ABSTRACT
Brain tumor diagnosis using MRI scans poses significant challenges due to the complex nature of tumor appearances and variations. Traditional methods often require extensive manual intervention and are prone to human error, leading to misdiagnosis and delayed treatment. Current approaches primarily include manual examination by radiologists and conventional machine learning techniques. These methods rely heavily on feature extraction and classification algorithms, which may not capture the intricate patterns present in brain MRI images. Conventional techniques often suffer from limited accuracy and generalizability, mainly due to the high variability in tumor appearance and the subjective nature of manual interpretation. Additionally, traditional machine learning models may struggle with the high-dimensional data inherent in MRI images. To address these limitations, our research introduces a deep learning-based model utilizing convolutional neural networks (CNNs).Our model employs a sequential CNN architecture with multiple convolutional, max-pooling, and dropout layers, followed by dense layers for classification. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The precision, recall, and F1-scores ranging from 97 to 98% with a roc-auc ranging from 99 to 100% for each tumor category further substantiate the model's effectiveness. Additionally, the utilization of Grad-CAM visualizations provides insights into the model's decision-making process, enhancing interpretability. This research addresses the pressing need for enhanced diagnostic accuracy in identifying brain tumors through MRI imaging, tackling challenges such as variability in tumor appearance and the need for rapid, reliable diagnostic tools.
Subject(s)
Brain Neoplasms , Deep Learning , Magnetic Resonance Imaging , Neural Networks, Computer , Humans , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/classification , Magnetic Resonance Imaging/methods , Algorithms , Image Interpretation, Computer-Assisted/methods , Male , FemaleABSTRACT
Brain tumor classification using MRI images is a crucial yet challenging task in medical imaging. Accurate diagnosis is vital for effective treatment planning but is often hindered by the complex nature of tumor morphology and variations in imaging. Traditional methodologies primarily rely on manual interpretation of MRI images, supplemented by conventional machine learning techniques. These approaches often lack the robustness and scalability needed for precise and automated tumor classification. The major limitations include a high degree of manual intervention, potential for human error, limited ability to handle large datasets, and lack of generalizability to diverse tumor types and imaging conditions.To address these challenges, we propose a federated learning-based deep learning model that leverages the power of Convolutional Neural Networks (CNN) for automated and accurate brain tumor classification. This innovative approach not only emphasizes the use of a modified VGG16 architecture optimized for brain MRI images but also highlights the significance of federated learning and transfer learning in the medical imaging domain. Federated learning enables decentralized model training across multiple clients without compromising data privacy, addressing the critical need for confidentiality in medical data handling. This model architecture benefits from the transfer learning technique by utilizing a pre-trained CNN, which significantly enhances its ability to classify brain tumors accurately by leveraging knowledge gained from vast and diverse datasets.Our model is trained on a diverse dataset combining figshare, SARTAJ, and Br35H datasets, employing a federated learning approach for decentralized, privacy-preserving model training. The adoption of transfer learning further bolsters the model's performance, making it adept at handling the intricate variations in MRI images associated with different types of brain tumors. The model demonstrates high precision (0.99 for glioma, 0.95 for meningioma, 1.00 for no tumor, and 0.98 for pituitary), recall, and F1-scores in classification, outperforming existing methods. The overall accuracy stands at 98%, showcasing the model's efficacy in classifying various tumor types accurately, thus highlighting the transformative potential of federated learning and transfer learning in enhancing brain tumor classification using MRI images.
Subject(s)
Brain Neoplasms , Deep Learning , Magnetic Resonance Imaging , Humans , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/classification , Magnetic Resonance Imaging/methods , Neural Networks, Computer , Machine Learning , Image Interpretation, Computer-Assisted/methodsABSTRACT
PURPOSE: The purpose of this study is to develop accurate and automated detection and segmentation methods for brain tumors, given their significant fatality rates, with aggressive malignant tumors like Glioblastoma Multiforme (GBM) having a five-year survival rate as low as 5 to 10%. This underscores the urgent need to improve diagnosis and treatment outcomes through innovative approaches in medical imaging and deep learning techniques. METHODS: In this work, we propose a novel approach utilizing the two-headed UNetEfficientNets model for simultaneous segmentation and classification of brain tumors from Magnetic Resonance Imaging (MRI) images. The model combines the strengths of EfficientNets and a modified two-headed Unet model. We utilized a publicly available dataset consisting of 3064 brain MR images classified into three tumor classes: Meningioma, Glioma, and Pituitary. To enhance the training process, we performed 12 types of data augmentation on the training dataset. We evaluated the methodology using six deep learning models, ranging from UNetEfficientNet-B0 to UNetEfficientNet-B5, optimizing the segmentation and classification heads using binary cross entropy (BCE) loss with Dice and BCE with focal loss, respectively. Post-processing techniques such as connected component labeling (CCL) and ensemble models were applied to improve segmentation outcomes. RESULTS: The proposed UNetEfficientNet-B4 model achieved outstanding results, with an accuracy of 99.4% after postprocessing. Additionally, it obtained high scores for DICE (94.03%), precision (98.67%), and recall (99.00%) after post-processing. The ensemble technique further improved segmentation performance, with a global DICE score of 95.70% and Jaccard index of 91.20%. CONCLUSION: Our study demonstrates the high efficiency and accuracy of the proposed UNetEfficientNet-B4 model in the automatic and parallel detection and segmentation of brain tumors from MRI images. This approach holds promise for improving diagnosis and treatment planning for patients with brain tumors, potentially leading to better outcomes and prognosis.
