Classification Of Meningiomas Research Articles

F.3 Multicentre prospective validation of integrated molecular classification of meningiomas and prediction of recurrence risk using DNA methylation

Background: Meningiomas have significant heterogeneity between patients, making prognostication challenging. For this study, we prospectively validate the prognostic capabilities of a DNA methylation-based predictor and multiomic molecular groups (MG) of meningiomas. Methods: DNA methylation profiles were generated using the Illumina EPICarray. MG were assigned as previously published. Performance of our methylation-based predictor and MG were compared with WHO grade using generalized boosted regression modeling by generating time-dependent receiver operating characteristic (ROC) curves and computing area under the ROC curves (AUCs) along with their 95% confidence interval using bootstrap resampling. Results: 295 meningiomas treated from 2018-2021 were included. Methylation-defined high-risk meningiomas had significantly poorer PFS and OS compared to low-risk cases (p<0.0001). Methylation risk increased with higher WHO grade and MG. Higher methylome risk (HR 4.89, 95%CI 2.02-11.82) and proliferative MG (HR 4.11, 95%CI 1.29-13.06) were associated with significantly worse PFS independent of WHO grade, extent of resection, and adjuvant RT. Both methylome-risk and MG classification predicted 3- and 5-year PFS and OS more accurately than WHO grade alone (ΔAUC=0.10-0.23). 42 cases were prescribed adjuvant RT prospectively although RT did not significantly improve PFS in high-risk cases (p=0.41). Conclusions: Molecular profiling outperforms conventional WHO grading for prognostication in an independent, prospectively collected cohort of meningiomas.

Clinical implications of DNA methylation-based integrated classification of histologically defined grade 2 meningiomas

The combination of DNA methylation analysis with histopathological and genetic features allows for a more accurate risk stratification and classification of meningiomas. Nevertheless, the implications of this classification for patients with grade 2 meningiomas, a particularly heterogeneous tumor entity, are only partially understood. We correlate the outcomes of histopathologically confirmed grade 2 meningioma with an integrated molecular-morphologic risk stratification and determine its clinical implications. Grade 2 meningioma patients treated at our institution were re-classified using an integrated risk stratification involving DNA methylation array-based data, copy number assessment and TERT promoter mutation analyses. Grade 2 meningioma cases according to the WHO 2021 criteria treated between 2007 and 2021 (n = 100) were retrospectively analyzed. The median clinical and radiographic follow-up periods were 59.8 and 54.4 months. A total of 38 recurrences and 17 deaths were observed. The local control rates of the entire cohort after 2-, 4-, and 6-years were 84.3%, 68.5%, and 50.8%, with a median local control time of 77.2 months. The distribution of the integrated risk groups were as follows: 31 low, 54 intermediate, and 15 high risk cases. In the multivariable Cox regression analysis, integrated risk groups were significantly associated with the risk of local recurrence (hazard ratio (HR) intermediate: 9.91, HR high-risk: 7.29, p < 0.01). Gross total resections decreased the risk of local tumor progression (HR gross total resection: 0.19, p < 0.01). The comparison of 1p status and integrated risk groups (low vs. intermediate/high) revealed nearly identical local control rates within their respective subgroups. In summary, only around 50% of WHO 2021 grade 2 meningiomas have an intermediate risk profile. Integrated molecular risk stratification is crucial to guide the management of patients with grade 2 tumors and should be routinely applied to avoid over- and undertreatment, especially concerning the use of adjuvant radiotherapy.

The Evolving Classification of Meningiomas: Integration of Molecular Discoveries to Inform Patient Care.

