Classification Of Gliomas Research Articles

Multimodal MRI Image Decision Fusion-Based Network for Glioma Classification.

PurposeGlioma is the most common primary brain tumor, with varying degrees of aggressiveness and prognosis. Accurate glioma classification is very important for treatment planning and prognosis prediction. The main purpose of this study is to design a novel effective algorithm for further improving the performance of glioma subtype classification using multimodal MRI images.MethodMRI images of four modalities for 221 glioma patients were collected from Computational Precision Medicine: Radiology-Pathology 2020 challenge, including T1, T2, T1ce, and fluid-attenuated inversion recovery (FLAIR) MRI images, to classify astrocytoma, oligodendroglioma, and glioblastoma. We proposed a multimodal MRI image decision fusion-based network for improving the glioma classification accuracy. First, the MRI images of each modality were input into a pre-trained tumor segmentation model to delineate the regions of tumor lesions. Then, the whole tumor regions were centrally clipped from original MRI images followed by max–min normalization. Subsequently, a deep learning-based network was designed based on a unified DenseNet structure, which extracts features through a series of dense blocks. After that, two fully connected layers were used to map the features into three glioma subtypes. During the training stage, we used the images of each modality after tumor segmentation to train the network to obtain its best accuracy on our testing set. During the inferring stage, a linear weighted module based on a decision fusion strategy was applied to assemble the predicted probabilities of the pre-trained models obtained in the training stage. Finally, the performance of our method was evaluated in terms of accuracy, area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), etc.ResultsThe proposed method achieved an accuracy of 0.878, an AUC of 0.902, a sensitivity of 0.772, a specificity of 0.930, a PPV of 0.862, an NPV of 0.949, and a Cohen’s Kappa of 0.773, which showed a significantly higher performance than existing state-of-the-art methods.ConclusionCompared with current studies, this study demonstrated the effectiveness and superiority in the overall performance of our proposed multimodal MRI image decision fusion-based network method for glioma subtype classification, which would be of enormous potential value in clinical practice.

Brain Tumor Classification Based on Hybrid Optimized Multi-features Analysis Using Magnetic Resonance Imaging Dataset

ABSTRACT Brain tumors are deadly but become deadliest because of delayed and inefficient diagnosis process. Large variations in tumor types also instigate additional complexity. Machine vision brain tumor diagnosis addresses the problem. This research’s objective was to develop a brain tumor classification model based on machine vision techniques using brain Magnetic Resonance Imaging (MRI). For this purpose, a novel hybrid-brain-tumor-classification (HBTC) framework was designed and evaluated for the classification of cystic (cyst), glioma, meningioma (menin), and metastatic (meta) brain tumors. The proposed framework lessens the inherent complexities and boosts performance of the brain tumor diagnosis process. The brain MRI dataset was input to the HBTC framework, pre-processed, segmented to localize the tumor region. From the segmented dataset Co-occurrence matrix (COM), run-length matrix (RLM), and gradient features were extracted. After the application of hybrid multi-features, the nine most optimized features were selected and input to the framework’s classifiers, namely multilayer perception (MLP), J48, meta bagging (MB), and random tree (RT) to classify cyst, glioma, menin, and meta tumors. Maximum brain tumor classification performance achieved by the HBTC framework was 98.8%. The components and performance of the proposed framework show that it is a novel and robust classification framework.

Surveillance imaging frequency in adult patients with lower-grade (WHO Grade 2 and 3) gliomas.

With improved outcome following aggressive treatment in patients with grade 2 and 3 IDH-mutant (IDHmt), 1p/19q codeleted oligodendroglioma and IDHmt, non-codeleted astrocytoma, prolonged surveillance is desirable for early detection of tumor growth and malignant transformation. Current National Comprehensive Cancer Network (NCCN) guidelines provide imaging follow-up recommendations based on molecular classification of lower-grade gliomas, although individualized imaging guidelines based on treatments received and after tumor recurrence are not clearly specified. Other available guidelines have yet to incorporate the molecular biomarkers that inform the WHO classification of gliomas, and in some cases do not adequately consider current knowledge on IDHmt glioma growth rate and recurrence patterns. Moreover, these guidelines also do not provide specific recommendations for concerning clinical symptoms or radiographic findings warranting imaging studies out of prespecified intervals. Focusing on molecularly defined grade 2 and 3 IDHmt astrocytomas and oligodendrogliomas, we review current knowledge of tumor growth rates and time to tumor progression for each tumor type and propose a range of recommended MRI surveillance intervals for both the newly diagnosed and recurrent tumor setting. Additionally, we summarize situations in which imaging is advisable outside of these intervals.

