A Comparative Analysis of Deep Learning Architectures for Classifying Malignant Lung Nodules in CT Scans

Lung cancer remains a leading cause of cancer mortality worldwide, underscoring the need for improved early detection methods. While deep learning models, particularly Convolutional Neural Networks (CNNs), have shown promise in analyzing low-dose computed tomography (LDCT) scans for pulmonary nodule classification, a comparative analysis of modern CNN architectures for this specific task is limited. This study aims to conduct a rigorous head-to-head evaluation of ResNet, DenseNet, and EfficientNet for benign-malignant classification of lung nodules. Using the publicly available LIDC-IDRI dataset of thoracic CT scans, we developed a deep learning pipeline for binary nodule classification. The dataset was preprocessed, and 8,420 annotated nodule patches were extracted and augmented. Three CNN architectures—ResNet50, DenseNet121, and EfficientNetB0—were initialized with ImageNet pre-trained weights and fine-tuned. Model performance was evaluated on a held-out test set using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC). Interpretability was assessed using Grad-CAM visualizations. DenseNet121 achieved the highest performance with an accuracy of 95.6% and an AUC of 0.982, demonstrating a superior balance of sensitivity and specificity and producing the fewest false negatives. EfficientNetB0 followed closely (AUC: 0.976) with the shortest training time, while ResNet50 was a strong but slightly less sensitive baseline (AUC: 0.964). Grad-CAM analysis confirmed that all models focused on relevant nodule regions, with DenseNet and EfficientNet exhibiting more localized activations. This study demonstrates that architectural choice significantly impacts performance in lung nodule malignancy classification. DenseNet emerged as the most effective backbone for this task, offering high discriminatory power and critical sensitivity to malignant cases.