Meningioma classification and treatment have evolved over the past eight decades. Since Bailey, Cushing, and Eisenhart's description of meningiomas in the 1920s and 1930s, there have been continual advances in clinical stratification by histopathology, radiography and, most recently, molecular profiling, to improve prognostication and predict response to therapy. Precise and accurate classification is essential to optimizing management for patients with meningioma, which involves surveillance imaging, surgery, primary or adjuvant radiotherapy, and consideration for clinical trials. Currently, the World Health Organization (WHO) grade, extent of resection (EOR), and patient characteristics are used to guide management. While these have demonstrated reliability, a substantial number of seemingly benign lesions recur, suggesting opportunities for improvement of risk stratification. Furthermore, the role of adjuvant radiotherapy for grade 1 and 2 meningioma remains controversial. Over the last decade, numerous studies investigating the molecular drivers of clinical aggressiveness have been reported, with the identification of molecular markers that carry clinical implications as well as biomarkers of radiotherapy response. Here, we review the historical context of current practices, highlight recent molecular discoveries, and discuss the challenges of translating these findings into clinical practice.

DCGAN-based data augmentation for improving CNN performance in meningioma classification

Using Magnetic Resonance Imaging (MRI) to scan the brain and using the image to identify whether the patient has a brain tumor or not is the common way doctors use it today. However, as this may potentially add to the workload of healthcare professionals, it becomes crucial to explore methods for automating image identification. One effective algorithm for this purpose is the utilization of a Convolutional Neural Network (CNN) network. However, when applying a CNN network to discern whether an individual has meningioma or not, it becomes evident that the available data may be limited. Meningioma is relatively uncommon, and not all associated images have been made accessible for analysis. The shortage of original samples makes it hard to train the CNN network and has relatively low accuracy. In this case, this study tries to use DCGAN to generate more images based on the original sample. By comparing the accuracy and f1 score of the CNN network, this study finds that implementing images has improved the performance of the CNN network. By implementing the images, the DCGAN generates, the accuracy for the same CNN network to identify whether the images have meningioma or not is increased from 93.53 percent to 97.75 percent. The f1 score also increased from about 0.9187 to about 0.9738.

Deep learning–based automatic segmentation of meningioma from T1-weighted contrast-enhanced MRI for preoperative meningioma differentiation using radiomic features

BackgroundThis study aimed to establish a dedicated deep-learning model (DLM) on routine magnetic resonance imaging (MRI) data to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations. Another purpose of our work was to develop a radiomics model based on the radiomics features extracted from automatic segmentation to differentiate low- and high-grade meningiomas before surgery.MaterialsA total of 326 patients with pathologically confirmed meningiomas were enrolled. Samples were randomly split with a 6:2:2 ratio to the training set, validation set, and test set. Volumetric regions of interest (VOIs) were manually drawn on each slice using the ITK-SNAP software. An automatic segmentation model based on SegResNet was developed for the meningioma segmentation. Segmentation performance was evaluated by dice coefficient and 95% Hausdorff distance. Intra class correlation (ICC) analysis was applied to assess the agreement between radiomic features from manual and automatic segmentations. Radiomics features derived from automatic segmentation were extracted by pyradiomics. After feature selection, a model for meningiomas grading was built.ResultsThe DLM detected meningiomas in all cases. For automatic segmentation, the mean dice coefficient and 95% Hausdorff distance were 0.881 (95% CI: 0.851–0.981) and 2.016 (95% CI:1.439–3.158) in the test set, respectively. Features extracted on manual and automatic segmentation are comparable: the average ICC value was 0.804 (range, 0.636–0.933). Features extracted on manual and automatic segmentation are comparable: the average ICC value was 0.804 (range, 0.636–0.933). For meningioma classification, the radiomics model based on automatic segmentation performed well in grading meningiomas, yielding a sensitivity, specificity, accuracy, and area under the curve (AUC) of 0.778 (95% CI: 0.701–0.856), 0.860 (95% CI: 0.722–0.908), 0.848 (95% CI: 0.715–0.903) and 0.842 (95% CI: 0.807–0.895) in the test set, respectively.ConclusionsThe DLM yielded favorable automated detection and segmentation of meningioma and can help deploy radiomics for preoperative meningioma differentiation in clinical practice.