Subject(s)
Brain Neoplasms , Deep Learning , Magnetic Resonance Imaging , Humans , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/classification , Brain Neoplasms/pathology , Magnetic Resonance Imaging/methods , Image Processing, Computer-Assisted/methods , Glioblastoma/diagnostic imaging , Glioblastoma/classification , Glioblastoma/pathology , Glioma/diagnostic imaging , Glioma/classification , Glioma/pathologyABSTRACT
BACKGROUND: Glioma is a common and aggressive primary malignant cancer known for its high morbidity, mortality, and recurrence rates. Despite this, treatment options for glioma are currently restricted. The dysregulation of RBPs has been linked to the advancement of several types of cancer, but their precise role in glioma evolution is still not fully understood. This study sought to investigate how RBPs may impact the development and prognosis of glioma, with potential implications for prognosis and therapy. METHODS: RNA-seq profiles of glioma and corresponding clinical data from the CGGA database were initially collected for analysis. Unsupervised clustering was utilized to identify crucial tumor subtypes in glioma development. Subsequent time-series analysis and MS model were employed to track the progression of these identified subtypes. RBPs playing a significant role in glioma progression were then pinpointed using WGCNA and Lasso Cox regression models. Functional analysis of these key RBP-related genes was conducted through GSEA. Additionally, the CIBERSORT algorithm was utilized to estimate immune infiltrating cells, while the STRING database was consulted to uncover potential mechanisms of the identified biomarkers. RESULTS: Six tumor subgroups were identified and found to be highly homogeneous within each subgroup. The progression stages of these tumor subgroups were determined using time-series analysis and a MS model. Through WGCNA, Lasso Cox, and multivariate Cox regression analysis, it was confirmed that BCLAF1 is correlated with survival in glioma patients and is closely linked to glioma progression. Functional annotation suggests that BCLAF1 may impact glioma progression by influencing RNA splicing, which in turn affects the cell cycle, Wnt signaling pathway, and other cancer development pathways. CONCLUSIONS: The study initially identified six subtypes of glioma progression and assessed their malignancy ranking. Furthermore, it was determined that BCLAF1 could serve as an RBP-related prognostic marker, offering significant implications for the clinical diagnosis and personalized treatment of glioma.
Subject(s)
Biomarkers, Tumor , Brain Neoplasms , Glioma , RNA-Binding Proteins , Glioma/genetics , Glioma/classification , Glioma/metabolism , Humans , Brain Neoplasms/genetics , Brain Neoplasms/classification , Brain Neoplasms/metabolism , RNA-Binding Proteins/genetics , RNA-Binding Proteins/metabolism , Biomarkers, Tumor/genetics , Biomarkers, Tumor/metabolism , Databases, Genetic , Gene Expression Regulation, NeoplasticABSTRACT
This research focuses on improving the detection and classification of brain tumors using a method called Brain Tumor Classification using Dual-Discriminator Conditional Generative Adversarial Network (DDCGAN) for MRI images. The proposed system is implemented in the MATLAB programming language. In this study, images of the brain are taken from a dataset and processed to remove noise and enhance image quality. The brain pictures are taken from Brats MRI image dataset. The images are preprocessed using Structural interval gradient filtering to remove noises and improve the quality of the image. The preprocessing outcomes are given to feature extraction. The features are extracted by Empirical wavelet transform (EWT) and the extracted features are given to the Dual-discriminator conditional generative adversarial network (DDCGAN) for recognizing the brain tumor, which classifies the brain images into glioma, meningioma, pituitary gland, and normal. Then, the weight parameter of DDCGAN is optimized by utilizing Border Collie Optimization (BCO), which is a met a heuristic approach to handle the real world optimization issues. It maximizes the detection accurateness and reduced computational time. Implemented in MATLAB, the experimental results demonstrate that the proposed system achieves a high sensitivity of 99.58%. The BCO-DDCGAN-MRI-BTC method outperforms existing techniques in terms of precision and sensitivity when compared to methods like Kernel Basis SVM (KSVM-HHO-BTC), Joint Training of Two-Channel Deep Neural Network (JT-TCDNN-BTC), and YOLOv2 including Convolutional Neural Network (YOLOv2-CNN-BTC). The research findings indicate that the proposed method enhances the accuracy of brain tumor classification while reducing computational time and errors.
