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
kl419@rci.rutgers.edu

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.