A Multi-Task EfficientNetV2S Approach with Hierarchical Hybrid Attention for MRI Enhancing Brain Tumor Segmentation and Classification

<b>Background:</b> Brain tumors present a significant clinical problem due to high mortality and strong heterogeneity in size, shape, location, and tissue characteristics, complicating reliable MRI analysis. Existing automated methods are limited by non-selective skip connections that propagate noise, axis-separable attention modules that poorly integrate channel and spatial cues, shallow encoders with insufficiently discriminative features, and isolated optimization of segmentation or classification tasks. <b>Methods:</b> We propose a model using an EfficientNetV2S backbone with a Hierarchical Hybrid Attention (HHA) mechanism. The HHA couples a global-context pathway with a local-spatial pathway, employing a correlation-driven, per-pixel fusion gate to explicitly model interactions between them. Multi-scale dilated blocks are incorporated to enlarge the effective receptive field. The model is applied to a multiclass brain tumor MRI dataset, leveraging shared representation learning for joint segmentation and classification. <b>Results:</b> The design attains a Dice score of 92.25% and a Jaccard index of 86% for segmentation. For classification, it achieves an accuracy of 99.53%, with precision, recall, and F1 scores all close to 99%. These results indicate sharper tumor boundaries, stronger noise suppression in segmentation, and more robust discrimination in classification. <b>Conclusions:</b> The proposed framework effectively overcomes key limitations in brain tumor MRI analysis. The integrated HHA mechanism and shared representation learning yield superior segmentation quality with enhanced boundary delineation and noise suppression, alongside highly accurate tumor classification, demonstrating strong clinical utility.