DCV: A Taxonomy on Deep Learning Based Lung Cancer Classification

Abstract

Deep learning based on lung cancer classification has been used increasingly for the early diagnosis for several reasons such as lack of robust deep learning-based system, complexity of nodule structure, lack of proper lung segmentation technique, high false positive result, lack of best feature extraction and less amount of medical imaging data for training deep learning model, it has been difficult to get high classification performance. The aim of this paper getting high lung cancer classification performance. We introduce the Data, Classification technique and View (DCV) as main components of the system that concern for the better lung cancer classification results, along with them different intermediate components such as Lung nodule segmentation, Feature extraction, Feature reduction are also defined. These components are key for providing better classification performance result which helps radiologist for early diagnosis of lung cancer. We have proposed uses image data having different dimensionality as input to the deep learning based classifier which provides lung cancer classification to be viewed by radiologists for the early diagnosis of lung cancer.We evaluated the proposed DCV system by classifying 30 state-of-art research papers in the field of deep learning based lung cancer classification system. Through this paper, readers will get the result of deep learning based lung cancer classification system. Also, readers will understand the classification groups, validation criteria, future gaps of the 30 literature.