Detection of Lung Nodules in Computed Tomography Image using Deep Machine Learning: A Review
12 Pages Posted: 17 Jul 2019 Last revised: 30 Sep 2019
Date Written: May 18, 2019
Abstract
Lung Nodules detection is very critical in detection of early stage lung cancer. A radiologist tries to diagnoses the clinical chest computed tomography (CT) scans by detecting lung nodules in them. This task is rigorous and becomes even more difficult due to the complex structure and anatomy of lung parenchyma region. To assist radiologists in correct diagnosis of CT scan images, many Computer-aided detection (CAD) algorithms were developed and proposed. After the success of deep convolutional neural network (D-CNN) for classification of images, D-CNN has found its way into lung nodules detection systems. D-CNN has demonstrated better results and performances than traditional machine learning based lung nodules detection algorithms. In this paper, we will discuss about different D-CNN proposed for lung nodules detection and compare the results and performances of these detection algorithms. We will also discuss about the D-CNN which can be used to further improve the results of lung nodules detection.
Keywords: Lung Nodules, Convolutional Neural Network, Nodules detection, Classification, False positive reduction
JEL Classification: Y60
Suggested Citation: Suggested Citation