The accurate classification of brain tumors is an important step for early intervention. Artificial intelligence (AI)-based diagnostic systems have been utilized in recent years to help automate the process and provide more objective and faster diagnosis. This work introduces an enhanced AI-based architecture for improved brain tumor classification. We introduce a hybrid architecture that integrates vision transformer (ViT) and deep neural networks to create an ensemble classifier, resulting in a more robust brain tumor classification framework. The analysis pipeline begins with preprocessing and data normalization, followed by extracting three types of MRI-derived information-rich features. The latter included higher-order texture and structural feature sets to harness the spatial interactions between image intensities, which were derived using Haralick features and local binary patterns. Additionally, local deeper features of the brain images are extracted using an optimized convolutional neural networks (CNN) architecture. Finally, ViT-derived features are also integrated due to their ability to handle dependencies across larger distances while being less sensitive to data augmentation. The extracted features are then weighted, fused, and fed to a machine learning classifier for the final classification of brain MRIs. The proposed weighted ensemble architecture has been evaluated on publicly available and locally collected brain MRIs of four classes using various metrics. The results showed that leveraging the benefits of individual components of the proposed architecture leads to improved performance using ablation studies.
Accurate brain tumor classification is critical for ensuring timely and effective medical interventions. In recent years, artificial intelligence (AI)-driven diagnostic systems have emerged as transformative tools that optimize the classification process and enable rapid, objective decision-making. However, existing methods often suffer from limitations such as the loss of high-frequency details during multimodal preprocessing, inadequate cross-modal feature alignment, and insufficient focus on shared tumor regions within 3D architectures. To address these challenges, this study introduces a novel AI-based framework for advanced brain tumor classification. Specifically, we propose a multimodal magnetic resonance imaging (MRI) architecture that integrates Diffusion-Weighted MRI (DW-MRI) and T2-weighted MRI (T2-MRI) modalities, uniquely combining them in a dual-branch 3D neural architecture with advanced preprocessing and attention mechanisms. The preprocessing pipeline employs a learnable High-Frequency Information Retention (HFIR) technique to resize T2-MRI images, maintaining consistent spatial dimensions across modalities while preserving essential image details. The architecture utilizes dual-branch 3D convolutional neural networks (CNN) for modality-specific feature extraction, enhanced by a novel Adaptive Region Attention (ARA) module that dynamically aligns and emphasizes highly informative regions shared across modalities, providing deeper and more consistent insights into tumor characteristics. Rigorous evaluation on a dataset of brain MRI scans including three tumor classes demonstrates that the proposed framework achieves overall accuracy, sensitivity, and specificity of 92.86%, 80.00%, and 94.12%, respectively. Statistical analyses using bootstrap-resampled F1-scores confirm significant outperformance over other state-of-the-art models, underscoring its robust and interpretable potential for precise brain tumor diagnosis.
The overall purpose of this paper is to demonstrate how data preprocessing, training size variation, and subsampling can dynamically change the performance metrics of imbalanced text classification. The methodology encompasses using two different supervised learning classification approaches of feature engineering and data preprocessing with the use of five machine learning classifiers, five imbalanced sampling techniques, specified intervals of training and subsampling sizes, statistical analysis using R and tidyverse on a dataset of 1000 portable document format files divided into five labels from the World Health Organization Coronavirus Research Downloadable Articles of COVID-19 papers and PubMed Central databases of non-COVID-19 papers for binary classification that affects the performance metrics of precision, recall, receiver operating characteristic area under the curve, and accuracy. One approach that involves labeling rows of sentences based on regular expressions significantly improved the performance of imbalanced sampling techniques verified by performing statistical analysis using a t-test documenting performance metrics of iterations versus another approach that automatically labels the sentences based on how the documents are organized into positive and negative classes. The study demonstrates the effectiveness of ML classifiers and sampling techniques in text classification datasets, with different performance levels and class imbalance issues observed in manual and automatic methods of data processing.