Enhancing Lung Nodule Detection and Characterization Using NLST Data
Principal Investigator
Name
Adam Harrison
Institution
Riverain Technologies
Position Title
Director of Research Operations
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-1410
Initial CDAS Request Approval
Mar 25, 2025
Title
Enhancing Lung Nodule Detection and Characterization Using NLST Data
Summary
Riverain’s ClearRead solutions significantly enhance clinicians' abilities to detect and characterize lung nodules with greater accuracy and efficiency in both CT and X-ray imaging. These advancements are particularly critical for addressing the challenges associated with early lung disease detection.
To further evaluate and refine our models, Riverain will leverage the National Lung Screening Trial (NLST) dataset. This comprehensive collection of CT and X-ray images along with associated demographic and pathological information will provide a valuable resource for assessing model performance across a wide range of nodule types, ultimately improving diagnostic accuracy and clinical outcomes. In particular, the pathological assessments within the NLST data will allow Riverain to evaluate performance on three critical lung nodule categories: benign, benign biopsied, and malignant.
Aims
1- Assess the effectiveness of our algorithms in detecting and characterizing various types of lung nodules using CT data on nodules within the NLST data.
2- Assess the effectiveness of our algorithms in detecting and characterizing various types of lung nodules using X-ray data on nodules within the NLST data.
Collaborators
Jason Knapp, Chief Technology Officer, Riverain Technologies
Bo Gong, Senior Research Scientist, Riverain Technologies
Dennis Wu, Senior Research Scientist, Riverain Technologies
Jonathan Yerkins, Research Scientist, Riverain Technologies