BRAF mutations in low-grade gliomas; A case report

BRAF mutations play an important role in the classification and prognostication of low-grade gliomas and may offer a therapeutic target. We report a case of a V600E mutant low-grade glioma with morphological features of a ganglioglioma diagnosed in a 22-year-old female. Sections demonstrated a low-grade lesion with atypical astrocytic glial and neuronal elements, the latter stained positive for chromogranin A and BRAF V600E immunohistochemical stains; IDH-1 immunohistochemistry was negative. A provisional diagnosis of ganglioglioma (WHO grade I) was made with a differential diagnosis of pilocytic astrocytoma with gangliocytic differentiation.

Current WHO Guidelines and the Critical Role of Genetic Parameters in the Classification of Glioma: Opportunities for Immunotherapy

In the 5 years since the fourth edition of the WHO Classification of Tumors of the Central Nervous System (CNS) (revised) was released, the development of targeted sequencing and omics technology has helped researchers in the field of neuro-oncology to identify some new tumor types in clinical practice, as well as a series of genetic parameters related to tumor occurrence and development, poor prognosis, treatment response, etc. These findings not only provide basic knowledge for the classification of glioma, but also promote the progress of the treatment of gliomas. As a revolution in cancer treatment, immunotherapy has become a promising strategy since the pioneering discovery of lymphatics in the CNS. The advancement and clinical application of immunotherapy have strengthened the demand for accurate classification of glioma. In June 2021, the WHO and the International Agency for Research on Cancer (IARC) published the fifth edition of the WHO Classification of Tumors of the CNS. The fifth edition focuses on advancing the role of genetic parameters in the classification of glioma and divides glioma into more biologically and molecularly defined entities, with better natural history characteristics, and introduced new tumor types and subtypes, especially in the pediatric population. Most importantly, these updated classifications will enable clinicians to better assess the prognosis and formulate the optimal treatment of gliomas.

Prognostic significance of TERT promoter mutations in adult-type diffuse gliomas.

TERT promoter mutations are one of the most common genetic alterations in adult-type diffuse gliomas and show specific patterns compared with other genetic alterations according to glioma subtypes. This mutation has variable impacts on patient outcomes in association with other genetic alterations, including IDH1/2 mutations or histological types. The purpose of this paper is to review the current knowledge on the values of TERT promoter mutations in the diagnosis and prognostication of adult-type diffuse gliomas. We also aimed to discuss the interaction between the prognostic impacts of TERT promoter mutations and other molecular alterations. Although its impact on prognosis is somewhat complicated and enigmatic, the mutational status of the TERT promoter provides highly useful information for predicting patients' outcomes in the conventional classification of gliomas defined by IDH1/2 and 1p/19q status.

State-of-the-Art Explainability Methods with Focus on Visual Analytics Showcased by Glioma Classification

This study aims to reflect on a list of libraries providing decision support to AI models. The goal is to assist in finding suitable libraries that support visual explainability and interpretability of the output of their AI model. Especially in sensitive application areas, such as medicine, this is crucial for understanding the decision-making process and for a safe application. Therefore, we use a glioma classification model’s reasoning as an underlying case. We present a comparison of 11 identified Python libraries that provide an addition to the better known SHAP and LIME libraries for visualizing explainability. The libraries are selected based on certain attributes, such as being implemented in Python, supporting visual analysis, thorough documentation, and active maintenance. We showcase and compare four libraries for global interpretations (ELI5, Dalex, InterpretML, and SHAP) and three libraries for local interpretations (Lime, Dalex, and InterpretML). As use case, we process a combination of openly available data sets on glioma for the task of studying feature importance when classifying the grade II, III, and IV brain tumor subtypes glioblastoma multiforme (GBM), anaplastic astrocytoma (AASTR), and oligodendroglioma (ODG), out of 1276 samples and 252 attributes. The exemplified model confirms known variations and studying local explainability contributes to revealing less known variations as putative biomarkers. The full comparison spreadsheet and implementation examples can be found in the appendix.