This research focuses on improving the detection and classification of brain tumors using a method called Brain Tumor Classification using Dual-Discriminator Conditional Generative Adversarial Network (DDCGAN) for MRI images. Brain tumors can significantly impact normal brain function and lead to loss of lives, making timely diagnosis crucial. However, the process of locating affected brain cells is often time-consuming. In this study, images of the brain are taken from a dataset and processed to remove noise and enhance image quality. The proposed method employs the Empirical Wavelet Transform (EWT) for feature extraction and utilizes the DDCGAN to classify brain images into different types of tumors (glioma, meningioma, pituitary gland) and normal brain images. The weight parameter of DDCGAN is optimized using Border Collie Optimization (BCO), a method to handle real-world optimization issues. This optimization aims to maximize detection accuracy and minimize computational time. Implemented in MATLAB, the experimental results demonstrate that the proposed system achieves a high sensitivity of 99.58%. The BCO-DDCGAN-MRI-BTC method outperforms existing techniques in terms of precision and sensitivity when compared to methods like Kernel Basis SVM (KSVM-HHO-BTC), Joint Training of Two-Channel Deep Neural Network (JT-TCDNN-BTC), and YOLOv2 including Convolutional Neural Network (YOLOv2-CNN-BTC). The research findings indicate that the proposed method enhances the accuracy of brain tumor classification while reducing computational time and errors.
Subject(s)
Brain Neoplasms , Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Magnetic Resonance Imaging/methods , Humans , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/classification , Brain Neoplasms/pathology , Image Processing, Computer-Assisted/methods , Neural Networks, Computer , Wavelet AnalysisABSTRACT
This paper proposes a novel approach, BTC-SAGAN-CHA-MRI, for the classification of brain tumors using a SAGAN optimized with a Color Harmony Algorithm. Brain cancer, with its high fatality rate worldwide, especially in the case of brain tumors, necessitates more accurate and efficient classification methods. While existing deep learning approaches for brain tumor classification have been suggested, they often lack precision and require substantial computational time.The proposed method begins by gathering input brain MR images from the BRATS dataset, followed by a pre-processing step using a Mean Curvature Flow-based approach to eliminate noise. The pre-processed images then undergo the Improved Non-Sub sampled Shearlet Transform (INSST) for extracting radiomic features. These features are fed into the SAGAN, which is optimized with a Color Harmony Algorithm to categorize the brain images into different tumor types, including Gliomas, Meningioma, and Pituitary tumors. This innovative approach shows promise in enhancing the precision and efficiency of brain tumor classification, holding potential for improved diagnostic outcomes in the field of medical imaging. The accuracy acquired for the brain tumor identification from the proposed method is 99.29%. The proposed BTC-SAGAN-CHA-MRI technique achieves 18.29%, 14.09% and 7.34% higher accuracy and 67.92%,54.04%, and 59.08% less Computation Time when analyzed to the existing models, like Brain tumor diagnosis utilizing deep learning convolutional neural network with transfer learning approach (BTC-KNN-SVM-MRI); M3BTCNet: multi model brain tumor categorization under metaheuristic deep neural network features optimization (BTC-CNN-DEMFOA-MRI), and efficient method depending upon hierarchical deep learning neural network classifier for brain tumour categorization (BTC-Hie DNN-MRI) respectively.
