Hybrid ResNet-ViT Model for Lung Cancer Classification from Histopathology Images

Lung cancer remains one of the leading causes of cancer-related deaths globally. This study proposes a hybrid deep learning model that classifies lung cancer from histopathological images using Residual Networks (ResNet) and Vision Transformers (ViTs). The model uses ResNet for local feature extraction and ViT for global dependencies on the LC25000 dataset, which contains images of adenocarcinoma, benign tissue, and squamous cell carcinoma. The model achieved 99.31% classification accuracy after 10 epochs of training. Diagnostic precision and recall improved significantly, suggesting real-time clinical uses. Future work will explore model optimization, the inclusion of more lung disorders, and the development of multimodal data systems to further enhance diagnostic performance.