FISH analyses for 1p and 19q status on gliomas: Reporting an 8 years' experience from a tertiary care center in the Middle East

Diffuse gliomas are the most common primary malignancies of the central nervous system (CNS). The 2016 edition of the World Health Organization (WHO) classification of CNS tumors opted to integrate current molecular data with the traditional histologic diagnosis in the definition of the disease. This integrated diagnosis offers a greater level of objectivity and helps in establishing more definitive diagnoses for tumors that may have been controversial on histology alone. The classification of gliomas may require FISH technique to identify chromosomal abnormalities. FISH is commonly used to identify 1p/19q codeletion, but many challenges are encountered in the process. In this study, we review the FISH results for 1p/19q codeletion of n = 85 diffuse glioma samples examined at a tertiary care center in the Middle East over a period of 8 years. We also conduct a literature review to study the potential role of DNA-microarray in the identification of 1p/19q deletions. Glioblastoma (GBM), WHO grade IV is the most common glioma type identified (n = 24; 29%). All oligodendrogliomas show 1p/19q codeletion (26/26) while 12.5% of GBMs have 1p/19q codeletion (3/24). Isolated 1p deletions are only identified in one case of diffuse astrocytoma, WHO grade II. Isolated 19q deletions are identified in oligoastrocytoma, anaplastic astrocytoma, and glioblastoma. FISH is the most commonly used technique to diagnose oligodendroglioma because it is a simple, effective, and accessible technique in settings with limited resources. However, the optimization process remains highly variable between laboratories. Microarray is a more objective technique that can provide more information about the genetic alterations of the tumor for better diagnosis and sub-classification of diffuse glioma types.

CEST MRI provides amide/amine surrogate biomarkers for treatment-naïve glioma sub-typing

PurposeAccurate glioma classification affects patient management and is challenging on non- or low-enhancing gliomas. This study investigated the clinical value of different chemical exchange saturation transfer (CEST) metrics for glioma classification and assessed the diagnostic effect of the presence of abundant fluid in glioma subpopulations.MethodsForty-five treatment-naïve glioma patients with known isocitrate dehydrogenase (IDH) mutation and 1p/19q codeletion status received CEST MRI (B1rms = 2μT, Tsat = 3.5 s) at 3 T. Magnetization transfer ratio asymmetry and CEST metrics (amides: offset range 3–4 ppm, amines: 1.5–2.5 ppm, amide/amine ratio) were calculated with two models: ‘asymmetry-based’ (AB) and ‘fluid-suppressed’ (FS). The presence of T2/FLAIR mismatch was noted.ResultsIDH-wild type had higher amide/amine ratio than IDH-mutant_1p/19qcodel (p < 0.022). Amide/amine ratio and amine levels differentiated IDH-wild type from IDH-mutant (p < 0.0045) and from IDH-mutant_1p/19qret (p < 0.021). IDH-mutant_1p/19qret had higher amides and amines than IDH-mutant_1p/19qcodel (p < 0.035). IDH-mutant_1p/19qret with AB/FS mismatch had higher amines than IDH-mutant_1p/19qret without AB/FS mismatch ( < 0.016). In IDH-mutant_1p/19qret, the presence of AB/FS mismatch was closely related to the presence of T2/FLAIR mismatch (p = 0.014).ConclusionsCEST-derived biomarkers for amides, amines, and their ratio can help with histomolecular staging in gliomas without intense contrast enhancement. T2/FLAIR mismatch is reflected in the presence of AB/FS CEST mismatch. The AB/FS CEST mismatch identifies glioma subgroups that may have prognostic and clinical relevance.

Grade classification of human glioma using a convolutional neural network based on mid-infrared spectroscopy mapping.

