Lung Cancer Classification from Chest CT Scans Using EfficientNet

Lung cancer is the leading cause of cancer-related deaths, and early detection is critical for improving survival.This study presents an explainable deep learning approach for classifying chest CT scans into normal, benign, and malignant categories.Six pretrained convolutional neural networks were evaluated on the public IQ-OTH/NCCD dataset using class-weighted training and light data augmentation.EfficientNet-B0 achieved the best performance, with 99.39% accuracy, a 0.988 macro F1score, and 0.996 AUC, while correctly identifying all malignant cases.