Hybrid CNN Transformer Ensemble Model

Hybrid Transformer Ensemble Model integrates the beneficial effect of synergy of ResNet50V2, DenseNet121 and MobileNetV2 within a unified transformer-based framework, as observed in image 7. The three CNN backbones are used simultaneously as independent feature extractors, and each of them ends with a Global Average Pooling layer to give compact one-dimensional features. Dense layers are used to project the vectors into the common dimensions space and then combine them together to form a single feature stack. This is followed by layer normalization, and then a multi-head mechanism of self-attention is applied, which detects the relationship between heterogenous features and underlines its contextual importance. The Residual connections and two layer feed-forward net (Dense-512 → Dropout-0.3 → Dense-256) are used to refine the learnt embeddings to gain more stability and better feature generalisation. The transformer enhanced representation is applied to the pooled CNNs to preserve the original discriminative information in them and to incorporate contextually enriched features. The joint embedding is processesed using two additional layers (Dense layers density of 256 each, separated by Dropout-0.5 layers) before it reaches the final softmax classification head assigning probability of fatty liver, cirrhosis, and HCC. The hybrid ensemble gives a more detailed and robust analysis of liver CT images, both in terms of multi-scale CNN features and the ability of the transformer to encode inter-feature relationships, outperforming the performance of backbones or independent transformer-enhanced models.