Diagnostics for lung cancer in its early stages and therapy monitoring for lung cancer depend heavily on medical imaging technologies. For the purpose of detecting lung cancer, a number of medical imaging modalities, including computed tomography, magnetic resonance imaging, positron emission tomography, chest X-ray, and molecular imaging approaches, have been thoroughly examined. Some of the disadvantages of these systems include their inability to automatically categorize cancer images, making them inappropriate for use in patients with other illnesses. The development of a sensitive and precise method for the early diagnosis of lung cancer is desperately needed. One of the areas of medical imaging that is expanding the fastest is deep learning, with quickly developing applications involving textural and medical image-based data modalities. Medical imaging technologies based on deep learning can help clinicians identify and categorize lung nodules more rapidly and precisely. Consequently, the sophisticated CNN model modifications are implemented in this study for the purpose of detecting lung cancer from chest scan images. The suggested CNN model outperforms the state-of-the-art support vector machine (SVM) classifier in machine learning when it comes to accurately classifying benign and malignant, or normal and cancerous, tissues. Furthermore, the quality metrics obtained reveal the higher performance of the suggested deep CNN model in supporting the experts in an improved diagnosis.