This study reviews the application of deep learning techniques, particularly Deep Convolutional Neural Networks (DCNN), in the diagnosis and classification of lung cancer. The research covers a comprehensive Systematic Literature Review (SLR) of medical imaging modalities such as X-rays, Whole Slide Imaging (WSI), CT scans, and MRI, focusing on the years 2015–2024. The study highlights the importance of early detection in improving prognosis and treatment outcomes for lung cancer, which is the deadliest form of cancer. Deep learning methods, especially Convolutional Neural Networks (CNN), are shown to be highly effective in automating the diagnosis and classification of lung cancer images. CNNs achieve maximum accuracy due to their multi-layer structure, automatic weight learning, and ability to capture local features. The review presents performance measures such as precision, accuracy, specificity, sensitivity, and AUC, with CNN consistently demonstrating the highest accuracy. The findings underscore the significant contributions of DCNNs in enhancing lung cancer detection and classification, making them valuable tools for researchers in medical applications.This study reviews the application of deep learning techniques, particularly Deep Convolutional Neural Networks (DCNN), in the diagnosis and classification of lung cancer. The research covers a comprehensive Systematic Literature Review (SLR) of medical imaging modalities such as X-rays, Whole Slide Imaging (WSI), CT scans, and MRI, focusing on the years 2015–2024. The study highlights the importance of early detection in improving prognosis and treatment outcomes for lung cancer, which is the deadliest form of cancer. Deep learning methods, especially Convolutional Neural Networks (CNN), are shown to be highly effective in automating the diagnosis and classification of lung cancer images. CNNs achieve maximum accuracy due to their multi-layer structure, automatic weight learning, and ability to capture local features. The review presents performance measures such as precision, accuracy, specificity, sensitivity, and AUC, with CNN consistently demonstrating the highest accuracy. The findings underscore the significant contributions of DCNNs in enhancing lung cancer detection and classification, making them valuable tools for researchers in medical applications.