A Deep Learning Approach for Brain Tumor Firmness Detection Based on Five Different YOLO Versions: YOLOv3–YOLOv7

Brain tumor diagnosis traditionally relies on the manual examination of magnetic resonance images (MRIs), a process that is prone to human error and is also time consuming. Recent advancements leverage machine learning models to categorize tumors, such as distinguishing between “malignant” and “benign” classes. This study focuses on the supervised machine learning task of classifying “firm” and “soft” meningiomas, critical for determining optimal brain tumor treatment. The research aims to enhance meningioma firmness detection using state-of-the-art deep learning architectures. The study employs a YOLO architecture adapted for meningioma classification (Firm vs. Soft). This YOLO-based model serves as a machine learning component within a proposed CAD system. To improve model generalization and combat overfitting, transfer learning and data augmentation techniques are explored. Intra-model analysis is conducted for each of the five YOLO versions, optimizing parameters such as the optimizer, batch size, and learning rate based on sensitivity and training time. YOLOv3, YOLOv4, and YOLOv7 demonstrate exceptional sensitivity, reaching 100%. Comparative analysis against state-of-the-art models highlights their superiority. YOLOv7, utilizing the SGD optimizer, a batch size of 64, and a learning rate of 0.01, achieves outstanding overall performance with metrics including mean average precision (99.96%), precision (98.50%), specificity (97.95%), balanced accuracy (98.97%), and F1-score (99.24%). This research showcases the effectiveness of YOLO architectures in meningioma firmness detection, with YOLOv7 emerging as the optimal model. The study’s findings underscore the significance of model selection and parameter optimization for achieving high sensitivity and robust overall performance in brain tumor classification.

A mask R-CNN approach for detection and classification of brain tumours from MR images

ABSTRACT This study aims to tackle the implementation of a single deep learning (DL) technique to the brain tumour recognition, segmentation and classification problem based on MR images. We propose utilising the Mask R-CNN approach along with transfer learning models on images. This was done by assigning bounding boxes and successfully constructing a border on each image for the tumour volume in order to distinguish it from neighbouring tissues and structures. By processing the images in this way, a single DL model could accurately identify, classify and segment three different categories of brain tumours (meningioma, glioma or pituitary). ResNet-50 and ResNet-101 network architectures were trained for 1000 epochs, and their classification and segmentation performances were assessed. A higher classification success was achieved for the ResNet-101 backbone pretrained on COCO images (%75 accuracy) in the testing phase. ResNet-50, on the other hand, achieved a higher classification accuracy (%87) when used with the ImageNet dataset. The classification and segmentation successes of meningioma and pituitary tumours were comparable, while glioma tumours could be segmented at relatively lower success rates (41–73% for all models), despite similar classification performances (73–95%) with other tumour types.

Impact of molecular genetic profle of meningiomas on the clinical course and recurrence using combined modality treatment

Introduction. Meningioma is one of the most common central nervous system tumors, accounting for 39.7 % of all primary brain tumors. The tumor originates from arachnoid meningothelial cells and is characterized by a wide range of histological types classified into 15 subtypes. The histological classification of meningiomas allows us to predict meningioma behavior and the risk of disease recurrence, as well as to define treatment strategies. However, clinical outcomes in histological subgroups of patients are often inconsistent with the histological grade of malignancy. Thus, a more reliable method is needed both to determine the histological subtype of the tumor and to predict the clinical course of the disease with the potential for targeted treatment.The purpose of the study was to summarize the available data on the effect of results of the genomic and proteomic tumor analysis on carcinogenesis with the relationship between the mutational changes and noninvasive diagnosis, treatment and the course of the disease.Material and Methods. Literature search was carried out in the PubMed, Elibrary system, publications were included mainly from 2010 to 2023. with the identification of articles by the keyword “genetic analysis of meningiomas” and synonyms. 550 articles were found, of which 55 were used to write a literature review.Conclusion. The study of the molecular genetic profile of meningiomas will improve the classification and establish a correlation with MRI data, the course of the disease and prognosis.

