Automatic diagnosis of chest x ray
Principal Investigator
Name
Pheng-Ann Heng
Degrees
Ph.D
Institution
The Chinese University of Hong Kong
Position Title
Professor
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-490
Initial CDAS Request Approval
Jul 11, 2019
Title
Automatic diagnosis of chest x ray
Summary
We aim to develop automatic algorithms for detecting potential chest diseases from chest X-ray images. We would like to take advantage of large scale public datasets from different organizations including ours. We would also like to first do a cross-test over different data source to evaluate whether reasons like race, machine code would affect the performance of current machine learning methods. What's more, we wish to develop a robust algorithm that can perform well on generic data. The demographic data from the report could be used to obtain more information about the population distribution, which could be used in our further analysis.
Aims
-Develop automatic diagnosis algorithm for chest x-ray images.
-Explore better deep learning methods for medical images analysis.
-Cross-validation on different datasets with deep learning with the help of demographic data.
-Take advantage of state-of-the-art machine learning approaches to develop a more general algorithm.
Collaborators
-Hao Chen, The Chinese University of Hong Kong
-Pheng-Ann Heng, The Chinese University of Hong Kong