Tumennast Erdenebold

NeuroTrustNet: a cost-effective multimodal ensemble framework for brain tumor classification under cross-dataset variability

The proposed NeuroTrustNet is an integrated multimodal framework that combines complementary convolutional neural network, Vision Transformer, and handcrafted radiomic representations through the proposed Adaptive Attention Stacking mechanism, enabling sample-specific feature fusion to improve robustness under cross-da...