Lung cancer remains one of the leading causes of cancer-related deaths worldwide, underscoring the urgent need for effective diagnostic tools. This study uses deep transfer learning methods to detect lung cancer in histopathological images. Pre-trained convolutional neural networks (CNNs)—EfficientNetB7, InceptionV3, and ResNet50—were utilized to evaluate their feature extraction and classification performance. Pre-trained convolutional neural networks (CNNs) were employed for feature extraction, and the resulting features were classified using a support vector machine (SVM) on a publicly available dataset containing histopathological images of normal cells, adenocarcinoma, and squamous cell carcinoma. Additionally, a support vector machine (SVM) classifier was integrated to enhance classification accuracy, achieving up to 100% results. A user-friendly interface was also developed to facilitate result interpretation and visualization. The findings underscore the effectiveness of transfer learning and CNNs in medical imaging, presenting a robust approach for improving lung cancer diagnosis.