the same area under the ROC curve (AUC) of 0.75, which was higher than that of SVM (0.74). There was no significant difference among the AUCs of the three models (p>0.05). There was a larger net benefit in the RF model than the SVM and NB models across all threshold probabilities in the DCA analysis.

CONCLUSION

The RF model had good performance in predicting PR expression of high-grade meningioma. PR expression evaluation for high-grade meningioma would be helpful in clinical practice.

MRI-based machine learning models predict the malignant biological behavior of meningioma

BACKGROUND

The WHO grade and Ki-67 index are independent indices used to evaluate the malignant biological behavior of meningioma. This study aims to develop MRI-based machine learning models to predict the malignant biological behavior of meningioma from the perspective of the WHO grade, Ki-67 index, and their combination.

METHODS

This multicenter, retrospective study included 313 meningioma patients, of which 70 were classified as high-grade (WHO II/III) and 243 as low-grade (WHO I). The Ki-67 expression was classified into low-expression (n = 216) and high-expression (n = 97) groups with a threshold of 5%. Among them, there were 128 patients with malignant biological behavior whose WHO grade or Ki-67 index increased either or both. Data from Center A and B are were utilized for model development, while data from Center C and D were used for external validation. Radiomic features were extracted from the maximum cross-sectional area (2D) region of Interest (ROI) and the whole tumor volume (3D) ROI using different paraments from the T1, T2-weighted, and T1 contrast-enhanced sequences (T1CE), followed by five independent feature selections and eight classifiers. 240 prediction models were constructed to predict the WHO grade, Ki-67 index and their combination respectively. Models were evaluated by cross-validation in training set (n = 224). Suitable models were chosen by comparing the cross-validation (CV) area under the curves (AUC) and their relative standard deviations (RSD). Clinical and radiological features were collected and analyzed; meaningful features were combined with radiomic features to establish the clinical-radiological-radiomic (CRR) models. The receiver operating characteristic (ROC) analysis was used to evaluate those models in validation set. Radiomic models and CRR models were compared by Delong test.

RESULTS

1218 and 1781 radiomic features were extracted from 2D ROI and 3D ROI of each sequence. The selected grade, Ki-67 index and their combination radiomic models were T1CE-2D-LASSO-LR, T1CE-3D-LASSO-NB, and T1CE-2D-LASSO-LR, with cross-validated AUCs on the training set were 0.857, 0.798, and 0.888, the RSDs were 0.06, 0.09, and 0.05, the validation set AUCs were 0.829, 0.752, and 0.904, respectively. Heterogeneous enhancement was found to be associated with high grade and Ki-67 status, while surrounding invasion was associated with the high grade status, peritumoral edema and cerebrospinal fluid space surrounding tumor were correlated with the high Ki-67 status. The Delong test showed that these significant radiological features did not significantly improve the predictive performance. The AUCs for CRR models predicting grade, Ki-67 index, and their combination in the validation set were 0.821, 0.753, and 0.906, respectively.

CONCLUSIONS

This study demonstrated that MRI-based machine learning models could effectively predict the grade, Ki-67 index of meningioma. Models considering these two indices might be valuable for improving the predictive sensitivity and comprehensiveness of prediction of malignant biological behavior of meningioma.

Radiomics based on preoperative rectal cancer MRI to predict the metachronous liver metastasis

PURPOSE

At present, there are few effective method to predict metachronous liver metastasis (MLM) from rectal cancer. We aim to investigate the efficacy of radiomics based on multiparametric MRI of first diagnosed rectal cancer in predicting MLM from rectal cancer.

METHODS

From 301 consecutive histopathologically confirmed rectal cancer patients, 130 patients who have no distant metastasis detected at the time of diagnosis were enrolled and divided into MLM group (n = 49) and non-MLM group (n = 81) according to whether liver metastasis be detected later than 6 month after the first diagnosis of rectal cancer within 3 years' follow-up. The 130 patients were divided into a training set (n = 91) and a testing set (n = 39) at a ratio of 7:3 by stratified sampling using SPSS 24.0 software. The DWI model, HD T₂WI model, and DWI + HD T₂WI model were constructed respectively. The best performing model was selected and combined with the screened clinical features (including non-radiomics MRI features) to construct a fusion model. The testing set was used to evaluate the performance of the models, and the area under the curve (AUC) of receiver operating characteristics (ROC) was calculated for both the training set and the testing set.

RESULTS

The AUC of the DWI + HD T₂WI model in the testing set was higher than that of the DWI or the HD T₂ model alone with statistically significance (P < 0.05). The screened clinical features were extramural vascular invasion (EMVI), T and N stages in MRI (_mrT, _mrN), and the distance from the lower edge of the tumor to the anal verge. The AUC of the fusion model in the testing set was 0.911. Decision curves and nomogram also showed that the fusion model had excellent clinical performance.

CONCLUSION

The fusion model of primary rectal cancer MRI based radiomics combing clinical features can effectively predict MLM from rectal cancer, which may assist clinicians in formulating individualized monitoring and treatment plans.