BIOM-55. TARGETED GENE EXPRESSION PROFILING PREDICTS MENINGIOMA OUTCOMES AND RADIOTHERAPY RESPONSES

Abstract INTRODUCTION Improvements in meningioma risk stratification are needed and current indications for postoperative radiotherapy are controversial. Here we report multicenter clinical and analytical validation of a gene expression biomarker using clinical and genomic data from 1856 meningiomas from 12 institutions across 3 continents. METHODS A previously-developed 34-gene expression biomarker was applied to 3 validation cohorts: (1) a multicenter retrospective clinical validation cohort (N = 6 centers, N = 866 meningiomas, median follow-up 5.2 years), (2) a prospective investigator-blinded clinical validation cohort from RTOG 0539 (N = 103 meningiomas, median follow-up 8.4 years), and (3) an analytical validation cohort for test/re-test and FFPE/frozen analyses, and comparison across platforms for gene expression quantification (N = 8 centers, N = 1219 meningiomas). Biomarker performance was compared to 9 other meningioma classification systems. Favorable versus unfavorable cases were defined as (1) gene expression low risk with any resection, or gene expression intermediate risk with GTR (favorable), versus (2) gene expression intermediate risk with STR, or gene expression high risk with any resection (unfavorable). RESULTS The biomarker improved on WHO 2021 grade (5-year local freedom from recurrence [LFFR] delta-AUC 0.11, 95% CI 0.07-0.17, p&amp;lt; 0.001) and all other classification systems for LFFR and OS on multivariate analysis, achieving a negative predictive value for recurrence at 5-years of 91.9%. The biomarker predicted LFFR after postoperative radiotherapy, with a hazard ratio of 0.33 for unfavorable primary WHO grade 2 meningiomas (95% CI 0.14-0.76, P = 0.009), and 0.54 for unfavorable propensity-matched meningiomas across all WHO grades (95% CI 0.37-0.78, p = 0.0001). The biomarker reclassified 39.8% of meningiomas from RTOG 0539, including downstaging 30.5% of patients who received postoperative radiotherapy, and was independently prognostic for overall survival on multivariate analysis. CONCLUSIONS A 34-gene expression biomarker improves prognostication of meningioma outcomes and predicts postoperative radiotherapy responses.

BIOM-54. VALIDATING MCM2 IMMUNOHISTOCHEMISTRY AS A SURROGATE MARKER FOR AGGRESSIVE MENINGIOMA

Abstract Increasing efforts have focused to improve meningioma classification through various multi-omic analyses. One such recent study (Nassiri, et al, Nature, 2021) proposed an integrative molecular classification for meningiomas that included 4 molecular subtypes (MG1-4), with possible immunohistochemical surrogates for each subtype including S100B, ACADL, SCGN, and MCM2, respectively. While these immunohistochemical surrogates have been proposed for meningioma risk-stratification, their clinical utility has not been thoroughly tested. In this study, we sought to evaluate the utility of these immunohistochemical markers for risk-stratification in an independent cohort of meningioma. Tissue microarrays containing meningioma tissues were constructed, immunohistochemically stained, and blindly scored. Our cohort included n = 142 tumors (CNS WHO: 1=93, 2=45, 3=4). Median age was 49 years (range 14-80 years) with 89 female and 53 male patients. We found that MCM2 immunopositivity was a univariate marker of poor prognosis (median progression-free survival 1.2 years) when compared to negative tumors (median progression-free survival 13.0 years). The other three markers (S100B, ACADL, SCGN) were not associated with survival. MCM2 staining held up as a significantly independent (p = 0.03) poor prognostic marker on multivariate Cox proportional hazard modeling including other histopathological features: CNS WHO grade, brain invasion, mitotic index, and tumor size. Although MCM2 staining was independent of CNS WHO grade, all 4 of the CNS WHO 3 meningiomas were positive for MCM2. MCM2-positive tumors had a higher average mitotic count (6.1 mitoses/10hpf) compared to MCM2-negative tumors (1.8 mitoses/10hpf) (p = 0.0002, two-tailed t test). There was no difference between MCM2-positive and MCM2-negative meningiomas in relation to maximum tumor size (4.9cm and 4.2cm, respectively) and mean age (51.71 years and 50.34 years, respectively). In summary, in our cohort we found MCM2 immunopositive staining (surrogate marker for high-risk molecular subtype M4) to be an independently poor prognostic biomarker in meningioma when accounting for other well-established histopathological characteristics.

