Abstract:
Lung cancer is a type of cancer that begins in the cells of the lungs. It is one of the most common
forms of cancer worldwide and is a leading cause of cancer-related deaths. Lung cancer usually
develops in the cells lining the air passages of the lungs.There are two main types of lung cancer:
non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). NSCLC is the most
prevalent, comprising about 85% of all lung cancer cases, while SCLC is generally more
aggressive and tends to spread quickly. The need for early detection is underscored by the fact
that lung cancer symptoms often manifest at advanced stages, limiting treatment options and
reducing the likelihood of successful intervention. This thesis presents a comprehensive study on
the application of six pre-trained convolutional neural network models, namely MobileNetV2,
InceptionV3, ResNet50, VGG16, VGG19, and NASHNetMobile, for the classification of lung
cancer categories. The dataset used in this research consists of 15,000 images, spanning three
distinct classes: Lung Adenocarcinoma, Lung Benign Tissue, and Lung Squamous Cell
Carcinoma. To optimize model performance, hyperparameter tuning is employed using the Keras
Tuner framework. This approach allows for the systematic exploration of hyperparameter
configurations to enhance the models' accuracy and generalization. The hyperparameters include
learning rates, dropout rates, and other key parameters crucial for model training. The results
indicate that MobileNetV2 achieved the highest accuracy among the tested models, with an
impressive 98.47%. Following closely, VGG16 demonstrated the second-best performance,
achieving an accuracy of 98.40%. The study contributes valuable insights into the practical
application of deep learning models for medical image classification tasks, particularly in the
context of lung cancer diagnosis. The reported accuracies demonstrate the potential of leveraging
pre-trained models to enhance the efficiency and accuracy of computer-aided diagnostic systems
for early detection of lung cancer.
