<![CDATA[This research aims to develop a reliable deep learning model for classifying CT-scan images of lung cancer. This research has the advantage of evaluating the performance of several Convolutional Neural Networks (CNN) architectures including DenseNet121, InceptionResNetV2, InceptionV3 and ResNet152V2 to compare their performance in classification accuracy. The dataset consists of 1,561 CT scan images obtained from Kaggle and the dataset is categorized into malignant cancer, benign cancer and normal. Through a combination of innovative data pre-processing techniques, such as augmentation with random rotation and normalization, division of the dataset using the hold-out method with ratios of 70:30, 80:20, and 90:10, and model training using Adam's optimizer and SGDM, researchers achieved very high classification accuracy. The evaluation results showed that InceptionV3 with SGDM optimizer at 90:10 ratio achieved performed very well with an accuracy of 99.38% while InceptionResNetV2 with Adam optimizer at 80:20 hold-out the highest performance, with an accuracy of 99.40%. These promising results indicate great potential in supporting the early discovery of lung cancer, thereby improving the accuracy of diagnosis and the chances of patient recovery. This research opens up opportunities for further development, such as the application of fine-tuning, ensemble learning, or integration with clinical decision support systems for medical applications.]]>
Copyrights © 2025
