Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images

Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for...

Full description

Saved in:
Bibliographic Details
Published in:Computational and mathematical methods in medicine 2016-01, Vol.2016 (2016), p.1-7
Main Authors: Wang, Junbo, Zhao, Dazhe, Cao, Peng, Li, Wei
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computer Graphics
Databases, Factual
False Positive Reactions
Humans
Image Processing, Computer-Assisted
Lung Neoplasms - diagnostic imaging
Neural Networks (Computer)
Pattern Recognition, Automated - methods
Radiographic Image Enhancement - methods
Radiographic Image Interpretation, Computer-Assisted - methods
Reproducibility of Results
Sensitivity and Specificity
Solitary Pulmonary Nodule - diagnostic imaging
Tomography, X-Ray Computed
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.
ISSN:1748-670X
1748-6718
DOI:10.1155/2016/6215085