This study proposes a convolutional neural network (CNN)-based computer-aided diagnosis (CAD) system for the grade classification of human glioma by using mid-infrared (MIR) spectroscopic mappings. Through data augmentation of pixels recombination, the mappings in the training set increased almost 161 times relative to the original mappings. The pixels of the recombined mappings in the training set came from all of the one-dimensional (1D) vibrational spectroscopy of 62 (almost 80% of all 77 patients) patients at specific bands. Compared with the performance of the CNN-CAD system based on the 1D vibrational spectroscopy, we found that the mean diagnostic accuracy of the recombined MIR spectroscopic mappings at peaks of 2917 cm-1 , 1539 cm-1 and 1234 cm-1 on the test set performed higher and the model also had more stable patterns. This research demonstrates that two-dimensional MIR mapping at a single frequency can be used by the CNN-CAD system for diagnosis and the research also gives a prompt that the mapping collection process can be replaced by a single-frequency IR imaging system, which is cheaper and more portable than a Fourier transform infrared microscopy and thus may be widely utilized in hospitals to provide meaningful assistance for pathologists in clinics.

The epithelial-mesenchymal transition of glioma cells promotes tissue factor expression via the miR200a/ZEB1 axis

Glioma is the most common brain tumor and the main cause of death from primary brain tumors. Due to the limitations of current diagnostic and treatment methods, the prognosis of high-grade glioma is not optimistic and is prone to venous thrombosis. Epithelial-mesenchymal transition (EMT) is a vital step for glioma cells to obtain a highly migratory and invasive cell phenotype. Tissue factor (TF) is the downstream target of several carcinogenic pathways. According to reports, the TF gene is highly methylated and down-regulated in IDH1 mutant gliomas with good prognosis. We aimed to investigate the impact of EMT on the expression of TF in glioma cells, as well as the corresponding mechanism. Our data indicated that the expression level of TF in glioma tissues increased, and was positively correlated with the WHO classification of glioma. After inducing EMT in glioma cells in vitro, TF expression increased significantly, indicating that EMT in glioma cells can promote TF expression. Further studies have shown that the expression level of ZEB1 is positively correlated with the WHO classification of glioma tissues and the expression level of TF in glioma tissues. This study proved that EMT promotes the expression of TF in glioma cells through the miR-200a/ZEB1 axis. In summary, these results indicated that EMT can promote the expression of TF in glioma cells via the miR-200a/ZEB1 axis. For gliomas, TF is related to EMT and has the potential to become an effective target against EMT and thrombotic events.

Comprehensive Analysis of Pyroptosis-Associated in Molecular Classification, Immunity and Prognostic of Glioma.

Integrative analysis was performed in the Chinese Glioma Genome Atlas and The Cancer Genome Atlas to describe the pyroptosis-associated molecular classification and prognostic signature in glioma. Pyroptosis-related genes were used for consensus clustering and to develop a prognostic signature. The immune statuses, molecular alterations, and clinical features of differentially expressed genes were analyzed among different subclasses and risk groups. A lncRNA-miRNA-mRNA network was built, and drug sensitivity analysis was used to identify small molecular drugs for the identified genes. Glioma can be divided into two subclasses using 30 pyroptosis-related genes. Cluster 1 displayed high immune signatures and poor prognosis as well as high immune-related function scores. A prognostic signature based on 15 pyroptosis-related genes of the CGGA cohort can predict the overall survival of glioma and was well validated in the TCGA cohort. Cluster 1 had higher risk scores. The high-risk group had high immune cell and function scores and low DNA methylation of pyroptosis-related genes. The differences in pyroptosis-related gene mutations and somatic copy numbers were significant between the high-risk and low-risk groups. The ceRNA regulatory network uncovered the regulatory patterns of different risk groups in glioma. Nine pairs of target genes and drugs were identified. In vitro, CASP8 promotes the progression of glioma cells. Pyroptosis-related genes can reflect the molecular biological and clinical features of glioma subclasses. The established prognostic signature can predict prognosis and distinguish molecular alterations in glioma patients. Our comprehensive analyses provide valuable guidelines for improving glioma patient management and individualized therapy.