Leveraging Attention-Based Convolutional Neural Networks for Meningioma Classification in Computational Histopathology.

Convolutional neural networks (CNNs) are becoming increasingly valuable tools for advanced computational histopathology, promoting precision medicine through exceptional visual decoding abilities. Meningiomas, the most prevalent primary intracranial tumors, necessitate accurate grading and classification for informed clinical decision-making. Recently, DNA methylation-based molecular classification of meningiomas has proven to be more effective in predicting tumor recurrence than traditional histopathological methods. However, DNA methylation profiling is expensive, labor-intensive, and not widely accessible. Consequently, a digital histology-based prediction of DNA methylation classes would be advantageous, complementing molecular classification. In this study, we developed and rigorously assessed an attention-based multiple-instance deep neural network for predicting meningioma methylation classes using tumor methylome data from 142 (+51) patients and corresponding hematoxylin-eosin-stained histological sections. Pairwise analysis of sample cohorts from three meningioma methylation classes demonstrated high accuracy in two combinations. The performance of our approach was validated using an independent set of 51 meningioma patient samples. Importantly, attention map visualization revealed that the algorithm primarily focuses on tumor regions deemed significant by neuropathologists, offering insights into the decision-making process of the CNN. Our findings highlight the capacity of CNNs to effectively harness phenotypic information from histological sections through computerized images for precision medicine. Notably, this study is the first demonstration of predicting clinically relevant DNA methylome information using computer vision applied to standard histopathology. The introduced AI framework holds great potential in supporting, augmenting, and expediting meningioma classification in the future.

A large-scale targeted proteomics of serum and tissue shows the utility of classifying high grade and low grade meningioma tumors

BackgroundMeningiomas are the most prevalent primary brain tumors. Due to their increasing burden on healthcare, meningiomas have become a pivot of translational research globally. Despite many studies in the field of discovery proteomics, the identification of grade-specific markers for meningioma is still a paradox and requires thorough investigation. The potential of the reported markers in different studies needs further verification in large and independent sample cohorts to identify the best set of markers with a better clinical perspective.MethodsA total of 53 fresh frozen tumor tissue and 51 serum samples were acquired from meningioma patients respectively along with healthy controls, to validate the prospect of reported differentially expressed proteins and claimed markers of Meningioma mined from numerous manuscripts and knowledgebases. A small subset of Glioma/Glioblastoma samples were also included to investigate inter-tumor segregation. Furthermore, a simple Machine Learning (ML) based analysis was performed to evaluate the classification accuracy of the list of proteins.ResultsA list of 15 proteins from tissue and 12 proteins from serum were found to be the best segregator using a feature selection-based machine learning strategy with an accuracy of around 80% in predicting low grade (WHO grade I) and high grade (WHO grade II and WHO grade III) meningiomas. In addition, the discriminant analysis could also unveil the complexity of meningioma grading from a segregation pattern, which leads to the understanding of transition phases between the grades.ConclusionsThe identified list of validated markers could play an instrumental role in the classification of meningioma as well as provide novel clinical perspectives in regard to prognosis and therapeutic targets.