This paper proposes a novel approach, BTC-SAGAN-CHA-MRI, for the classification of brain tumors using a Self-Attention based Generative Adversarial Network (SAGAN) optimized with a Color Harmony Algorithm. Brain cancer, with its high fatality rate worldwide, especially in the case of brain tumors, necessitates more accurate and efficient classification methods. While existing deep learning approaches for brain tumor classification have been suggested, they often lack precision and require substantial computational time. The proposed method begins by gathering input brain MR images from the BRATS dataset, followed by a pre-processing step using a Mean Curvature Flow-based approach to eliminate noise. The pre-processed images then undergo the Improved Non-Sub sampled Shearlet Transform (INSST) for extracting radiomic features. These features are fed into the SAGAN, which is optimized with a Color Harmony Algorithm to categorize the brain images into different tumor types, including Gliomas, Meningioma, and Pituitary tumors. This innovative approach shows promise in enhancing the precision and efficiency of brain tumor classification, holding potential for improved diagnostic outcomes in the field of medical imaging.
Subject(s)
Algorithms , Brain Neoplasms , Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/classification , Brain Neoplasms/pathology , Humans , Image Processing, Computer-Assisted/methods , Color , Neural Networks, Computer , Deep LearningABSTRACT
This study proposes a deep convolutional neural network for the automatic segmentation of glioblastoma brain tumors, aiming sat replacing the manual segmentation method that is both time-consuming and labor-intensive. There are many challenges for automatic segmentation to finely segment sub-regions from multi-sequence magnetic resonance images because of the complexity and variability of glioblastomas, such as the loss of boundary information, misclassified regions, and subregion size. To overcome these challenges, this study introduces a spatial pyramid module and attention mechanism to the automatic segmentation algorithm, which focuses on multi-scale spatial details and context information. The proposed method has been tested in the public benchmarks BraTS 2018, BraTS 2019, BraTS 2020 and BraTS 2021 datasets. The Dice score on the enhanced tumor, whole tumor, and tumor core were respectively 79.90 %, 89.63 %, and 85.89 % on the BraTS 2018 dataset, respectively 77.14 %, 89.58 %, and 83.33 % on the BraTS 2019 dataset, and respectively 77.80 %, 90.04 %, and 83.18 % on the BraTS 2020 dataset, and respectively 83.48 %, 90.70 %, and 88.94 % on the BraTS 2021 dataset offering performance on par with that of state-of-the-art methods with only 1.90 M parameters. In addition, our approach significantly reduced the requirements for experimental equipment, and the average time taken to segment one case was only 1.48 s; these two benefits rendered the proposed network intensely competitive for clinical practice.
Subject(s)
Brain Neoplasms , Glioblastoma , Magnetic Resonance Imaging , Neural Networks, Computer , Humans , Brain Neoplasms/classification , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/pathology , Glioblastoma/classification , Glioblastoma/diagnostic imaging , Glioblastoma/pathology , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methodsABSTRACT
We demonstrate that isomorphically mapping gray-level medical image matrices onto energy spaces underlying the framework of fast data density functional transform (fDDFT) can achieve the unsupervised recognition of lesion morphology. By introducing the architecture of geometric deep learning and metrics of graph neural networks, gridized density functionals of the fDDFT establish an unsupervised feature-aware mechanism with global convolutional kernels to extract the most likely lesion boundaries and produce lesion segmentation. An AutoEncoder-assisted module reduces the computational complexity from [Formula: see text] to [Formula: see text], thus efficiently speeding up global convolutional operations. We validate their performance utilizing various open-access datasets and discuss limitations. The inference time of each object in large three-dimensional datasets is 1.76 s on average. The proposed gridized density functionals have activation capability synergized with gradient ascent operations, hence can be modularized and embedded in pipelines of modern deep neural networks. Algorithms of geometric stability and similarity convergence also raise the accuracy of unsupervised recognition and segmentation of lesion images. Their performance achieves the standard requirement for conventional deep neural networks; the median dice score is higher than 0.75. The experiment shows that the synergy of fDDFT and a naïve neural network improves the training and inference time by 58% and 51%, respectively, and the dice score raises to 0.9415. This advantage facilitates fast computational modeling in interdisciplinary applications and clinical investigation.
Subject(s)
Brain Neoplasms , Deep Learning , Brain Neoplasms/classification , Brain Neoplasms/pathology , Humans , Neural Networks, Computer , Pattern Recognition, Automated , Diagnostic Imaging , Datasets as TopicABSTRACT
The Brain Tumor Epidemiology Consortium (BTEC) is an international organization that fosters collaboration among scientists focused on understanding the epidemiology of brain tumors with interests ranging from the etiology of brain tumor development and outcomes to the control of morbidity and mortality. The 2022 annual BTEC meeting with the theme "Pediatric Brain Tumors: Origins, Epidemiology, and Classification" was held in Lyon, France on June 20 - 22, 2022. Scientists from North America and Europe presented recent research and progress in the field. The meeting content is summarized in this report.
