Can Systemic Inflammatory Markers Be Used to Predict the Pathological Grade of Meningioma Before Surgery?

Multi-parametric MRI-based machine learning model for prediction of WHO grading in patients with meningiomas

OBJECTIVE

The purpose of this study was to develop and validate a nomogram combined multiparametric MRI and clinical indicators for identifying the WHO grade of meningioma.

MATERIALS AND METHODS

Five hundred and sixty-eight patients were included in this study, who were diagnosed pathologically as having meningiomas. Firstly, radiomics features were extracted from CE-T1, T2, and 1-cm-thick tumor-to-brain interface (BTI) images. Then, difference analysis and the least absolute shrinkage and selection operator were orderly used to select the most representative features. Next, the support vector machine algorithm was conducted to predict the WHO grade of meningioma. Furthermore, a nomogram incorporated radiomics features and valuable clinical indicators was constructed by logistic regression. The performance of the nomogram was assessed by calibration and clinical effectiveness, as well as internal validation.

RESULTS

Peritumoral edema volume and gender are independent risk factors for predicting meningioma grade. The multiparametric MRI features incorporating CE-T1, T2, and BTI features showed the higher performance for prediction of meningioma grade with a pooled AUC = 0.885 (95% CI, 0.821-0.946) and 0.860 (95% CI, 0.788-0.923) in the training and test groups, respectively. Then, a nomogram with a pooled AUC = 0.912 (95% CI, 0.876-0.961), combined radiomics score, peritumoral edema volume, and gender improved diagnostic performance compared to radiomics model or clinical model and showed good calibration as the true results. Moreover, decision curve analysis demonstrated satisfactory clinical effectiveness of the proposed nomogram.

CONCLUSIONS

A novel nomogram is simple yet effective in differentiating WHO grades of meningioma and thus can be used in patients with meningiomas.

CLINICAL RELEVANCE STATEMENT

We proposed a nomogram that included clinical indicators and multi-parameter radiomics features, which can accurately, objectively, and non-invasively differentiate WHO grading of meningioma and thus can be used in clinical work.

KEY POINTS

• The study combined radiomics features and clinical indicators for objectively predicting the meningioma grade. • The model with CE-T1 + T2 + brain-to-tumor interface features demonstrated the best predictive performance by investigating seven different radiomics models. • The nomogram potentially has clinical applications in distinguishing high-grade and low-grade meningiomas.

The role of preoperative hematological inflammatory markers as a predictor of meningioma grade: A systematic review and meta-analysis

Background

Inflammatory processes play an important role in the aggressiveness of a tumor. However, the relationship between inflammatory markers in meningioma grade is not well known. Knowledge of preoperative meningioma grade plays an important role in the prognosis and treatment of this tumor. This study aims to assess preoperative hematological inflammatory markers as a predictor of the pathological grade of meningioma.

Methods

To ensure comprehensive retrieval of relevant studies, we searched the following key databases, PubMed, Science Direct, and Biomed Central, with evidence related to preoperative hematological inflammatory markers among meningioma up to September 2023. The studies involved were selected based on established eligibility criteria. The analysis in this study uses Review Manager 5.4.

Results

Six studies were obtained from the search results. The total number of patients 2789 (469 high-grade meningioma and 2320 low-grade meningioma) analysis shows elevated neutrophil-to-lymphocyte ratio (NLR) (mean difference [MD]: 0.29; 95% confidence interval [CI] 0.13-0.45; P = 0.0004), monocyte-to-lymphocyte ratio (MLR) (MD: 0.02; 95% CI 0.00-0.04; P = 0.003), and low lymphocyte-to-monocyte ratio (LMR) (MD: -0.82; 95% CI -1.46--0.18; P = 0.005) significantly associated with high-grade meningioma compared to low-grade meningioma. No significant correlation between high-grade and low-grade meningioma based on platelet-lymphocyte ratio value is observed.

Conclusion

The parameters of NLR, MLR, and LMR have been found to be cost-effective preoperative methods that demonstrate potential value in the prediction of meningioma grade. To enhance the reliability of the findings, it is imperative to do further prospective study.