Correlation of progesterone receptors and P63 to the histological grade of meningiomas: Review and significance in an African population.

Meningiomas, a common neoplasm of the central nervous system, is a widely studied meningeal tumor. According to the World Health Organization (WHO) 2021 classification of meningiomas, there are 15 subtypes that have been grouped into grades 1, 2, and 3. The WHO grade 1 meningiomas are generally grouped as benign while the WHO grades 2 and 3 tumors are grouped as malignant. Progesterone receptors and P63 are common immunohistochemical markers that have proven useful in the diagnosis, grading, and prognostication of many neoplasms such as breast carcinoma, prostate carcinoma, and gastrointestinal tumors in histopathology practice. The application of these immunohistochemical markers to the grading of meningiomas has been reported and their usefulness documented in reports from Africa, Europe, North America, South America, and Asia. This study, therefore, seeks to determine if these findings are applicable to the meningiomas seen in an African population. A 10-year review of results and histologically diagnosed cases of meningiomas received in the Department of Morbid Anatomy, University of Nigeria, Enugu. Immunostaining for progesterone receptors (PgRs) and P63 were done and results compared with histologic grades. The three WHO grades of meningioma were assessed in this study. M: F ratio was 1:1.4 and peak age was 41-50 years age range (SD ± 16.54). The majority of the cases were WHO grade 1 (86.1%) while the WHO grades 2 and 3 tumors were 8% and 5.9%, respectively. The fibrous variant was the most common subtype (27.1%). There was no correlation between progesterone receptor and P63 immunopositivity to the WHO grades of meningioma (P = 0.112 and P = 0.138, respectively). Our study showed that progesterone receptors and P63 immunopositivity did not correlate with the WHO grades of meningiomas. This may be due to the predominant variant of meningioma seen in this study. These findings indicate that PgR antagonist may not be an effective alternative for treatment in patients with inoperable meningiomas. Furthermore, P63 immunopositivity may not be a sufficient grading tool for managing meningiomas in our population.

Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis

Meningiomas are common intracranial tumors. Machine learning (ML) algorithms are emerging to improve accuracy in four primary domains: classification, grading, outcome prediction, and segmentation. Such algorithms include both, traditional approaches that rely on hand-crafted features and deep learning techniques that utilize automatic feature extraction. To evaluate the performance of published traditional ML vs. deep learning algorithms in classification, grading, outcome prediction, and segmentation of meningiomas. A systematic review and meta-analysis were conducted. Major databases were searched through September 2021 for publications evaluating traditional ML vs. deep learning models on meningioma management. Performance measures including pooled sensitivity, specificity, F1-score, area under the receiver-operating characteristic curve (AUC), positive and negative likelihood ratios (LR+, LR-) along with their respective 95% confidence intervals (95%CIs) were derived using random-effects models. 534 records were screened, and 43 articles were included, regarding classification (3 articles), grading (29), outcome prediction (7), and segmentation (6) of meningiomas. Of the 29 studies that reported on grading, 10 could be meta-analyzed with two deep learning models (sensitivity 0.89, 95%CI 0.74-0.96; specificity 0.91, 95%CI 0.45-0.99; LR+ 10.1, 95%CI 1.33-137; LR- 0.12, 95%CI 0.04-0.59) and eight traditional ML (sensitivity 0.74, 95%CI 0.62-0.83; specificity 0.93, 95%CI 0.79-0.98; LR+ 10.5, 95%CI 2.91-39.5; and LR- 0.28, 95%CI 0.17-0.49). The insufficient performance metrics reported precluded further statistical analysis of other performance metrics. Machine learning on meningiomas is mostly carried out with traditional methods. For meningioma grading, traditional machine learning methods generally had a higher LR+, while deep learning models a lower LR-.

Surgical outcomes of premeatal and retromeatal cerebellopontine angle meningioma in Vietnam: a single-center prospective cross-sectional study.