Subject(s)
Brain Neoplasms , Child , Humans , Brain Neoplasms/classification , Brain Neoplasms/epidemiology , Brain Neoplasms/etiologyABSTRACT
The World Health Organization (WHO) published the fifth edition of the WHO Classification of Tumors of the Central Nervous System (WHO CNS5) in 2021, as an update of the WHO central nervous system (CNS) classification system published in 2016. WHO CNS5 was drafted on the basis of recommendations from the Consortium to Inform Molecular and Practical Approaches to CNS Tumor Taxonomy (cIMPACT-NOW) and expounds the classification scheme of the previous edition, which emphasized the importance of genetic and molecular changes in the characteristics of CNS tumors. Multiple newly recognized tumor types, including those for which there is limited knowledge regarding neuroimaging features, are detailed in WHO CNS5. The authors describe the major changes introduced in WHO CNS5, including revisions to tumor nomenclature. For example, WHO grade IV tumors in the fourth edition are equivalent to CNS WHO grade 4 tumors in the fifth edition, and diffuse midline glioma, H3 K27M-mutant, is equivalent to midline glioma, H3 K27-altered. With regard to tumor typing, isocitrate dehydrogenase (IDH)-mutant glioblastoma has been modified to IDH-mutant astrocytoma. In tumor grading, IDH-mutant astrocytomas are now graded according to the presence or absence of homozygous CDKN2A/B deletion. Moreover, the molecular mechanisms of tumorigenesis, as well as the clinical characteristics and imaging features of the tumor types newly recognized in WHO CNS5, are summarized. Given that WHO CNS5 has become the foundation for daily practice, radiologists need to be familiar with this new edition of the WHO CNS tumor classification system. Online supplemental material and the slide presentation from the RSNA Annual Meeting are available for this article. ©RSNA, 2022.
Subject(s)
Astrocytoma , Brain Neoplasms , Central Nervous System Neoplasms , Glioma , Astrocytoma/classification , Astrocytoma/pathology , Brain Neoplasms/classification , Brain Neoplasms/pathology , Central Nervous System Neoplasms/classification , Central Nervous System Neoplasms/pathology , Glioma/classification , Glioma/pathology , Humans , Isocitrate Dehydrogenase/genetics , Mutation , World Health OrganizationABSTRACT
AIM: To evaluate isocitrate dehydrogenase (IDH) mutation status and Ki67 percentages of tumors that were treated in our institution to determine whether these markers affected the initial diagnosis and survival rates. MATERIAL AND METHODS: High-grade glioma patients, who were operated in our department between 2013 and 2018, were enrolled in the study and retrospectively reviewed. New immunohistochemistry staining studies were conducted and survival analyses were performed. RESULTS: Of 135 patients and 136 tumors, 117 were glioblastoma multiforme (GBM), 8 were grade III-IV glioma, 4 were anaplastic astrocytoma and 7 were anaplastic oligodendroglioma. One patient had two different lesions, which were GBM and anaplastic astrocytoma respectively. Mean age was 55 (7-85) years, and 88 (65%) were male and 47 (35%) were female. The most common complaint was motor deficit (56%). Fourteen patients underwent reoperation due to recurrent disease. Tumors were most commonly found in the frontal lobe (53, 39%). Magnetic resonance imaging (MRI) features showed that existence of necrosis is strongly related to GBM (p < 0.01). Approximately 126 patients were found to be IDH-wildtype, which changed 6 patients? diagnosis to GBM, IDH wildtype from grade III-IV glioma. Five patients, who were diagnosed with anaplastic astrocytoma and anaplastic oligodendroglioma initially were found to be IDH wildtype. IDH mutation status, extend of resection, and age were found to affect survival. CONCLUSION: IDH mutation status is important in classifying high-grade gliomas, as well as its effects on prognosis. This mutation is related to several radiological features of tumors. Extent of resection and patient age are also profoundly affect survival. Detailing the diagnosis with molecular features will help physicians to shape targeted adjuvant therapies, which would better outcomes.