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

BACKGROUND

Meningiomas are common intracranial tumors. Machine learning (ML) algorithms are emerging to improve accuracy in 4 primary domains: classification, grading, outcome prediction, and segmentation. Such algorithms include both traditional approaches that rely on hand-crafted features and deep learning (DL) techniques that utilize automatic feature extraction. The aim of this study was to evaluate the performance of published traditional ML versus DL algorithms in classification, grading, outcome prediction, and segmentation of meningiomas.

METHODS

A systematic review and meta-analysis were conducted. Major databases were searched through September 2021 for publications evaluating traditional ML versus DL models on meningioma management. Performance measures including pooled sensitivity, specificity, F1-score, area under the receiver-operating characteristic curve, positive and negative likelihood ratios (LR+, LR-) along with their respective 95% confidence intervals (95% CIs) were derived using random-effects models.

RESULTS

Five hundred thirty-four 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 2 DL 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 8 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.

CONCLUSIONS

ML on meningiomas is mostly carried out with traditional methods. For meningioma grading, traditional ML methods generally had a higher LR+, while DL models a lower LR-.

Association between preoperative hematologic markers and aggressive behavior in meningiomas

INTRODUCTION

Meningiomas have varying degrees of aggressive behavior. Some systemic hematologic makers are associated with malignancy, but their value in predicting aggressive meningioma behavior is not fully understood.

OBJECTIVE

To evaluate the association between preoperative markers such as neutrophil-lymphocyte ratio (NLR), neutrophil-monocyte ratio (NMR), monocyte-lymphocyte ratio (MLR), platelet-lymphocyte ratio (PLR), and prognostic nutritional index (PNI), and diagnostic and prognostic factors including WHO grade, proliferation index, presence of edema on preoperative MRI, and tumor recurrence.

METHODS

A retrospective review of patients treated between 2000 and 2019 with a preoperative complete blood count (CBC) differential lab draw before intracranial meningioma resection was conducted. All preoperative steroid dosages were converted to dexamethasone equivalents. Primary outcomes included presence/absence of perilesional edema, WHO grade, Ki-67/MIB-index, and recurrence. Univariate and multivariable regression analyses were conducted.

RESULTS

A total of 209 meningioma patients were included. Of these, 143 (68 %) were WHO grade I, 61 (29 %) grade II and 5 (2 %) were grade III. Recurrence was reported in 19 (9.1 %) tumors. No hematologic markers were associated with recurrence. In separate multivariable logistic analyses, no biomarkers were associated with perilesional edema or WHO grade. MLR was associated with higher MIB-index (p = 0.018, OR 6.57, 95 % CI 1.37-30.91).

CONCLUSION

Most hematologic markers were not associated with meningioma invasiveness, grade, proliferative index, or aggressiveness. Preoperative MLR was associated with high proliferation index in patients undergoing surgery for intracranial meningioma. Higher MLR could be a surrogate for meningioma proliferation and has potential to be used as an adjunct for risk-stratifying meningiomas.

Preoperative hematological inflammatory markers associated with grade and survival in Meningiomas

Meningiomas represent the most frequently diagnosed intracranial tumors. Inflammatory cells present in the tumor can modulate both antitumor and protumor functions, and modify the therapeutic response. Hematological inflammatory parameters have provided prognostic information useful in the treatment and clinical evaluation of several tumors. The aim of this study was to evaluate preoperative hematological markers of patients with meningiomas and to relate them to clinical variables and recurrence-regrowth free survival. Eighty-nine patients without corticosteroid therapy were included. Blood test results and tumor characteristics were collected from medical records. Associations between clinical characteristics and the recurrence-regrowth free survival (RFS) were evaluated using Cox proportional hazard analysis and Kaplan-Meier curves. The receiver operating characteristic (ROC) curves were constructed. Of the 89 cases, 73 (82%) were grade I and 16 (18%) grade II. The mean age was 53 ± 13.9 years, with higher frequency in women. Anemia was observed in 23.6% and neutrophilia in 42% of the patients. In univariate analysis, anemia (p = 0.04), neutrophilia (p = 0.02) and neutrophil/lymphocyt ratio (NLR) (p = 0.02) were associated with an increased risk of recurrence-regrowth and shorter RFS. In multivariate analysis, anemia and NLR > 4.1 represented a higher risk of recurrence-regrowth (p = 0.003). The ROC curve analysis showed that only the lymphocyte/monocyte (L/M) > 2.5 was able to predict the tumor grade. The preoperative presence of anemia, neutrophilia, NLR > 4.1 and L/M > 2.5 were associated with a worse prognosis in meningiomas. The use of preoperative hematological inflammatory parameters as prognostic factors can be promissing for evaluation and follow-up of meningiomas.

