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.

Instance-driven semantic segmentation and clinical information assessment of temporal changes for lung nodules

Principal Investigator
Name
Kang Li
Degrees
Ph.D.
Institution
Department of Industrial and Systems Engineering
Position Title
Assistant Professor
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-261
Initial CDAS Request Approval
Dec 5, 2016
Title
Instance-driven semantic segmentation and clinical information assessment of temporal changes for lung nodules
Summary
The main objective of this proposal is to develop and validate a fully-automatic computer system for nodule detection and monitoring from 3D CT scans. We plan to develop a clinically usable CAD (Computer Assisted Diagnosis) system for lung cancer, which will be used as an aid for clinical practitioners.
Aims

To fulfill the objective, we design our research in two phases.

Phase 1: we aim to develop novel algorithms on which our system will be based. The investigators have been developing various methods for pulmonary nodule detection and vasculature segmentation over the last several years. Phase 1 of this proposal focuses on improving the accuracy and consistency of the existing methods through extensive testing and validation, as well as developing other image processing methods that are needed to fully implement the system. In this phase, we will demonstrate the feasibility of our methods.

Phase 2: we plan to improve and refine the methods developed in Phase 1 and to incorporate them into a publicly available software system for real-world clinical use. The system will be able to detect nodules less than 5mm in size identify (register) corresponding nodules in CT scans of a patient taken at different times, and assess the growth rate of nodules.

Collaborators

Prof. Kang Li, Ph.D.
Assistant Professor, Department of Industrial and Systems Engineering
Rutgers University, U.S.

Chaowei Tan, candidate of Ph.D.
Rutgers University, U.S.