**Abstract:** Lung cancer is the second most common cancer globally, with over two million new cases annually. Early detection is crucial for effective treatment. This paper introduces VER-Net, a novel hybrid transfer learning model designed to detect lung cancer using CT scan images. The model stacks three different transfer learning models (VGG19, EfficientNetB0, and ResNet101) to improve classification accuracy. Various preprocessing techniques, data augmentation, and hyperparameter tuning are employed to enhance the model's performance. Experimental results show that VER-Net outperforms eight other transfer learning models, achieving 91%, 92%, 91%, and 91.3% accuracy, precision, recall, and F1-score, respectively. VER-Net's superior performance suggests its potential for lung cancer detection and other diseases where CT scan images are available. **Keywords:** Lung cancer detection, CT scan, Transfer learning, Image processing, Stacking, VGG19, EfficientNetB0, ResNet101 **Introduction:** Lung cancer is a leading cause of cancer-related deaths, with significant advancements in computer-aided detection systems. Transfer learning has become popular for disease detection due to its advantages in leveraging pre-trained models. This paper proposes VER-Net, a hybrid model that combines the strengths of VGG19, EfficientNetB0, and ResNet101 to enhance lung cancer detection. **Methods:** The dataset consists of 1653 CT images of lung cancers, including Adenocarcinoma, Large cell carcinoma, Squamous cell carcinoma, and normal images. Data preprocessing, including resizing and augmentation, is performed to improve model performance. The models are trained and evaluated using multiclass classifications. **Results:** VER-Net outperforms other transfer learning models in terms of accuracy, precision, recall, and F1-score. It achieves 91% accuracy, 92% precision, 91% recall, and 91.3% F1-score. Compared to state-of-the-art models, VER-Net demonstrates better accuracy. **Conclusion:** VER-Net is effective for lung cancer detection and may also be useful for other diseases where CT scan images are available. The model's performance highlights the potential of transfer learning in medical image analysis. **Keywords:** Lung cancer detection, CT scan, Transfer learning, Image processing, Stacking, VGG19, EfficientNetB0, ResNet101**Abstract:** Lung cancer is the second most common cancer globally, with over two million new cases annually. Early detection is crucial for effective treatment. This paper introduces VER-Net, a novel hybrid transfer learning model designed to detect lung cancer using CT scan images. The model stacks three different transfer learning models (VGG19, EfficientNetB0, and ResNet101) to improve classification accuracy. Various preprocessing techniques, data augmentation, and hyperparameter tuning are employed to enhance the model's performance. Experimental results show that VER-Net outperforms eight other transfer learning models, achieving 91%, 92%, 91%, and 91.3% accuracy, precision, recall, and F1-score, respectively. VER-Net's superior performance suggests its potential for lung cancer detection and other diseases where CT scan images are available. **Keywords:** Lung cancer detection, CT scan, Transfer learning, Image processing, Stacking, VGG19, EfficientNetB0, ResNet101 **Introduction:** Lung cancer is a leading cause of cancer-related deaths, with significant advancements in computer-aided detection systems. Transfer learning has become popular for disease detection due to its advantages in leveraging pre-trained models. This paper proposes VER-Net, a hybrid model that combines the strengths of VGG19, EfficientNetB0, and ResNet101 to enhance lung cancer detection. **Methods:** The dataset consists of 1653 CT images of lung cancers, including Adenocarcinoma, Large cell carcinoma, Squamous cell carcinoma, and normal images. Data preprocessing, including resizing and augmentation, is performed to improve model performance. The models are trained and evaluated using multiclass classifications. **Results:** VER-Net outperforms other transfer learning models in terms of accuracy, precision, recall, and F1-score. It achieves 91% accuracy, 92% precision, 91% recall, and 91.3% F1-score. Compared to state-of-the-art models, VER-Net demonstrates better accuracy. **Conclusion:** VER-Net is effective for lung cancer detection and may also be useful for other diseases where CT scan images are available. The model's performance highlights the potential of transfer learning in medical image analysis. **Keywords:** Lung cancer detection, CT scan, Transfer learning, Image processing, Stacking, VGG19, EfficientNetB0, ResNet101