Classification of Lung Cancer with Deep Learning Res-U-Net and Molecular Imaging

Abstract

Abstract Lung cancer is the prevalent malignancy, despite the great breakthroughs in detection and prevention and it remains the important cause of death. In recent days, artificial intelligence has exploded in all fields of science. The use of artificial intelligence in medical science has improved in accuracy and precision of predicting this infestation in the initial stages. In the proposed study a deep learning and molecular imaging is used for classifying two different types of lung cancer. The PET/CT (positron emission tomography/computed tomography) employing an injection 18F-FDG has developed as a useful tool in therapeutic oncologic imaging for both metabolic and anatomic analysis. The proposed model uses Res-U-Net to classify small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC) from normal by using 18F-FDG PET/CT images from the radiogenmics dataset. This datasets are pre-processed by Gaussian smoothing to reduce the noise from the PET/CT images. Finally, the classification result is obtained through the support vector machine (SVM) classifier which proves the efficiency of the proposed technique. The outcome of the proposed technique yields best and accurate results and it yields the classification accuracy rate of 96.45%for lung cancer into NSCLC and SCLC.