Lung Cancer Classification Using CNN and Random Forest

Lung cancer is one of the leading causes of cancer-related mortality worldwide. Early detection of lung cancer is crucial for improving survival rates and enabling more effective treatment options. However, manually detecting and classifying various forms of lung cancers is time-consuming and can be inaccurate. Traditional classification methods rely on manual feature extraction, necessitating the experimenter's expertise and professional knowledge. This research introduces a streamlined feature selection method using a deep convolutional neural network (CNN) to effectively tackle the issue. The aim of this proposed lightweight deep CNN is to enhance accuracy while reducing the number of parameters. The established approach involves three key stages: pre-processing, feature extraction, and classification. In the pre-processing phase, K-fold cross-validation ensures robust classification, complemented by data augmentation to augment the image dataset. In the feature extraction stage, modified CNNs effectively extract pertinent features, followed by Random Forest (RF) utilization to distinguish various forms of lung cancer from CT scan images. The proposed Deep CNN-RF model demonstrates effective detection and classification of various types of lung cancer, achieving an impressive accuracy rate of 97.1%.