A prospective study on 33 patients treated with microsurgery from August 2020 to May 2022 at the Neurosurgery Center, Viet Duc University Hospital. The mean age of 27 females (85%) and 6 (15%) males was 54±12 years. Based on their location to the IAC, there were 16 premeatal cases (49%) (anterior to the IAC) and 17 retromeatal cases (15%) (posterior to the IAC). The time of diagnosis of the retromeatal group was later (16.5 vs. 9.7 months), the average tumor size of the 2 groups was not different, but when there was brainstem compression, the average tumor size of retromeatal group was larger (49 vs. 44mm). The clinical presentations of the retromeatal group were related to the cerebellar symptoms, while trigeminal neuropathy symptoms all came from the premeatal group. Gross total resection of the premeatal group was 31% and of the retrometal group was 71%. The results of preserving the facial nerve function of the premeatal group were lower (44 vs. 82%). Postoperative Karnofsky score of the retromeatal group improved, while the premeatal group did not change. Classification of CPA meningiomas according to their location to the IAC plays an important role in diagnosis and treatment, affecting clinical symptoms, surgical strategy as well as surgical outcomes.

Detection and classification of glioma, meningioma, pituitary tumor, and normal in brain magnetic resonance imaging using deep learning-based hybrid model

Detection and classification of glioma, meningioma, pituitary tumor, and normal in brain magnetic resonance imaging using deep learning-based hybrid model

Advances and trends in meningioma research over the last decade: A scientometric and visual analysis.

We conducted a scientometric and visual analysis of meningioma studies in the past ten years and discussed the current status and trends of meningioma research to provide a reference basis for conducting relevant clinical practice or research. A search of the topic of meningioma in the Web of Science Core Collection database was conducted for January 2012-December 2021. The scientometric tools CiteSpace (version 5.8.R3), VOS viewer (version 1.6.17), and the Bibliometrix package of R software (version 4.2.1) were used to visualize and analyze the country of publication, institution, author, keywords, and cited literature of meningioma. A total of 10,397 documents related to meningioma were collected, of which 6,714 articles were analyzed. The annual analysis shows an increase in published articles, with an annual growth rate of 8.9%. 26,696 authors from 111 countries or regions were involved in publishing relevant studies. The country with the highest number of publications was the United States (1671), and the institution with the highest number of publications was the University of California, San Francisco (242). The keyword clustering of current studies can be grouped into five groups: meningioma characteristics and basic research, surgical treatment, radiation therapy, stereotactic radiosurgery, and management of complications. Keyword trend analysis shows that meningioma classification and molecular characteristics are emerging hotspots for meningioma research in recent years. The scientometric and visual analysis demonstrated the research status and trends of meningioma. Over the past decade, meningioma research has focused on managing meningiomas with a predominance of surgical treatment and radiation therapy. At the same time, meningioma classification and molecular characteristics are emerging as current and possible research hotspots in the coming period.

Detection of meningioma tumor images using Modified Empirical Mode Decomposition (MEMD) and convolutional neural networks

The meningioma brain tumor detection is more important than the other tumor detection such as Glioma and Glioblastoma, due to its high severity level. The tumor pixel density of meningioma tumor is high and it leads to sudden death if it is not detected timely. The meningioma images are detected using Modified Empirical Mode Decomposition- Convolutional Neural Networks (MEMD-CNN) classification approach. This method has the following stages data augmentation, spatial-frequency transformation, feature computations, classifications and segmentation. The brain image samples are increased using data augmentation process for improving the meningioma detection rate. The data augmented images are spatially transformed into frequency format using MEMD transformation method. Then, the external empirical mode features are computed from this transformed image and they are fed into CNN architecture to classify the source brain image into either meningioma or non-meningioma. The pixels belonging tumor category are segmented using morphological opening-closing functions. The meningioma detection system obtains 99.4% of Meningioma Classification Rate (MCR) and 99.3% of Non-Meningioma Classification Rate (NMCR) on the meningioma and non-meningioma images. This MEMD-CNN technique for meningioma identification attains 98.93% of SET, 99.13% of SPT, 99.18% of MSA, 99.14% of PR and 99.13% of FS. From the statistical comparative analysis of the proposed MEMD-CNN system with other conventional detection systems, the proposed method provides optimum tumor segmentation results.

