Interfaces and algorithms to interactively improve medical datasets for machine learning

Galmed is creating leading edge medical image processing technology that exploits machine learning to empower physicians and improve patient care. The success of our algorithms depends on the availability of high-quality data, which in our current study means working with chest x-ray images (CXRs) that are accurately labeled with the findings that a radiologist would report in their examination.
The goal of this study is to identify and adapt algorithms and their corresponding user interfaces to make significant improvements to the sample CXR dataset at our disposal, while leveraging the limited time available from expert label reviewers. As the larger machine learning community far outside medical field relies on weakly-labeled but large publicly-available datasets, this study has a potentially broad impact.
Results from this study will be directly used in the development of Galmeds products, benefitting Galmed, the Canadian economy, and patients in hospitals where Galmeds software is used.

Faculty Supervisor:

Leonid Sigal

Student:

Borna Ghotbi

Partner:

Galiano Medical Solutions Inc

Discipline:

Computer science

Sector:

Medical devices

University:

Program: