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.

Validating the performance of Deep Neural Network models for lung nodule detection

Principal Investigator
Name
Naglis Ramanauskas
Degrees
M.D.
Institution
Oxipit, UAB
Position Title
Chief Medical Officer
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-886
Initial CDAS Request Approval
Feb 16, 2022
Title
Validating the performance of Deep Neural Network models for lung nodule detection
Summary
Lung nodule detection and quantification is one of most consuming and time challenging tasks in radiology. Solutions which can improve radiologist's specificity/sensitivity on this task can improve patient outcomes in terms of early cancer detection. The NLST dataset would serve as a real-world validation dataset to evaluate the performance of available DNN models in a cancer screening setting.
Aims

1) Evaluate available lung nodule detection models.
2) Quantify the performance uplift in terms of reduction of false negatives/false positives.
3) Analyse what-if scenarios in terms of detecting missed nodules sooner retrospectively.

Collaborators

The research team of Oxipit, UAB