Dynamic evolution and subtype qualitative analysis of early lung nodule from longitudinal CT images based on deep model
Principal Investigator
Name
Changmiao Wang
Degrees
Ph.D.
Institution
Shenzhen Research Institute of Big Data
Position Title
Associate Professor
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-897
Initial CDAS Request Approval
Mar 22, 2022
Title
Dynamic evolution and subtype qualitative analysis of early lung nodule from longitudinal CT images based on deep model
Summary
Lung cancer ranks the first in the global incidence of malignant tumors. Early CT screening of lung cancer can benefit patients and significantly reduce the mortality rate of lung cancer. In this proposal, the main objective aims to combine the imaging, pathology report, with the qualitative analysis of early lung nodule as the main line. Firstly, we will focus on the study the fine-grained analysis of component density. Second, high-throughput imaging characteristics and deep learning features of early lung nodule will be fused together. Thirdly, we will provide the qualitative analysis of the dynamic evolution of continuous time series CT images of early lung nodule.
Aims
The expected research results will further improve the early detection and accurate diagnosis of lung nodule. It can also provide scientific and feasible guidance for early diagnosis, early treatment and personalized treatment of early lung nodule.
Collaborators
Changmiao Wang, Shenzhen Research Institue of Big Data