Aug 2026· International Journal for Research in Applied Science and Engineering Technology· 0 citations
TL;DR
NeuroCAM-X is presented, a novel explainable hybrid artificial intelligence framework that integrates deep learning-based MRI image analysis with Optical Character Recognition-enabled clinical report interpretation for comprehensive brain tumor diagnosis and addresses critical gaps in medical AI.
Abstract
Brain tumor classification from Magnetic Resonance Imaging (MRI) is a critical task in medical diagnostics that
demands both high accuracy and clinical interpretability. This research presents NeuroCAM-X, a novel explainable hybrid
artificial intelligence framework that integrates deep learning-based MRI image analysis with Optical Character Recognition
(OCR)-enabled clinical report interpretation for comprehensive brain tumor diagnosis. The system employs an EfficientNet-B0
architecture achieving 97.0% classification accuracy on a dataset of 7,023 MRI images. Unlike conventional approaches that
rely solely on imaging data, NeuroCAM-X implements a hybrid decision engine that cross-validates MRI predictions with OCRextracted clinical findings, achieving an 87.5% agreement rate for diagnostic consistency. The framework incorporates multiple
Explainable AI (XAI) techniques—Grad-CAM, SHAP, and LIME—to provide complementary visual interpretations of model
predictions with 94.3% alignment to expert-identified tumor regions. In addition, the system includes automated tumor analytics
for quantitative assessment and staging to support clinical decision-making. A production-ready web application provides patient
management, interactive diagnostic visualization, and automated report generation. Preliminary clinical evaluation
demonstrated high physician trust (4.2/5.0) and satisfaction (4.4/5.0), indicating the framework's potential for clinical
deployment. This work addresses critical gaps in medical AI by combining accurate classification, multimodal data integration,
explainable AI, quantitative analytics, and clinical decision support within a unified framework suitable for real-world
healthcare applications
Brain tumors are abnormal cell growths in the brain that require accurate and timely diagnosis, where Magnetic Resonance Imaging (MRI) plays a critical role in detecting and characterizing tumor structures. However, accurate interpretation of Magnetic Resonance Imaging (MRI) scans is challenging due to their complexity and the limited availability of expert radiologists. This challenge is further compounded by the lack of interpretability in many existing deep learning-based diagnostic systems. Therefore, the need for an automated and interpretable brain tumor classification system arises, which is the problem this study aims to address. In this research, a brain tumor classification system integrated with Explainable Artificial Intelligence (XAI) was developed using MRI images. The model was designed to classify brain tumors into glioma, meningioma, pituitary tumor, and no-tumor categories while providing visual explanations for its predictions using Grad-Class Activation Mapping (Grad-CAM). The performance of the system was evaluated for each tumor category using accuracy, precision, specificity, recall, F1-Score, false positive rate and also the Receiver Operating Characteristic and Area Under Curve (ROC-AUC). Experimental results show that the developed CNN model achieved an overall classification accuracy of 90.6% with an AUC-ROC value of 0.9892, indicating strong discriminative capability across tumor classes. The Grad-CAM visualizations consistently highlighted tumor-affected regions in the MRI images, confirming that the model based its predictions on clinically relevant anatomical structures. The developed model demonstrated effective classification performance and improved interpretability, making it suitable as a reliable decision-support tool for automated brain tumor diagnosis
T. H. Stephen, A. Oke, A. S. Falohun et al.· LAUTECH Journal of Engineeri...· 0 citations
Brain tumors represent one of the most life-threatening diseases, and their early and accurate detection is critical for improving patient outcomes. Magnetic Resonance Imaging (MRI) is the most reliable imaging technique for identifying brain tumors, yet manual interpretation by radiologists is time-consuming and prone to errors. To address these challenges, this study investigates the application of deep learning architectures, including Convolutional Neural Network (CNN), VGG16, VGG19, ResNet50, and MobileNet, for brain tumor detection and classification. A publicly available MRI dataset consisting of glioma, meningioma, pituitary, and no-tumor cases was used. The models were trained and evaluated using accuracy, precision, recall, F1-score, ROC curves, and confusion matrices, while interpretability was assessed using Local Interpretable Model-Agnostic Explanations (LIME). Experimental results demonstrate that ResNet50 achieved the highest performance with 96.9% accuracy, followed closely by MobileNet at 96.6%, whereas CNN performed less effectively at 87.9%. The findings confirm that advanced deep learning architectures not only achieve high classification accuracy but also improve interpretability, thereby offering reliable and clinically applicable solutions for automated brain tumor diagnosis.
H. Uzel, Feyyaz Alpsalaz, Yıldırım Özüpak et al.· Computers and Electronics in...· 0 citations
OBJECTIVE
Accurate classification of brain tumors is of utmost importance in early diagnosis and treatment, which can be further enhanced through advanced deep learning techniques. This work introduces HyPerNet-a Hybrid Perception Network for brain tumor classification that integrates cutting-edge methods to maximize classification accuracy, interpretability, and efficiency. HyPerNet leverages multi-modal fusion, combining Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and Positron Emission Tomography (PET) scans to extract complementary information from different imaging modalities.