Subject(s)
Astrocytoma , Biomarkers, Tumor , Glioblastoma , Glioma , Astrocytoma/genetics , Astrocytoma/surgery , Brain Neoplasms/classification , Brain Neoplasms/pathology , Brain Neoplasms/surgery , Female , Glioblastoma/classification , Glioblastoma/pathology , Glioblastoma/surgery , Glioma/classification , Glioma/pathology , Glioma/surgery , Humans , Immunohistochemistry , Isocitrate Dehydrogenase/genetics , Ki-67 Antigen , Male , Middle Aged , Oligodendroglioma/classification , Oligodendroglioma/pathology , Oligodendroglioma/surgery , Prognosis , Retrospective Studies , World Health OrganizationABSTRACT
Based on alterations in gene expression associated with the production of glycolysis and cholesterol, this research classified glioma into prognostic metabolic subgroups. In this study, data from the CGGA325 and The Cancer Genome Atlas (TCGA) datasets were utilized to extract single nucleotide variants (SNVs), RNA-seq expression data, copy number variation data, short insertions and deletions (InDel) mutation data, and clinical follow-up information from glioma patients. Glioma metabolic subtypes were classified using the ConsensusClusterPlus algorithm. This study determined four metabolic subgroups (glycolytic, cholesterogenic, quiescent, and mixed). Cholesterogenic patients had a higher survival chance. Genome-wide investigation revealed that inappropriate amplification of MYC and TERT was associated with improper cholesterol anabolic metabolism. In glioma metabolic subtypes, the mRNA levels of mitochondrial pyruvate carriers 1 and 2 (MPC1/2) presented deletion and amplification, respectively. Differentially upregulated genes in the glycolysis group were related to pathways, including IL-17, HIF-1, and TNF signaling pathways and carbon metabolism. Downregulated genes in the glycolysis group were enriched in terpenoid backbone biosynthesis, nitrogen metabolism, butanoate metabolism, and fatty acid metabolism pathway. Cox analysis of univariate and multivariate survival showed that risks of glycolysis subtypes were significantly higher than other subtypes. Those results were validated in the CGGA325 dataset. The current findings greatly contribute to a comprehensive understanding of glioma and personalized treatment.
Subject(s)
Brain Neoplasms/classification , Glioma/classification , Algorithms , Brain Neoplasms/genetics , Brain Neoplasms/metabolism , Cholesterol/biosynthesis , Cholesterol/genetics , Computational Biology , Databases, Genetic/statistics & numerical data , Female , Gene Expression Regulation, Neoplastic , Glioma/genetics , Glioma/metabolism , Glycolysis/genetics , Humans , Male , Middle Aged , PrognosisABSTRACT
Image fusion can be performed on images either in spatial domain or frequency domain methods. Frequency domain methods will be most preferred because these methods can improve the quality of edges in an image. In image fusion, the resultant fused images will be more informative than individual input images, thus more suitable for classification problems. Artificial intelligence (AI) algorithms play a significant role in improving patient's treatment in the health care industry and thus improving personalized medicine. This research work analyses the role of image fusion in an improved brain tumour classification model, and this novel fusion-based cancer classification model can be used for personalized medicine more effectively. Image fusion can improve the quality of resultant images and thus improve the result of classifiers. Instead of using individual input images, the high-quality fused images will provide better classification results. Initially, the contrast limited adaptive histogram equalization technique preprocess input images such as MRI and SPECT images. Benign and malignant class brain tumor images are applied with discrete cosine transform-based fusion method to obtain fused images. AI algorithms such as support vector machine classifier, KNN classifier, and decision tree classifiers are tested with features obtained from fused images and compared with the result obtained from individual input images. Performances of classifiers are measured using the parameters accuracy, precision, recall, specificity, and F1 score. SVM classifier provided the maximum accuracy of 96.8%, precision of 95%, recall of 94%, specificity of 93%, F1 score of 91%, and performed better than KNN and decision tree classifiers when extracted features from fused images are used. The proposed method results are compared with existing methods and provide satisfactory results.
Subject(s)
Algorithms , Brain Neoplasms/classification , Brain Neoplasms/diagnostic imaging , Image Enhancement/methods , Machine Learning , Computational Biology , Databases, Factual/statistics & numerical data , Decision Trees , Early Detection of Cancer/methods , Early Detection of Cancer/statistics & numerical data , Humans , Multimodal Imaging/methods , Multimodal Imaging/statistics & numerical data , Neural Networks, Computer , Neuroimaging/methods , Neuroimaging/statistics & numerical data , Precision Medicine/methods , Precision Medicine/statistics & numerical data , Support Vector MachineABSTRACT
BACKGROUND: The 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. METHODS: Data 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. RESULTS: Significant 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. CONCLUSIONS: The 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.
