Deep Learning Methods for Lung Cancer Detection, Classification and Prediction - A Review

Abstract

Lung cancer is the most common cancer that is fatal if treated late. If the disease could be found at an earlier stage before it's severity, it is more likely to be treated and diagnosed successfully. The presence of lung cancers can be detected from computed tomography and chest x-ray images by locating enlarged lymph nodes. The spread of disease around these nodes can be identified by characterizing size, shape and location; thus, assist doctors in detecting lung cancers at early stages. In many cases, the lung cancer diagnosis is based on doctors' experience, which might lead to misdiagnosis and cause medical issues in patients. There have been numerous strategies and methods for predicting level of cancer malignancy using deep learning and machine learning methods. In this paper, we have studied different Deep Learning methods used for the detection, classification and prediction of cancerous lung nodules and the identification of their malignancy levels. We have analyzed the advantages and limitations of each method along with various datasets used and they are summarized.