Nomograms for Predicting the Risk and Prognosis of Liver Metastases in Pancreatic Cancer: A Population-Based Analysis

The liver is the most prevalent location of distant metastasis for pancreatic cancer (PC), which is highly aggressive. Pancreatic cancer with liver metastases (PCLM) patients have a poor prognosis. Furthermore, there is a lack of effective predictive tools for anticipating the diagnostic and prognostic techniques that are needed for the PCLM patients in current clinical work. Therefore, we aimed to construct two nomogram predictive models incorporating common clinical indicators to anticipate the risk factors and prognosis for PCLM patients. Clinicopathological information on pancreatic cancer that referred to patients who had been diagnosed between the years of 2004 and 2015 was extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate logistic regression analyses and a Cox regression analysis were utilized to recognize the independent risk variables and independent predictive factors for the PCLM patients, respectively. Using the independent risk as well as prognostic factors derived from the multivariate regression analysis, we constructed two novel nomogram models for predicting the risk and prognosis of PCLM patients. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, the consistency index (C-index), and the calibration curve were then utilized to establish the accuracy of the nomograms’ predictions and their discriminability between groups. Using a decision curve analysis (DCA), the clinical values of the two predictors were examined. Finally, we utilized Kaplan–Meier curves to examine the effects of different factors on the prognostic overall survival (OS). As many as 1898 PCLM patients were screened. The patient’s sex, primary site, histopathological type, grade, T stage, N stage, bone metastases, lung metastases, tumor size, surgical resection, radiotherapy, and chemotherapy were all found to be independent risks variables for PCLM in a multivariate logistic regression analysis. Using a multivariate Cox regression analysis, we discovered that age, histopathological type, grade, bone metastasis, lung metastasis, tumor size, and surgery were all independent prognostic variables for PCLM. According to these factors, two nomogram models were developed to anticipate the prognostic OS as well as the risk variables for the progression of PCLM in PCLM patients, and a web-based version of the prediction model was constructed. The diagnostic nomogram model had a C-index of 0.884 (95% CI: 0.876–0.892); the prognostic model had a C-index of 0.686 (95% CI: 0.648–0.722) in the training cohort and a C-index of 0.705 (95% CI: 0.647–0.758) in the validation cohort. Subsequent AUC, calibration curve, and DCA analyses revealed that the risk and predictive model of PCLM had high accuracy as well as efficacy for clinical application. The nomograms constructed can effectively predict risk and prognosis factors in PCLM patients, which facilitates personalized clinical decision-making for patients.

Meningioma grading based on positron emission tomography: A systematic review and meta-analysis

Introduction

Meningiomas are the most common central nervous system tumor in adults. Knowledge of the tumor grade can guide optimal treatment timing and shape personalized follow-up strategies. Positron emission tomography (PET) has been utilized for the metabolic assessment of various intracranial space-occupying lesions. Herewith, we set out to evaluate the diagnostic accuracy of PET for the noninvasive assessment of meningioma's grade.

Materials and methods

The Medline, Scopus and Cochrane databases were systematically searched in March 2022 for studies that evaluated the sensitivity and specificity of PET compared to the gold standard of histological diagnosis in the grading of meningiomas. Summary statistics will be calculated and scatter plots, summary curve from the HSROC model and posterior predictions by empirical Bayes estimates will be presented.

Results

Five studies consisting of 242 patients with a total of 196 low-grade (Grade 1) and 46 high grade (Grade 2/3) meningiomas were included in our analysis. Three of the included studies used ¹⁸F-FDG, one study used ¹⁸F-FLT and one used(Whiting et al., 2011) 18 F-FET as PET tracers. The pooled sensitivity was 76% (95% CI: 52%-91%) and the pooled specificity was 89% (95% CI: 83%-93%). The diagnostic odds ratio was 27.17 (95% CI: 9.22-80.06), the positive likelihood ratio was 7.18 (95% CI: 4.54-11.34) and the negative likelihood ratio was 0.26 (95% CI: 0.11-0.61).

Conclusion

PET is a promising and viable option as a noninvasive imaging tool to differentiate the meningioma grades. However, currently it cannot overtake the gold standard of histological grade confirmation. More studies are required for further validation and refinement of this imaging technique and assessment of other radiotracers as well.

Performance comparison of 2D and 3D MRI radiomics features in meningioma grade prediction: A preliminary study

Objectives

The objective of this study was to compare the predictive performance of 2D and 3D radiomics features in meningioma grade based on enhanced T1 WI images.

Methods

There were 170 high grade meningioma and 170 low grade meningioma were selected randomly. The 2D and 3D features were extracted from 2D and 3D ROI of each meningioma. The Spearman correlation analysis and least absolute shrinkage and selection operator (LASSO) regression were used to select the valuable features. The 2D and 3D predictive models were constructed by naive Bayes (NB), gradient boosting decision tree (GBDT), and support vector machine (SVM). The ROC curve was drawn and AUC was calculated. The 2D and 3D models were compared by Delong test of AUCs and decision curve analysis (DCA) curve.

Results

There were 1143 features extracted from each ROI. Six and seven features were selected. The AUC of 2D and 3D model in NB, GBDT, and SVM was 0.773 and 0.771, 0.722 and 0.717, 0.733 and 0.743. There was no significant difference in two AUCs (p=0.960, 0.913, 0.830) between 2D and 3D model. The 2D features had a better performance than 3D features in NB models and the 3D features had a better performance than 2D features in GBDT models. The 2D features and 3D features had an equal performance in SVM models.

Conclusions

The 2D and 3D features had a comparable performance in predicting meningioma grade. Considering the issue of time and labor, 2D features could be selected for radiomics study in meningioma.

Key points

There was a comparable performance between 2D and 3D features in meningioma grade prediction. The 2D features was a proper selection in meningioma radiomics study because of its time and labor saving.