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 Diagnostic System for Lung Nodule Detection, Localization, Attribution, and Classification using Deep Learning

Principal Investigator
Name
Devon Bernard
Degrees
B.S.
Institution
Hive Medical
Position Title
CTO
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-601
Initial CDAS Request Approval
Nov 13, 2019
Title
Computer-Aided Diagnostic System for Lung Nodule Detection, Localization, Attribution, and Classification using Deep Learning
Summary
This project will focus on developing a deep learning model for estimating likelihood of lung nodule malignancy in LDCTs. To train this model, we will first develop segmentation, localization, and characterization models that will feed results into the final neural network. The goal is developing software tools and a CAD screening system for lung cancer. This project will entail additional labeling of cases with model-specific features to enhance the existing dataset and testing a variety of convolutional neural networks and deep learning models.
Aims

1) Create a model for anatomic lung segmentation of lobes and bronchi.
2) Create a model for detecting and localizing nodules.
3) Create a model for characterizing nodules (size, volume, calcification pattern, lobulation, spiculation, pleural retraction).
4) Create a model for estimating nodule malignancy likelihood and Lung-RADS category classification.

Collaborators

Hive Medical