Investigation of Deep Learning based methods to Detection, Segmentation and Classification of Lung Nodules
Principal Investigator
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-354
Initial CDAS Request Approval
Sep 20, 2017
Title
Investigation of Deep Learning based methods to Detection, Segmentation and Classification of Lung Nodules
Summary
Lung Cancer is one of the most dangerous types of cancer which makes most of the cancer-related death in men and second most common in women after breast cancer. Early detection and analysis however, could increase the chance to treat and deal with disease in most of the patients. The computer-assisted analysis plays a significant role in the early detection and diagnosis of lung cancer. A conventional computer-aided diagnosis scheme requires several image processing steps to perform a proper analysis, segmentation and classification pipeline. Deep learning, as a new area of machine learning, is recently becoming a state of the art for most of the medical imaging studies. In this study, we develop a deep convolutional neural network (CNN) and apply it to CT images for the detection, segmentation and classification of small lung nodules.
Aims
1. Development of new detection pipeline for small lung nodules using CNN
2. Computer aided segmentation and classification of small nodules
Collaborators
NA