Meningioma and psychiatric symptoms: An individual patient data analysis

Meningioma: International Consortium on Meningiomas consensus review on scientific advances and treatment paradigms for clinicians, researchers, and patients

Meningiomas are the most common primary intracranial tumors in adults and are increasing in incidence due to the aging population and increased access to neuroimaging. While most exhibit nonmalignant behavior, a subset of meningiomas are biologically aggressive and are associated with treatment resistance, resulting in significant neurologic morbidity and even mortality. In recent years, meaningful advances in our understanding of the biology of these tumors have led to the incorporation of molecular biomarkers into their grading and prognostication. However, unlike other central nervous system (CNS) tumors, a unified molecular taxonomy for meningiomas has not yet been established and remains an overarching goal of the Consortium to Inform Molecular and Practical Approaches to CNS Tumor Taxonomy-Not Official World Health Organization (cIMPACT-NOW) working group. Additionally, clinical equipoise still remains on how specific meningioma cases and patient populations should be optimally managed. To address these existing gaps, members of the International Consortium on Meningiomas including field-leading experts, have prepared this comprehensive consensus narrative review directed toward clinicians, researchers, and patients. Included in this manuscript are detailed overviews of proposed molecular classifications, novel biomarkers, contemporary treatment strategies, trials on systemic therapies, health-related quality-of-life studies, and management strategies for unique meningioma patient populations. In each section, we discuss the current state of knowledge as well as ongoing clinical and research challenges to road map future directions for further investigation.

Exploring machine learning applications in Meningioma Research (2004-2023)

Objective

This study aims to examine the trends in machine learning application to meningiomas between 2004 and 2023.

Methods

Publication data were extracted from the Science Citation Index Expanded (SCI-E) within the Web of Science Core Collection (WOSCC). Using CiteSpace 6.2.R6, a comprehensive analysis of publications, authors, cited authors, countries, institutions, cited journals, references, and keywords was conducted on December 1, 2023.

Results

The analysis included a total of 342 articles. Prior to 2007, no publications existed in this field, and the number remained modest until 2017. A significant increase occurred in publications from 2018 onwards. The majority of the top 10 authors hailed from Germany and China, with the USA also exerting substantial international influence, particularly in academic institutions. Journals from the IEEE series contributed significantly to the publications. "Deep learning," "brain tumor," and "classification" emerged as the primary keywords of focus among researchers. The developmental pattern in this field primarily involved a combination of interdisciplinary integration and the refinement of major disciplinary branches.

Conclusion

Machine learning has demonstrated significant value in predicting early meningiomas and tailoring treatment plans. Key research focuses involve optimizing detection indicators and selecting superior machine learning algorithms. Future efforts should aim to develop high-performance algorithms to drive further innovation in this field.

Clinical Presentation and Prognosis

Over the past three decades, the care for patients with meningioma has steadily improved as a result of a better understanding of the natural history, molecular biology, and classification of these tumors. Surgical frameworks for management have been established and validated with more options for adjuvant and salvage treatment available for patients with residual or recurrent disease. Overall these advances have improved clinical outcomes and prognosis.Alongside the improved clinical management has come an increase in biological understanding of these tumors. The number of publications within the field of meningioma research continues to expand and biological studies identifying molecular factors at the cytogenic and genomic level offer exciting potential for more personalized management strategies. As survival and understanding have increased, treatment outcomes are moving from traditional metrics, which describe the morbidity and mortality to more patient-centered measures. The subjective experiences of patients with meningioma are gaining interest among clinical researchers and it is recognized that even supposedly mild symptoms arising from meningioma can have a significant effect on a patient's quality of life.This chapter reviews the varied clinical presentations of meningioma, which in the modern era of widespread brain imaging must include a discussion of incidental meningioma. The second part examines prognosis and the clinical, pathological, and molecular factors that can be used to predict outcomes.

Brain Tumor Classification Using a Combination of Variational Autoencoders and Generative Adversarial Networks

Brain tumors are a pernicious cancer with one of the lowest five-year survival rates. Neurologists often use magnetic resonance imaging (MRI) to diagnose the type of brain tumor. Automated computer-assisted tools can help them speed up the diagnosis process and reduce the burden on the health care systems. Recent advances in deep learning for medical imaging have shown remarkable results, especially in the automatic and instant diagnosis of various cancers. However, we need a large amount of data (images) to train the deep learning models in order to obtain good results. Large public datasets are rare in medicine. This paper proposes a framework based on unsupervised deep generative neural networks to solve this limitation. We combine two generative models in the proposed framework: variational autoencoders (VAEs) and generative adversarial networks (GANs). We swap the encoder-decoder network after initially training it on the training set of available MR images. The output of this swapped network is a noise vector that has information of the image manifold, and the cascaded generative adversarial network samples the input from this informative noise vector instead of random Gaussian noise. The proposed method helps the GAN to avoid mode collapse and generate realistic-looking brain tumor magnetic resonance images. These artificially generated images could solve the limitation of small medical datasets up to a reasonable extent and help the deep learning models perform acceptably. We used the ResNet50 as a classifier, and the artificially generated brain tumor images are used to augment the real and available images during the classifier training. We compared the classification results with several existing studies and state-of-the-art machine learning models. Our proposed methodology noticeably achieved better results. By using brain tumor images generated artificially by our proposed method, the classification average accuracy improved from 72.63% to 96.25%. For the most severe class of brain tumor, glioma, we achieved 0.769, 0.837, 0.833, and 0.80 values for recall, specificity, precision, and F1-score, respectively. The proposed generative model framework could be used to generate medical images in any domain, including PET (positron emission tomography) and MRI scans of various parts of the body, and the results show that it could be a useful clinical tool for medical experts.

Brain tumors and indications for brain imaging in patients with psychiatric manifestations: a case report

Background

Studies on the relationship between psychiatric symptoms and brain tumors are ambiguous, as it is not clear whether these symptoms are due to the direct effect of the tumor or a secondary psychological response to stress, resulting from the diagnosis and treatment of the disease; therefore, it is difficult to analyze and retrieve relevant information.

Case presentation

We present the case of a 43-year-old male patient, who was admitted to a psychiatric emergency room with psychiatric symptoms, such as restlessness and extreme talkativeness, but normal neurological examinations. He showed no response to outpatient treatment and had no history of psychiatric disorders. The onset of symptoms was 2 months before his visit. On neuroimaging, a brain tumor was observed in the right temporal and occipital lobes. Accordingly, the patient was transferred to the neurosurgery ward.

Conclusion

Factors, such as increased internal pressure on the brain due to a brain tumor or the effect of tumor area, contribute to the occurrence of symptoms, such as restlessness and talkativeness. However, further studies are needed to confirm these findings.

Neuroimaging Recommendations in Outpatients With Dementia: Three Cases of Frontal Meningioma Demonstrating Reversible Dementia

Benign brain tumors largely affect the brain and can lead to reversible dementia, which can be resolved following the treatment of the primary etiology. Herein, we report three cases of relatively large frontal meningiomas in patients who presented with cognitive impairment as initial symptoms. The three participants demonstrated notable dementia alongside frontal meningioma. Following resection, all patients showed dramatic cognitive function improvement, and they successfully returned to society. Our cases illustrate the benefit of active surveillance with neuroimaging in selected patients, especially those who present with acute or subacute dementia.