A brain tumor is the result of abnormal growth of cells in the central nervous system (CNS), widely considered as a complex and diverse clinical entity that is difficult to diagnose and cure. In this study, we focus on current advances in medical imaging, particularly magnetic resonance imaging (MRI), and how machine learning (ML) and deep learning (DL) algorithms might be combined with clinical assessments to improve brain tumor diagnosis. Due to its superior contrast resolution and safety compared to other imaging methods, MRI is highlighted as the preferred imaging modality for brain tumors. The challenges related to brain tumor analysis in different processes including detection, segmentation, classification, and survival prediction are addressed along with how ML/DL approaches significantly improve these steps. We systematically analyzed 107 studies (2018–2024) employing ML, DL, and hybrid models across publicly available datasets such as BraTS, TCIA, and Figshare. In the light of recent developments in brain tumor analysis, many algorithms have been proposed to accurately obtain ontological characteristics of tumors, enhancing diagnostic precision and personalized therapeutic strategies.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and the leading cause of dementia worldwide, affecting over 55 million people globally, with numbers expected to rise dramatically. Early detection and classification of AD are crucial for improving patient outcomes and slowing disease progression. However, conventional diagnostic approaches often fail to provide accurate classification in the early stages. This paper proposes a novel approach using advanced computer-aided diagnostic (CAD) systems and the YOLOv11 neural network for early detection and classification of AD. The YOLOv11 model leverages its advanced object detection capabilities to simultaneously localize and classify AD-related biomarkers by integrating multimodal data fusion of T2-weighted MRI and DTI images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Regions of interest (ROIs) were selected and annotated based on known AD biomarkers, and the YOLOv11 model was trained to classify AD into four stages: Cognitively Normal (CN), Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI), and Mild Cognitive Impairment (MCI). The model achieved exceptional performance, with 93.6% precision, 91.6% recall, and 96.7% mAP50, demonstrating its ability to identify subtle biomarkers by combining MRI and DTI modalities. This work highlights the novelty of using YOLOv11 for simultaneous detection and classification, offering a promising strategy for early-stage AD diagnosis and classification.

Computer-aided diagnosis (CAD) systems based on deep learning have shown significant potential for Alzheimer’s disease (AD) stage classification from Magnetic Resonance Imaging (MRI). Nevertheless, challenges such as class imbalance, small sample sizes, and the presence of multiple slices per subject may lead to biased evaluation and statistically unreliable performance, particularly for minority classes. In this study, a Vision Transformer (ViT)-based framework is proposed for multi-class AD classification using a Kaggle dataset containing 6400 MRI slices across four cognitive stages. A subject-wise data-splitting strategy is employed to prevent information leakage between the training and testing sets, and the statistical unreliability of near-perfect scores in underrepresented classes is critically examined. An ablation study is conducted to assess the contribution of key architectural components, demonstrating the effectiveness of self-attention and patch embedding in capturing discriminative features. Furthermore, attention-based visualization maps are incorporated to highlight brain regions influencing the model’s decisions and to illustrate subtle anatomical differences between MildDemented and VeryMildDemented cases. The proposed approach achieves a test accuracy of 97.98%, outperforming existing methods on the same dataset while providing improved interpretability. It supports early and accurate AD stage identification.

The accurate detection and classification of brain tumors from magnetic resonance imaging (MRI) are critical for diagnosis and treatment planning. While deep learning has shown remarkable success in this domain, many state-of-the-art models rely on complex, end-to-end convolutional neural networks (CNNs) that require extensive computational resources and large, annotated datasets for training. This work proposes a novel and efficient methodology that, for the first time, leverages self-supervised DINO vision transformer backbones (DINO v1, DINOv2, and DINOv3) on a large corpus of natural images as powerful feature extractors for brain tumor analysis. We utilize the rich, general-purpose features from DINO-family backbones without fine-tuning the core model. These extracted features are then fed into a simpler, task-specific classifier (such as a support vector machine or a multi-layer perceptron) for the final detection and multi-class classification (e.g., glioma, meningioma, and pituitary tumor). Our methodology is evaluated on two benchmark medical imaging datasets with various classifying granularities. The results demonstrate that the proposed method achieves competitive and, in some cases, superior classification accuracy compared to representative fine-tuned convolutional neural networks and attention-based architectures, while significantly reducing the number of trainable parameters and training time. In particular, the best configuration achieves up to 98.17% accuracy and an F1-score of 98.18% on the 15-class dataset and 99.08% accuracy and an F1-score of 99.02% on the 4-class dataset. This study confirms the exceptional transfer learning capabilities of self-supervised vision transformers like DINO in the medical imaging domain, establishing it as a highly effective and efficient backbone for robust brain tumor detection and classification systems.