An Investigation on CNN-based Lung Cancer Prediction Method

Diagnosis of any disease is done only after detection of the type and intensity of the disease. Chronic pulmonary disease such as Chronic Obstructive Pulmonary Disease (COPD), lung cancer, and cystic fibrosis needs to be detected in the initial stages to get proper treatment. However, early diagnosis of cancer in the case of lungs is not very easy due to the presence of no recognizable symptoms until much more adverse situations. The proposed work aims at detecting the lung cancer using the Convolutional Neural Network (CNN) regarding the dataset compiled from Kaggle Domain. Various parameters are used to determine the performance of the proposed method, namely, precision, recall and F1-score. Experimental results concluded that, the proposed CNN-based lung cancer detection approach resulted in significantly improved performance when compared to few existing methods. The proposed method has 94% of average precision, 93.6% of recall and 94.6% of F1-score, respectively.