Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Automatic Lung Lesion Detection and Classification in CT

Principal Investigator
Name
Sasa Grbic
Degrees
Ph.D.
Institution
Siemens Medical Solutions USA, Inc.
Position Title
Staff Scientist
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-108
Initial CDAS Request Approval
Jan 8, 2015
Title
Automatic Lung Lesion Detection and Classification in CT
Summary
Previously, we developed an efficient lung segmentation method from CT data, which can accurately segment the lungs in a few seconds. In this project, we will develop an automatic lung lesion detection algorithm using machine learning. Constraining the lesion detection to the segmented lung region will help to reduce the false positive rate. We will investigate various image features and classifiers (including deep learning) to achieve the best detection accuracy. After lung lesion detection, we will develop an algorithm for automatic lesion type classification using image/texture features.
Aims

1. Develop an automatic lung lesion detection algorithm
2. Develop a lung lesion classification algorithm
3. Quantitative evaluation of the developed algorithms on a large dataset (e.g., the NLST data)