Lungs Cancer Identification by Deep Learning 3D CNN Architecture

The importance of early lung cancer diagnosis in enhancing patients' life expectancies cannot be overstated. Rapid and correct diagnosis is difficult for radiologists due to the large amount of Computerized Tomography (CT) images. As a result, demand for Computer Aided Diagnosis (CAD) lung cancer is increasing. The distinction between cancerous and non-cancerous tissues lies at the heart of all lung cancer detection systems. Binary categorization (benign and malignant) has been conducted on computed tomography (CT) images from the LUNA 16 database conglomerate and database image resource effort. The data has been pre-processed to remove noise as well as for feature selection. 3D CNN architecture has been used to classification. The 10-fold cross-validation method was applied to verify the results. Experiments revealed that the proposed lightweight architecture achieved an optimum classification accuracy of 90.13% when compared to existing classification algorithms.