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.

New Machine Learning Methods for Lung Nodule Detection and Classification to Optimize Cancer Screening

Principal Investigator
Name
Maxine Tan
Degrees
Ph.D.
Institution
Monash University Malaysia
Position Title
Lecturer
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-522
Initial CDAS Request Approval
Jun 13, 2019
Title
New Machine Learning Methods for Lung Nodule Detection and Classification to Optimize Cancer Screening
Summary
Lung cancer is the leading cause of cancer death in many countries including the United States. We would like to download the NLST dataset to develop new deep learning and machine learning methods to improve the accuracy of lung nodule detection and classification schemes on computed tomography (CT) images. The current conventional computer aided diagnosis (CAD) schemes produce too many false positives that are distracting to radiologists. Our team aims to develop new methods that improve the accuracy of current CAD schemes for lung cancer classification, detection, and risk prediction whilst reducing the false positive rate.
Aims

1. To develop accurate lung nodule classification schemes that correctly classify lung nodules as benign or malignant at low false positive rates
2. To develop accurate lung nodule detection schemes that correctly differentiate lung nodules from non-nodule structures including vessel junctions and airway trees at low false positive rates
3. To develop risk prediction models that can accurately predict the risk of lung cancer occurring over sequential examinations

Collaborators

1. University of Malaya
2. Bioinformatics Institute, Agency for Science, Technology and Research, (A*STAR) Singapore