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.

Image processing algorithm to screen for lung cancer on radiology images

Principal Investigator
Name
Alexandros Karargyris
Degrees
PhD
Institution
IBM
Position Title
Software Engineering Researcher
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCO-214
Initial CDAS Request Approval
Jun 15, 2016
Title
Image processing algorithm to screen for lung cancer on radiology images
Summary
Medical Sieve is an ambitious long-term exploratory grand challenge project to build a next generation cognitive assistant with advanced multimodal analytics, clinical knowledge and reasoning capabilities that is qualified to assist in clinical decision making in radiology and cardiology. The project aims at producing a sieve that filters essential clinical and diagnostic imaging information to form anomaly-driven summaries and recommendations that tremendously reduce the viewing load of clinicians without negatively impacting diagnosis. More information about the project can be found here: http://researcher.watson.ibm.com/researcher/view_group.php?id=4384
Aims

1) To investigate whether hardcrafted image features can help with CXR image classification as normal versus abnormal in terms of lung disease (e.g. lung cancer). To provide accuracy results.
2) To investigate whether deep learning approaches can help with CXR image classification as normal versus abnormal in terms of lung disease (e.g. lung cancer). To provide accuracy results.
3) To investigate whether patient demographics and metadata from patients' records coupled with aforementioned image features can improve overall classification accuracy.
4) To investigate whether aforementioned image features can help with disease progression prediction.

Collaborators

Tanveer Syeda-Mahmood
Hongzhi Wang
Ehsan Dehgan Marvast
Tyler Baldwin