Local detection of microvessels in IDH-wildtype glioblastoma using relative cerebral blood volume: an imaging marker useful for astrocytoma grade 4 classification

BackgroundThe microvessels area (MVA), derived from microvascular proliferation, is a biomarker useful for high-grade glioma classification. Nevertheless, its measurement is costly, labor-intense, and invasive. Finding radiologic correlations with MVA could provide a complementary non-invasive approach without an extra cost and labor intensity and from the first stage. This study aims to correlate imaging markers, such as relative cerebral blood volume (rCBV), and local MVA in IDH-wildtype glioblastoma, and to propose this imaging marker as useful for astrocytoma grade 4 classification.MethodsData from 73 tissue blocks belonging to 17 IDH-wildtype glioblastomas and 7 blocks from 2 IDH-mutant astrocytomas were compiled from the Ivy GAP database. MRI processing and rCBV quantification were carried out using ONCOhabitats methodology. Histologic and MRI co-registration was done manually with experts’ supervision, achieving an accuracy of 88.8% of overlay. Spearman’s correlation was used to analyze the association between rCBV and microvessel area. Mann-Whitney test was used to study differences of rCBV between blocks with presence or absence of microvessels in IDH-wildtype glioblastoma, as well as to find differences with IDH-mutant astrocytoma samples.ResultsSignificant positive correlations were found between rCBV and microvessel area in the IDH-wildtype blocks (p < 0.001), as well as significant differences in rCBV were found between blocks with microvascular proliferation and blocks without it (p < 0.0001). In addition, significant differences in rCBV were found between IDH-wildtype glioblastoma and IDH-mutant astrocytoma samples, being 2–2.5 times higher rCBV values in IDH-wildtype glioblastoma samples.ConclusionsThe proposed rCBV marker, calculated from diagnostic MRIs, can detect in IDH-wildtype glioblastoma those regions with microvessels from those without it, and it is significantly correlated with local microvessels area. In addition, the proposed rCBV marker can differentiate the IDH mutation status, providing a complementary non-invasive method for high-grade glioma classification.

Learning-based analysis of amide proton transfer-weighted MRI to identify true progression in glioma patients

The purpose of this study was to develop and verify a convolutional neural network (CNN)-based deep-learning algorithm to identify tumor progression versus response by adding amide proton transfer-weighted (APTw) MRI data to structural MR images as the proposed model input. 145 scans with 2175 MR instances from 98 patients with malignant glioma (acquired between April 2010 and February 2018) were re-analyzed. An end-to-end classification framework based on a ResNet backbone was developed. The architecture includes a learnable subtraction layer and a hierarchical classification paradigm, and synthesizes information over multiple MR slices using a long short-term memory. Areas under the receiver-operating-characteristic curves (AUCs) were used to assess the impact of adding APTw MRI to structural MRI (T1w, T2w, FLAIR, and GdT1w) on classification of tumor response vs. progression, both on the slice- and scan-level. With both APTw and structural MRI data, adding a learnable subtraction layer and a hierarchical classification paradigm to the backbone ResNet model improved the slice-level classification performance from an AUC of 0.85 to 0.90. Adding APTw data to structural MR images as input to our proposed CNN classification framework led to an increase in AUCs from 0.88 to 0.90 for the slice-level classification (P < 0.001), and from 0.85 to 0.90 for the scan-level classification (P < 0.05). Generated saliency maps highlighted the vast majority of lesions. Complementing structural MRI sequences with protein-based APTw MRI enhanced CNN-based classification of recurrent glioma at the slice and scan levels. Addition of APTw MRI to structural MRI sequences enhanced CNN-based classification of recurrent glioma at the slice and scan levels.

Classification and Diagnosis of Adult Glioma: A Scoping Review.

Gliomas are primary central nervous system tumors that arise from glial progenitor cells. Gliomas have been classically classified morphologically based on their histopathological characteristics. However, with recent advances in cancer genomics, molecular profiles have now been integrated into the classification and diagnosis of gliomas. In this review article, we discuss the clinical features, imaging findings, and molecular profiles of adult-type diffuse gliomas based on the new 2021 World Health Organization Classifications of Tumors of the central nervous system.

Telomeric Parameters Improve Glioma Diagnosis and Liquid Biopsy Approaches.

Detection of telomeric maintenance mechanisms enabled classification of both typical and atypical glioma.

Immunohistochemical surrogates for molecular alterations for the classification and grading of gliomas.

