Jul 2026· International journal of computer information systems and industrial management applications· 0 citations
TL;DR
The proposed approach advances hybrid medical image analysis by introducing statistically validated, stability-oriented, and deployment-aware adaptive feature-level integration, providing a reproducible foundation for interpretable and robust neuro-diagnostic intelligence.
Abstract
Accurate brain tumor classification from magnetic resonance imaging requires models capable of capturing both structural complexity and subtle radiomic heterogeneity within lesion regions. Handcrafted radiomic approaches offer interpretability but lack hierarchical spatial abstraction, whereas deep convolutional networks, despite strong predictive capability, may overlook complementary statistical descriptors. This study proposes an Adaptive Hybrid Feature Fusion framework that integrates convolutional embeddings and handcrafted radiomic features through an instance-aware dynamic weighting mechanism. Radiomic descriptors derived from Gray-Level Co-occurrence Matrix statistics and histogram-based measures are combined with deep convolutional representations via a learned adaptive coefficient that regulates feature dominance prior to classification. The framework is evaluated on a publicly available multi-class MRI dataset using a standardized validation protocol. Experimental results demonstrate that adaptive fusion achieves 91.42% classification accuracy, outperforming standalone convolutional models by 2.85%, with statistically significant improvement (p = 0.012) and reduced cross-validation variance. Interpretability is incorporated through Grad-CAM to verify spatial alignment between predictive attention and tumor regions. The proposed approach advances hybrid medical image analysis by introducing statistically validated, stability-oriented, and deployment-aware adaptive feature-level integration, providing a reproducible foundation for interpretable and robust neuro-diagnostic intelligence.
Magnetic resonance imaging is widely used for the examination of brain abnormalities because it provides detailed soft-tissue information without ionizing radiation. Nevertheless, manual interpretation of large numbers of MRI slices is time-consuming and may be affected by inter-observer variation. This paper presents a structured deep learning framework for multi-class brain tumor classification using the EfficientNet family of convolutional neural networks. The framework emphasizes consistent preprocessing, transfer learning, class-balanced augmentation, careful validation, and clinically meaningful performance reporting. Rather than treating classification as an isolated model-training task, the proposed approach connects data quality, model calibration, error analysis, and reproducibility. The paper also explains why EfficientNet is suitable for medical image classification: its compound scaling strategy balances network depth, width, and input resolution, enabling strong feature learning with comparatively efficient computation. A complete experimental protocol is described for separating training, validation, and test data at the patient level; controlling information leakage; selecting evaluation metrics; and comparing EfficientNet variants with conventional convolutional baselines. The resulting framework can support reliable thesis-level experimentation and can later be extended with visual explanation methods such as Grad-CAM. The study concludes that model efficiency alone is insufficient; dependable brain tumor classification requires disciplined data handling, transparent reporting, and external validation.
Ajay Khatri, Sanmati Jain· International Journal of Eng...· 0 citations
BACKGROUND AND OBJECTIVE
Explainable artificial intelligence is essential for clinical adoption of deep learning models in prostate magnetic resonance imaging. Although ensemble learning can improve robustness, its impact on explanation stability, spatial consistency, and clinical interpretability remains insufficiently quantified. This study aims to evaluate post-hoc interpretability methods across both single-model and ensemble configurations, and to examine whether ensemble-based explanations provide more reliable and clinically meaningful insights than single-model explanations. Critically, this work treats interpretability as a measurable property rather than a purely qualitative visualization.
METHODS
Convolutional neural networks and bagging-based ensemble models (five VGG16-based classifiers trained on bootstrap samples with replacement, aggregated by soft averaging) were trained on the public PROSTATEx dataset using T2-weighted and apparent diffusion coefficient images. Visual explanations were generated using Gradient-weighted Class Activation Mapping (Grad-CAM) and saliency maps. Lesion localization was evaluated using centroid distance and Dice similarity coefficient with expert-annotated lesion masks. An agreement metric was introduced to quantify spatial consistency between attribution methods and its relationship with prediction reliability.
RESULTS
The baseline classifier achieved an area under the curve of 0.84, with sensitivity of 0.81 and specificity of 0.86. Grad-CAM localized lesion centroids with higher precision on T2-weighted images (mean error 6.93 pixels) than apparent diffusion coefficient images (mean error 16.3 pixels). Combining saliency maps and Grad-CAM improved the mean Dice score from 0.42/0.45 (individual methods) to 0.52. Ensemble-based explanations were significantly smoother and less variable than individual classifier explanations (Mann-Whitney U, Levene test, all p<0.001). The agreement metric strongly separated correctly and incorrectly classified cases (Mann-Whitney U=84.5, p<0.001; point-biserial r=0.749; ROC-AUC =0.960).
CONCLUSIONS
These findings suggest that interpretability quality can be quantitatively assessed and improved through multi-method and ensemble-based analysis. The proposed agreement-driven framework enhances explanation robustness and supports reliable and transparent clinical decision support for prostate magnetic resonance imaging.
M. Gulum, M. Kantardzic, Christopher M. Trombley et al.· Computer Methods and Program...· 0 citations
Brain tumor (BT) classification plays a vital role in computer-aided diagnosis, as early detection directly influences treatment planning and patient survival. Advances in artificial intelligence, particularly in machine learning (ML) and deep learning (DL), have greatly improved automated tumor identification from magnetic resonance imaging (MRI), reducing reliance on manual assessment. This study proposes a hybrid framework that combines generative adversarial networks (GANs), convolutional neural networks (CNNs), and Vision Transformers (ViTs) for accurate tumor classification. GANs are used to generate realistic synthetic MRI images, addressing data scarcity and increasing dataset diversity. CNNs extract discriminative deep features, accelerating training while limiting overfitting. These features are then processed by a ViT model, capable of capturing complex spatial relationships within medical images. Experimental results show that the proposed ViT–CNN–GAN approach achieves 97.36% accuracy, outperforming conventional methods. Overall, this framework demonstrates the potential of advanced DL models to strengthen MRI-based tumor diagnosis and support more reliable clinical decision-making.
Iliass Zine-dine, J. Riffi, Khalid El Fazazy et al.· International Journal of Onl...· 0 citations
An explainable artificial intelligence framework for brain tumor classification using Gradient-weighted Class Activation Mapping (Grad-CAM), which 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.
Ajay Khatri, Sanmati Jain· International Journal of Eng...· 0 citations
Brain tumors represent a significant clinical challenge, with accurate classification being essential for treatment planning. Current deep learning approaches face two critical limitations: insufficient robust-ness across diverse imaging conditions and lack of clinical interpretability. Here we present an ensemble deep learning framework integrating three complementary architectures (MobileNetV2, EfficientNetB3, and DenseNet121) with spatial attention mechanisms and explainability features. Using 7,023 MRI images across four diagnostic categories (glioma, meningioma, pituitary tumor, and tumor-absent), our approach achieved 98.47% classification accuracy with balanced performance across all classes (F1-scores: 98.12% for glioma, 97.89% for meningioma, 98.76% for pituitary, 99.21% for tumor-absent cases). The ensemble demonstrated statistically significant improvement over individual models (p < 0.01, McNemar’s test), with gains of 1.24-1.75 percentage points. Integration of Gradient-weighted Class Activation Map-ping provided interpretable visual explanations with activation patterns consistently focusing on tumor regions. The findings demonstrate the potential of combining ensemble learning, attention, and visual explanation for brain tumor classification. However, the results represent internal validation on a single partition of aggregated public datasets and require confirmation through repeated validation and independent clinical evaluation.
Unknown authors· International Journal of Eng...· 0 citations