METHODS
A dynamic attention mechanism adapts to image complexity, improving performance under noisy and artifact-laden conditions. The architecture incorporates explainable AI components using Grad-CAM for clinical interpretability, along with 3D convolutional neural networks for volumetric feature learning. Hybrid feature extraction, integrating Convolutional Neural Networks (CNNs) with graph neural networks (GNNs), enables the model to capture both local and relational tumor characteristics. Domain adaptation via transfer learning allows the model to generalize across diverse datasets, improving robustness.
RESULT
In experiments conducted on a benchmark dataset of 8,256 images, HyPerNet achieved a classification accuracy of 97.14%, precision of 97.09%, recall of 97.09%, F1-score of 97.09%, and specificity of 98.9%, outperforming state-of-the-art models such as DenseNet121, ResNet101, and MobileNetV3. Notably, HyPerNet attains these results with only 1.66 million parameters, making it highly efficient for deployment on mobile and edge devices.
CONCLUSION
These findings establish HyPerNet as a reliable, interpretable, and computationally efficient solution for clinical brain tumor classification.
Hamad D Al-Sharari· Asian Pacific Journal of Can...· 0 citations
Brain tumors require accurate and early diagnosis to support effective treatment decisions. Magnetic Resonance Imaging (MRI) is widely used for brain tumor assessment; however, many deep learning-based approaches remain black-box systems with limited clinical interpretability. This study proposes Explainable Artificial Intelligence Vision Transformer (XAIViT), a hybrid Convolutional Neural Network (CNN)–Transformer architecture designed to improve both classification performance and model interpretability for four-class brain tumor classification. The proposed framework integrates EfficientNet-B3 as a convolutional feature extractor with a Transformer Encoder to capture global contextual information through self-attention mechanisms. Experiments were conducted using the Brain Tumor MRI Dataset from Kaggle, which consists of 7023 MRI images across four classes: glioma, meningioma, pituitary, and no-tumor. Data preprocessing included intensity normalization, data augmentation, stratified dataset splitting, and early stopping strategies during training. The proposed XAIViT framework achieved a classification accuracy of 99.24%, with macro-average precision, recall, and F1-score values exceeding 0.99 on the test dataset. Furthermore, Gradient-weighted Class Activation Mapping (Grad-CAM)-based visual explanations demonstrated that the model consistently focused on anatomically relevant tumor regions, thereby improving transparency and trustworthiness. These findings indicate that the proposed XAIViT framework has strong potential as an Explainable Artificial Intelligence (XAI)-based clinical decision support system for MRI-based brain tumor analysis.
Diagnosis of brain tumor is one of the most critical tasks in medical imaging and early and accurate diagnosis is extremely important for improving the treatment planning and outcome of patients with brain tumors. Brain tumor assessment is achieved with Magnetic Resonance Imaging (MRI), which is commonly used, but manual interpretation of MRI scans can be time-consuming and subject to inter-observer variability. To overcome these difficulties, an explainable deep learning (XDL) framework is proposed that classifies brain tumors into a multiclass classification problem using magnetic resonance imaging (MRI) images. To overcome these challenges, this study proposes an explainable deep learning (XDL) framework that is capable of brain tumor classification as a multiclass classification problem from MRI images. Five state-of-the-art deep learning architectures ResNet50, VGG16, DenseNet121, Vision Transformer (ViT), and a Hybrid CNN ViT model, were tested and compared to determine which one would be the best fit for the classification task. Preprocessing and augmentation of MRI images were performed before training and evaluation the model. Metrics used to evaluate the performance included accuracy, precision, recall, F1 score, the confusion matrix, and Receiver Operating Characteristic Area Under Curve (ROC-AUC). The Hybrid CNN–ViT framework was compared and it was found that the hybrid approach, combining the advantages of CNN for feature extraction and transformer for contextual learning, led to better classification performance. Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME) were used to explain the best-performing model to improve the transparency and interpretability of the model. To validate that the model attended to clinically relevant tumour regions in classification, the explainability results were obtained. The proposed framework showed high classification accuracy of 98.68% and an average of ROC-AUC score at approximately 0.999, indicating that the framework has good predictive power and high interpretability. The results indicate that the proposed explainable deep learning framework shows great promise of helping clinical diagnosis of brain tumors to be reliable and transparent, by integrating with AI.
Mohd. Yousuf, Joy Chowdhury, Susmoy Chowdhury et al.· American Journal of Applied...· 0 citations
Deep neural networks can classify brain MRI images with high predictive capability, yet their internal decision processes are difficult to interpret. This limitation is especially important in medical imaging, where a prediction should be supported by evidence that can be examined by clinicians and researchers. This paper presents an explainable artificial intelligence framework for brain tumor classification using Gradient-weighted Class Activation Mapping (Grad-CAM). The proposed framework generates class-specific heatmaps from a trained convolutional network and overlays them on MRI images to show the regions that most strongly influence a prediction. The paper explains the mathematical intuition of Grad-CAM, provides a step-by-step implementation and validation protocol, and distinguishes visually attractive heatmaps from clinically meaningful explanations. Particular attention is given to layer selection, normalization, faithfulness, localization quality, uncertainty, and expert review. The framework also identifies common failure modes, including attention to text markers, skull boundaries, background artifacts, or preprocessing traces. A structured reporting checklist is proposed so that explanation results are assessed alongside classification performance. The paper concludes that Grad-CAM can improve transparency and error analysis, but it should be treated as supporting evidence rather than proof of causal reasoning or clinical correctness.
Ajay Khatri, Sanmati Jain· International Journal of Eng...· 0 citations
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