Subject(s)
Astrocytoma/diagnostic imaging , Brain Neoplasms/diagnostic imaging , Cerebral Blood Volume , Glioblastoma/diagnostic imaging , Microvessels/diagnostic imaging , Astrocytoma/classification , Biomarkers, Tumor/analysis , Brain Neoplasms/classification , Glioblastoma/classification , Humans , Magnetic Resonance Imaging , Reproducibility of Results , Statistics, NonparametricABSTRACT
The corresponding member of the Academy of Medical Sciences of the USSR Professor Leonid Iosifovich Smirnov (1889 - 1955) authored several dozen publications on neuropathology of infections, schizophrenia, cerebral injuries, and brain tumors. Based on his study of pathology of gunshot head injuries during World War II he suggested a doctrine of traumatic on traumatic brain disease. He was the author of the first Russian classification of cerebral tumors and had an impact on the development of neurooncology in the former USSR. The aim of this paper is to show the early development of modern neuropathology at the example of a leading Soviet neuropathologist in the first half of the 20th century and his relevance for modern classification of CNS tumors.
Subject(s)
Brain Neoplasms , Neuropathology , Brain Neoplasms/classification , Brain Neoplasms/history , History, 19th Century , History, 20th Century , Humans , Neuropathology/history , USSRABSTRACT
T2-FLAIR mismatch sign has been advocated to be 100% specific for IDH-mutant 1p/19q non-codeleted gliomas (diffuse astrocytomas). However, false positives have been reported in recent works. Loose application of the criteria may lead to erroneous classification, especially by non-trained neuroradiologists. In this pictorial essay, we aim to bring attention to the need for strict criteria for the application of T2-FLAIR mismatch sign and to discuss the potential pitfalls in the application of these criteria. For that, a series of adult brain tumour cases are presented to demonstrate how to apply this radiological sign in the clinical practice.
Subject(s)
Brain Neoplasms/diagnostic imaging , Brain Neoplasms/genetics , Glioma/diagnostic imaging , Glioma/genetics , Magnetic Resonance Imaging , Brain/diagnostic imaging , Brain/pathology , Brain Neoplasms/classification , Brain Neoplasms/pathology , Chromosomes, Human, Pair 1/genetics , Chromosomes, Human, Pair 19/genetics , Glioma/classification , Glioma/pathology , Humans , Image Interpretation, Computer-Assisted , Isocitrate Dehydrogenase/genetics , Mutation , NeuroimagingABSTRACT
OBJECTIVE: The aim of this study was to investigate the epidemiological characteristics, associated risk factors, and prognostic value of glioma-related epilepsy in patients with diffuse high-grade gliomas (DHGGs) that were diagnosed after the 2016 updated WHO classification was released. METHODS: Data from 449 patients with DHGGs were retrospectively collected. Definitive diagnosis was reaffirmed according to the 2016 WHO classification. Seizure outcome was assessed using the Engel classification at 12 months after surgery. Univariate and multivariate analyses were performed to identify risk factors associated with preoperative and postoperative glioma-related epilepsy. Lastly, the prognostic value of glioma-related epilepsy was evaluated by Kaplan-Meier and Cox analysis. RESULTS: The incidence of glioma-related epilepsy decreased gradually as the malignancy of the tumor increased. Age < 45 years (OR 2.601, p < 0.001), normal neurological function (OR 3.024, p < 0.001), and lower WHO grade (OR 2.028, p = 0.010) were independently associated with preoperative glioma-related epilepsy, while preoperative glioma-related epilepsy (OR 7.554, p < 0.001), temporal lobe involvement (OR 1.954, p = 0.033), non-gross-total resection (OR 2.286, p = 0.012), and lower WHO grade (OR 2.130, p = 0.021) were identified as independent predictors of poor seizure outcome. Furthermore, postoperative glioma-related epilepsy, rather than preoperative glioma-related epilepsy, was demonstrated as an independent prognostic factor for overall survival (OR 0.610, p = 0.010). CONCLUSIONS: The updated WHO classification seems conducive to reveal the distribution of glioma-related epilepsy in DHGG patients. For DHGG patients with high-risk predictors of poor seizure control, timely antiepileptic interventions could be beneficial. Moreover, glioma-related epilepsy (especially postoperative glioma-related epilepsy) is associated with favorable overall survival.