Recent advances in molecular diagnostics have led to a better understanding of glioma tumorigenesis, prognosis, and treatment. Therefore, the 2016 WHO Classification of Tumours of the Central Nervous System and more recent literature recommends the incorporation of molecular results in the pathology report. The methods for molecular testing vary among institutions; however, most practicing pathologists utilize a range of immunohistochemical surrogates for molecular alterations in the evaluation of gliomas. This manuscript reviews the clinical aspects and pitfalls of the immunohistochemical stains with diagnostic, prognostic and therapeutic implications in gliomas.

Hydrogen Proton Magnetic Resonance Spectroscopy (MRS) in Differential Diagnosis of Intracranial Tumors: A Systematic Review.

Meningioma, glioma, and metastases are the most common intracranial tumors in clinical practice. In order to improve the prognosis of patients, timely diagnosis and early treatment are crucial. Hydrogen proton magnetic resonance spectroscopy (1H-MRS) imaging can noninvasively display the biochemical information of tissues in vivo and has been applied to identify and diagnose intracranial tumors. We want to comprehensively evaluate 1H-MRS identify and diagnose intracranial tumors by meta-analysis. Some databases such as PubMed and Cochrane Library were used to systematically search articles that were about identifying and diagnosing intracranial tumors with 1H-MRS. Then, weighted mean difference (WMD) was used as an effect size to conduct meta-analysis. There are altogether nine articles, including 533 patients. Results of meta-analysis: The Cho/Cr and Cho/NAA ratios in the LGG group were significantly lower than those in the HGG group (WMD = −0.69, 95% CI (−0.92, −0.45), P < 0.001, WMD = −0.76, 95% CI (−1.03, −0.48), P < 0.001). The Cho/Cr ratio of tumor and peritumor in the HGG group was significantly different from that in the metastasis group (0.68, 95% CI (−1.27, 2.62), P < 0.001, WMD = 0.94, 95% CI (0.41, 1.47), P < 0.001). There was no significant difference in the tumor and peritumor NAA/Cr ratio between the HGG group and metastasis group (WMD = −0.64, 95% CI (−1.63, 0.34), P=0.31, WMD = −0.22, 95% CI (−0.59, 0.15), P=0.24). 1H-MRS can provide metabolic information of different intracranial tumors and can effectively diagnose and differentiate glioma and metastasis. 1H-MRS can also provide a reliable basis for the classification of glioma, and has certain clinical application value.

WHO CNS5 2021 classification of gliomas: apractical review and road signs for diagnosing pathologists and proper patho-clinical and neuro-oncological cooperation.

The 5th edition of World Health Organization (WHO) Central Nervous System (CNS) tumours classification has transformed the pathological diagnosis of gliomas from purely histological to the multilayered integrated one with molecular biomarkers necessary for proper classification, risk stratification, and prognostic-predictive clinical purposes. Because of deep and important changes in taxonomy and diagnostic approach to gliomas, this manuscript is a review of WHO CNS classification 5th edition with general testing guidance for pathologists and clinicians working in neuro-oncology.

Adolescent and young adult glioma: systematic review of demographic, disease, and treatment influences on survival.

Prognostic factors in adolescent and young adult (AYA) glioma are not well understood. Though clinical and molecular differences between pediatric and adult glioma have been characterized, their application to AYA populations is less clear. There is a major need to develop more robust evidence-based practices for managing AYA glioma patients. A systematic review using PRISMA methodology was conducted using multiple databases with the objective of identifying demographic, clinical, molecular and treatment factors influencing AYA glioma outcomes. 40 Studies met inclusion criteria. Overall survival was highly variable across studies depending on glioma grade, anatomic compartment and cohort characteristics. Thirty-five studies suffered from high risk of bias in at least one domain. Several studies included older adults within their cohorts; few captured purely AYA groups. Despite study heterogeneity, identified favorable prognosticators included younger age, higher functional status at diagnosis, low-grade pathology, oligodendroglioma histology and increased extent of surgical resection. Though isocitrate dehydrogenase (IDH) mutant status was associated with favorable prognosis, validity of this finding within AYA was compromised though may studies including older adults. The prognostic influence of chemotherapy and radiotherapy on overall survival varied across studies with conflicting evidence. Existing literature is heterogenous, at high risk of bias, and rarely focused solely on AYA patients. Many included studies did not reflect updated pathological and molecular AYA glioma classification. The optimal role of chemotherapy, radiotherapy, and targeted agents cannot be determined from existing literature and should be the focus of future studies.