Serum Inflammation-based Scores in Endocrine Tumors

CONTEXT

Serum inflammation-based scores reflect systemic inflammatory response and/or patients' nutritional status, and may predict clinical outcomes in cancer. While these are well-described and increasingly used in different cancers, their clinical usefulness in the management of patients with endocrine tumors is less known.

EVIDENCE ACQUISITION

A comprehensive PubMed search was performed using the terms "endocrine tumor," "inflammation," "serum inflammation-based score," "inflammatory-based score," "inflammatory response-related scoring," "systemic inflammatory response markers," "neutrophil-to-lymphocyte ratio," "neutrophil-to-platelet ratio," "lymphocyte-to-monocyte ratio," "Glasgow prognostic score," "neutrophil-platelet score," "Systemic Immune-Inflammation Index," and "Prognostic Nutrition Index" in clinical studies.

EVIDENCE SYNTHESIS

The neutrophil-to-lymphocyte ratio and the platelet-to-lymphocyte ratio are the ones most extensively investigated in patients with endocrine tumors. Other scores have also been considered in some studies. Several studies focused in finding whether serum inflammatory biomarkers may stratify the endocrine tumor patients' risk and detect those at risk for developing more aggressive and/or refractory disease, particularly after endocrine surgery.

CONCLUSIONS

In this review, we summarize the current knowledge on the different serum inflammation-based scores and their usefulness in predicting the phenotype, clinical aggressiveness, and disease outcomes and prognosis in patients with endocrine tumors. The value of such serum inflammation-based scores in the management of patients with endocrine tumors has been emerging over the last decade. However, further research is necessary to establish useful markers and their cut-offs for routine clinical practice for individual diseases.

Tumor volume and the dural tail sign enable the differentiation of intracranial solitary fibrous tumor/hemangiopericytoma from high-grade meningioma

OBJECTIVES

Intracranial solitary fibrous tumor/hemangiopericytoma (SFT/HPC) is a rare mesenchymal neoplasm with imaging features mimicking high-grade meningioma (HGM) and can easily be misdiagnosed. We sought to determine the value of routine preoperative data in differentiating these tumors.

PATIENTS AND METHODS

Patients with confirmed SFT/HPC or HGM between January 2012 and June 2020 were identified. A total of 28 preoperative variables (including age, sex, tumor location, tumor volume, 10 traditional MRI features, and 14 peripheral blood indices) were collected for each patient. The top features were selected sequentially based on the least absolute shrinkage and selection operator (LASSO) and support vector machines-recursive feature elimination (SVM-RFE) methods. Differentiation and calibration of the classifiers were assessed by receiver operating characteristic (ROC) curves and calibration curves, respectively. Nomograms were constructed based on multivariate analysis.

RESULTS

A total of 127 patients, including 29 with SFT/HPC and 98 with HGM, were analyzed. Three features were first selected using the LASSO and SVM-RFE methods, and corresponding models were developed. Although the area under the curve (AUC) of model 1 was the highest, a comprehensive analysis suggested the superiority of model 2, which consisted only of the features tumor volume (TV) and dural tail sign (DTS) (AUC: 0.942, sensitivity: 93.10%, p-value of H-L test: 0.734, Brier score: 0.07). A risk score formula and a nomogram were constructed.

