Main Article Content
Abstract
In this paper, deep learning methods for lung cancer detection are discussed. Lung cancer is one of the most common types of cancer which is responsible of millions of death over the years. Early and correct diagnosis will help the patient to overcome the disease timely. Medical imaging is assisting the radiologists and physicians to diagnose this kind of cancer. Computer aided diagnosis is also playing its part with an objective of better and accurate results. Major objective of this paper is to provide the current trends in relation to deep learning architectures such as (CNN) Convolution Neural Networks (2D and 3D), R-CNN (Region based convolution neural network), DBF (Deep Belief networks), DNN (Deep neural networks), VGG-16 CNN, U-net Convolution Networks, SDAE(Stacked De-noising Autoencoders) etc. This paper provides a short review considering the research trends from the last five years, i.e. 2015-2019. Tabular view of datasets, sample sizes and success rates are also demonstrated in the latter half of the paper for better understanding of the latest computational methods.