Mutational signature of extracranial meningioma metastases and their respective primary tumors

Extracranial metastases of intracranial meningiomas are rare. Little is known about the mutational pattern of these tumors and their metastatic seeding. Here, we retrospectively explored the molecular alterations of these metastatic lesions and their respective intracranial tumor manifestations.Histology and genome sequencing were performed in intracranial meningiomas and their extracranial metastatic lesions operated upon between 2002 and 2021. Next-generation DNA/RNA sequencing (NGS) and methylome analysis were performed to determine molecular alterations.We analyzed the tumors of five patients with clinically suspected metastases of a meningioma using methylome analysis and next generation panel sequencing of the primary tumors as well as the metastatic lesions. Metastases were found in the spinal cord and one in the lung. In four of these patients, molecular analyses confirmed metastatic disease, while the fifth patient was found to harbor two molecularly distinct meningiomas. On pathological assessment, the primary lesions ranged from CNS WHO grades 1 to 3 (integrated molecular-morphologic meningioma classification scores 2 to 6). Of the four true metastatic cases, three out of the four metastasizing tumors harbored alterations in the BAP1 gene, comprising a stop-mutation combined with copy-number loss (WHO grade 1), copy number loss (WHO grade 3) and a frameshift mutation (WHO grade 2). Furthermore, the latter was confirmed to harbor a BAP1 tumor predisposition syndrome. The fourth metastasizing tumor had copy-number losses in NF2 and PTEN. Only one of four showed CDKN2A homozygous deletion; none showed TERT promotor mutation.Our results molecularly confirm true metastatic disease in four meningioma patients. BAP1 gene alterations were the most frequent. Larger cohorts, most likely from multicenter studies are necessary to evaluate the role of BAP-1 alterations to further understand the metastatic spread in meningiomas. for metastatic spread and might indicate patients at risk for metastatic spread. Further explorations within larger cohorts are necessary to validate these findings which might influence the clinical management in the future.

Molecular classification and grading of meningioma.

Meningiomas are the most common primary intracranial tumor in older adults (Ostrom et al. in Neuro Oncol 21(Suppl 5):v1-v100, 2019). Treatment is largely driven by, in addition to patient characteristics and extent of resection/Simpson grade, the World Health Organization (WHO) grading of meningiomas. The current grading scheme, based predominantly on histologic features and only limited molecular characterization of these tumors (WHO Classification of Tumours Editorial Board, in: Central nervous system tumours, International Agency for Research on Cancer, Lyon, 2021), (Mirian et al. in J Neurol Neurosurg Psychiatry 91(4):379-387, 2020), does not consistently reflect the biologic behavior of meningiomas. This leads to both under-treatment and over-treatment of patients, and hence, suboptimal outcomes (Rogers et al. in Neuro Oncol 18(4):565-574). The goal of this review is to synthesize studies to date investigating molecular features of meningiomas as they relate to patient outcomes, in order to clarify best practices in assessing and, therefore, treating meningiomas. The available literature of genomic landscape and molecular features of in meningioma was screened using PubMed. Greater understanding of meningiomas is reached by integrating histopathology, mutational analysis, DNA copy number changes, DNA methylation profiles, and potentially additional modalities to fully capture the clinical and biologic heterogeneity of these tumors. Diagnosis and classification of meningioma is best accomplished using a combination of histopathology with genomic and epigenomic factors. Future classification schemes may benefit from such an integrated approach.