Automatic musculoskeletal analysis of the spine in low dose chest CT scans using machine learning techniques
Principal Investigator
Name
Guillaume Chabin
Degrees
M.Sc.
Institution
Siemens Healthcare SAS
Position Title
Research Scientist
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-518
Initial CDAS Request Approval
Jun 5, 2019
Title
Automatic musculoskeletal analysis of the spine in low dose chest CT scans using machine learning techniques
Summary
Musculoskeletal analysis of the spine in lung cancer screening CT images could potentially reveal compression fractures or osteoporosis risks for patients without further imaging. However, manual quantification of compression fractures or osteoporosis is infeasible in the current clinical routine due to increasing number of screening scans. In this project, we will explore the use several machine learning algorithms to detect and quantify vertebra compression fractures as well as osteoporosis in low-dose chest CT images. A small randomly selected subset of the data will be used for training the machine learning algorithm. Remaining large dataset will be used to perform quantitative evaluation and to understand generalization abilities of the proposed algorithms.
Aims
1. Develop an automated fracture quantification algorithm in low-dose chest CT
2. Develop an automated osteoporosis quantification algorithm in low-dose chest CT
3. Perform a quantitative evaluation of the algorithms in a large dataset
Collaborators
None