Subject(s)
Brain Neoplasms/complications , Epilepsy/etiology , Glioma/complications , Seizures/physiopathology , Adolescent , Adult , Aged , Brain Neoplasms/classification , Epilepsy/epidemiology , Female , Glioma/classification , Humans , Incidence , Kaplan-Meier Estimate , Male , Margins of Excision , Middle Aged , Predictive Value of Tests , Prognosis , Retrospective Studies , Risk Factors , Seizures/etiology , Survival Analysis , Temporal Lobe/surgery , Treatment Outcome , World Health Organization , Young AdultABSTRACT
Rethinking IDH-wildtype glioblastoma through its unique features can help researchers find innovative and effective treatments. It is currently emerging that, after decades of therapeutic impasse, some traditional concepts regarding IDH-wildtype glioblastoma need to be supplemented and updated to overcome therapeutic resistance. Indeed, multiple clinical aspects and recent indirect and direct experimental data are providing evidence that the supratentorial brain parenchyma becomes entirely and quiescently micro-infiltrated long before primary tumor bulk growth. Furthermore, they are indicating that the known micro-infiltration that occurs during the IDH-wildtype glioblastoma growth and evolution is not at the origin of distant relapses. It follows that the ubiquitous supratentorial brain parenchyma micro-infiltration as a source for the development of widespread distant recurrences is actually due to the silent stage that precedes tumor growth rather than to the latter. All this implies that, in addition to the heterogeneity of the primary bulk, there is a second crucial cause of therapeutic resistance that has never hitherto been identified and challenged. In this regard, the ancestral founder cancer stem cell (CSC) appears as the key cell that can link the two causes of resistance.
Subject(s)
Brain Neoplasms , Glioblastoma , Brain Neoplasms/classification , Brain Neoplasms/diagnosis , Brain Neoplasms/genetics , Brain Neoplasms/therapy , Glioblastoma/classification , Glioblastoma/diagnosis , Glioblastoma/genetics , Glioblastoma/therapy , Humans , Isocitrate Dehydrogenase/genetics , Neoplasm Recurrence, Local , Neoplasms, Second PrimaryABSTRACT
Pediatric tumors are uncommon, yet are the leading cause of cancer-related death in childhood. Tumor types, molecular characteristics, and pathogenesis are unique, often originating from a single genetic driver event. The specific diagnostic challenges of childhood tumors led to the development of the first World Health Organization (WHO) Classification of Pediatric Tumors. The classification is rooted in a multilayered approach, incorporating morphology, IHC, and molecular characteristics. The volume is organized according to organ sites and provides a single, state-of-the-art compendium of pediatric tumor types. A special emphasis was placed on "blastomas," which variably recapitulate the morphologic maturation of organs from which they originate. SIGNIFICANCE: In this review, we briefly summarize the main features and updates of each chapter of the inaugural WHO Classification of Pediatric Tumors, including its rapid transition from a mostly microscopic into a molecularly driven classification systematically taking recent discoveries in pediatric tumor genomics into account.
Subject(s)
Brain Neoplasms/classification , Child , Genomics , Humans , World Health OrganizationABSTRACT
AIMS: Glioneuronal tumours, although rare, are an important cause of treatment-resistant epilepsy. Differential diagnosis of glioneuronal tumour subtypes is complicated by their variable histological appearance and the lack of pathognomonic histological or molecular biomarkers. In this study we have applied techniques available in a diagnostic laboratory setting to characterise molecular and cytogenetic abnormalities in a single institution cohort of glioneuronal tumours. METHODS: A cohort of 29 glioneuronal tumours that included 21 gangliogliomas and 5 dysembryoplastic neuroepithelial tumours (DNETs) was analysed using low pass whole genome sequencing (WGS) and 2 multiplex ligation-dependent probe amplification (MLPA) central nervous system (CNS) tumour probesets. RESULTS: Low pass WGS identified chromosomal or subchromosomal alterations in 15 specimens. The most common chromosomal alterations were gains of chromosome 7 (n = 8) and chromosome 16 (n = 3). The BRAFV600E mutation was detected by MLPA in 9/21 (42.9%) gangliogliomas and 2/2 pleomorphic xanthoastrocytomas (PXAs). Chromosome 7 gains detected by WGS were reflected in MLPAs by overall gains of chromosome 7 gene probes, including those for BRAF, KIAA1549 and EGFR, while an internal BRAF/MKRN1 duplication was detected in a single ganglioglioma. Homozygous CDKN2A/B loss was detected by MLPA in 3 gangliogliomas, with p16 immunohistochemistry supporting these results. CONCLUSIONS: The combination of low pass WGS and MLPA identifies multiple, diverse genetic and chromosomal alterations in glioneuronal tumours, irrespective of histological tumour grade.