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.

Computer-aided assessment of the chest from a Lung Cancer Screening population

Principal Investigator
Name
Benedikt Graf
Degrees
Ph.D.
Institution
IBM Watson Health
Position Title
Senior Scientist, Imaging Analytics
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-394
Initial CDAS Request Approval
Mar 9, 2018
Title
Computer-aided assessment of the chest from a Lung Cancer Screening population
Summary
Lung cancer accounts for the largest number of cancer related deaths in the US every year. Lung Cancer Screening (LCS) with an annual low-dose chest CT scan has been recommended for at-risk population by the U.S. Preventive Services Task Force. LCS participants are typically also at risk of developing other diseases due to their smoking history. Therefore, LCS related data (images, clinical readings, diagnostic outcomes, and treatment recommendations) provide a rich source to evaluate the overall health of the chest for LCS participants.

In this project, we aim to develop and validate automated computer algorithms based on computer vision and machine learning that assess the chest and report abnormalities and/or risk factors. The algorithms will leverage image data as well as other relevant information. The automatically generated findings will be validated against clinical findings present in the NLST data.
Aims

1. Develop and validate algorithms that assess the lung and report abnormal findings in the lung (i.e. nodules, lung parenchymal diseases)
2. Develop and validate algorithms that assess other chest regions (i.e. heart) and measure disease related biomarkers such as the coronary artery calcium

Collaborators

Benedikt Graf, IBM Watson Health
Arkadiusz Sitek, IBM Watson Health
Yiting Xie, IBM Watson Health
Emily Lindemer, IBM Watson Health
Paul Dufort, IBM Watson Health
David Richmond, IBM Watson Health
Lilla Boroczky, IBM Watson Health