CONCLUSIONS

TV can be used to effectively identify SFT/HPC and HGM, whereas adding DTS can improve the overall prediction accuracy. As these two variables are routinely available and are easy for clinicians to master, they can provide a powerful reference for clinical decision-making.

Pre-operative serum inflammation-based scores in patients with pituitary adenomas

OBJECTIVE

Full blood count (FBC) and serum inflammation-based scores reflect systemic inflammation and predict outcomes in cancer, but little is known in pituitary adenomas (PAs). We aimed to characterise FBC and inflammation-based scores in PA patients and investigate their usefulness in predicting challenging disease course.

METHODS

We studied 424 PA patients first operated at our centre with available pre-operative biochemical data. Patients with infection, malignancies, autoimmune or haematological conditions were excluded. Inflammation-based scores studied: Neutrophil-to-Lymphocyte Ratio (NLR), Platelet-to-Lymphocyte Ratio (PLR), Lymphocyte-to-Monocyte Ratio (LMR), Systemic Immune-Inflammation Index (SII), Neutrophil-Platelet Score (NPS), Prognostic Nutrition Index (PNI), and Glasgow Prognostic Score (GPS).

RESULTS

Cushing's disease patients had more platelets, leucocytes, neutrophils and monocytes, and higher NLR, NPS and SII. Serum inflammation-based scores didn't differ among non-Cushing PA subtypes. The glucocorticoid excess severity influenced leucocyte, eosinophil, basophil and platelet counts, and GPS in Cushing's disease. Patients with functioning non-Cushing PAs with suprasellar extension, cavernous sinus invasion and hypopituitarism had GPS ≥ 1, while NPS ≥ 1 was associated with suprasellar extension. More invasive and difficult to treat corticotrophinomas were associated with fewer platelets pre-operatively (< 299.5 × 10⁹/L predicting multimodal treatment). Non-functioning PA patients who suffered apoplexy had more leucocytes, neutrophils and monocytes, higher GPS ≥ 1 and fewer platelets; re-operated cases had fewer lymphocytes, higher NLR and PLR.

CONCLUSIONS

Serum inflammation-based scores may predict invasive/refractory PAs: GPS and PNI in non-functioning and functioning non-Cushing PAs; NPS in functioning non-Cushing PAs; NLR and PLR in non-functioning PAs. Platelets < 299.5 × 10⁹/L predict multimodal treatment in Cushing's disease. Further studies are needed to confirm these observations.

Prognostic Significance of Preoperative Neutrophil-to-Lymphocyte Ratio in Patients With Meningiomas

Background

Meningiomas are the most common benign intracranial tumors. However, even WHO grade I meningiomas occasionally show local tumor recurrence. Prognostic factors for meningiomas have not been fully established. Neutrophil-to-lymphocyte ratio (NLR) has been reported as a prognostic factor for several solid tumors. The prognostic value of NLR in meningiomas has been analyzed in few studies.

Materials and Methods

This retrospective study included 160 patients who underwent surgery for meningiomas between October 2010 and September 2017. We analyzed the associations between patients’ clinical data (sex, age, primary/recurrent, WHO grade, extent of removal, tumor location, peritumoral brain edema, and preoperative laboratory data) and clinical outcomes, including recurrence and progression-free survival (PFS).

Results

Forty-four meningiomas recurred within the follow-up period of 3.8 years. WHO grade II, III, subtotal removal, history of recurrence, Ki-67 labeling index ≥3.0, and preoperative NLR value ≥2.6 were significantly associated with shorter PFS (P < 0.001, < 0.001, 0.002, < 0.001, and 0.015, respectively). Furthermore, NLR ≥ 2.6 was also significantly associated with shorter PFS in a subgroup analysis of WHO grade I meningiomas (P = 0.003). In univariate and multivariate analyses, NLR ≥2.6 remained as a significant predictive factor for shorter PFS in patients with meningioma (P = 0.014).

Conclusions

NLR may be a cost-effective and novel preoperatively usable biomarker in patients with meningiomas.