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.

Lung disease detection and measuring algorithms on chest X ray images.

Principal Investigator

Name
Joseph Chui

Degrees
MSc

Institution
Ferrum Health, Inc.

Position Title
Machine Vision Engineer

Email
joe@ferrumhealth.com

About this CDAS Project

Study
PLCO (Learn more about this study)

Project ID
PLCO-491

Initial CDAS Request Approval
Jul 11, 2019

Title
Lung disease detection and measuring algorithms on chest X ray images.

Summary
Our algorithms use chest X ray images, diagnosis and patient demographics to train and validate inference models to:
Detect lung nodules and other lung/chest abnormalities, such as Granuloma and cardiac abnormalities, and measure their properties and characteristics.
It is important for our algorithms to train and validate the models, not only with data from patients of cancer or other abnormalities, but also with data from patients of negative diagnoses. The amount of data of negative findings in PLCO can become very valuable to the proposed project.
Our proposed project aims to train and validate statistical models using PLCO data as well as other datasets to improve the inference quality of the models.
With our granted access to the CT images of NLST, we are intending to investigate the inferring performances from models based on different imaging modalities.

Aims

Aim 1: Improving the quality of the inference models by including PLCO data in model training, and to validate the models with PLCO data held out from the training.
Aim 2: Assessing correlations of inference results between models using CT images and models using X Ray images.

Collaborators

Ferrum Health